agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 3/5] Make archiver process an auxiliary process 281+ messages / 7 participants [nested] [flat]
* [PATCH 3/5] Make archiver process an auxiliary process @ 2018-11-07 07:53 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2018-11-07 07:53 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data wes moved onto shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/bootstrap/bootstrap.c | 8 +++ src/backend/postmaster/pgarch.c | 98 +++++++---------------------- src/backend/postmaster/pgstat.c | 6 ++ src/backend/postmaster/postmaster.c | 43 ++++++++----- src/include/miscadmin.h | 2 + src/include/pgstat.h | 1 + src/include/postmaster/pgarch.h | 4 +- 7 files changed, 70 insertions(+), 92 deletions(-) diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index bfc629c753..2f38420313 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -326,6 +326,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: statmsg = pgstat_get_backend_desc(B_STARTUP); break; + case ArchiverProcess: + statmsg = pgstat_get_backend_desc(B_ARCHIVER); + break; case BgWriterProcess: statmsg = pgstat_get_backend_desc(B_BG_WRITER); break; @@ -451,6 +454,11 @@ AuxiliaryProcessMain(int argc, char *argv[]) StartupProcessMain(); proc_exit(1); /* should never return */ + case ArchiverProcess: + /* don't set signals, archiver has its own agenda */ + PgArchiverMain(); + proc_exit(1); /* should never return */ + case BgWriterProcess: /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 3ca30badb2..6441e69e9a 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -78,7 +78,6 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* @@ -95,7 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); static void pgarch_exit(SIGNAL_ARGS); static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); @@ -111,75 +109,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -219,8 +148,8 @@ pgarch_forkexec(void) * The argc/argv parameters are valid only in EXEC_BACKEND case. However, * since we don't use 'em, it hardly matters... */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -252,8 +181,27 @@ PgArchiverMain(int argc, char *argv[]) static void pgarch_exit(SIGNAL_ARGS) { - /* SIGQUIT means curl up and die ... */ - exit(1); + PG_SETMASK(&BlockSig); + + /* + * We DO NOT want to run proc_exit() callbacks -- we're here because + * shared memory may be corrupted, so we don't want to try to clean up our + * transaction. Just nail the windows shut and get out of town. Now that + * there's an atexit callback to prevent third-party code from breaking + * things by calling exit() directly, we have to reset the callbacks + * explicitly to make this work as intended. + */ + on_exit_reset(); + + /* + * Note we do exit(2) not exit(0). This is to force the postmaster into a + * system reset cycle if some idiot DBA sends a manual SIGQUIT to a random + * process. This is necessary precisely because we don't clean up our + * shared memory state. (The "dead man switch" mechanism in pmsignal.c + * should ensure the postmaster sees this as a crash, too, but no harm in + * being doubly sure.) + */ + exit(2); } /* SIGUSR1 signal handler for archiver process */ diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c index 51c486bebd..ca5c6376e5 100644 --- a/src/backend/postmaster/pgstat.c +++ b/src/backend/postmaster/pgstat.c @@ -2927,6 +2927,9 @@ pgstat_bestart(void) case StartupProcess: lbeentry.st_backendType = B_STARTUP; break; + case ArchiverProcess: + beentry->st_backendType = B_ARCHIVER; + break; case BgWriterProcess: lbeentry.st_backendType = B_BG_WRITER; break; @@ -4273,6 +4276,9 @@ pgstat_get_backend_desc(BackendType backendType) switch (backendType) { + case B_ARCHIVER: + backendDesc = "archiver"; + break; case B_AUTOVAC_LAUNCHER: backendDesc = "autovacuum launcher"; break; diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7a92dac525..ee41d7009e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -146,7 +146,8 @@ #define BACKEND_TYPE_AUTOVAC 0x0002 /* autovacuum worker process */ #define BACKEND_TYPE_WALSND 0x0004 /* walsender process */ #define BACKEND_TYPE_BGWORKER 0x0008 /* bgworker process */ -#define BACKEND_TYPE_ALL 0x000F /* OR of all the above */ +#define BACKEND_TYPE_ARCHIVER 0x0010 /* archiver process */ +#define BACKEND_TYPE_ALL 0x001F /* OR of all the above */ #define BACKEND_TYPE_WORKER (BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER) @@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1787,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3042,7 +3044,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3177,20 +3179,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3438,7 +3436,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3643,6 +3641,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3915,6 +3925,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5190,7 +5201,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5475,6 +5486,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 62d64aa0a1..dc7dd1c164 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -397,6 +397,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -409,6 +410,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 36b530bc27..0334213b98 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -718,6 +718,7 @@ typedef struct PgStat_GlobalStats */ typedef enum BackendType { + B_ARCHIVER, B_AUTOVAC_LAUNCHER, B_AUTOVAC_WORKER, B_BACKEND, diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ -- 2.23.0 ----Next_Part(Wed_Jan_22_17_24_04_2020_620)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v24 3/5] Make archiver process an auxiliary process @ 2018-11-07 07:53 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2018-11-07 07:53 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data wes moved onto shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/bootstrap/bootstrap.c | 8 +++ src/backend/postmaster/pgarch.c | 98 +++++++---------------------- src/backend/postmaster/pgstat.c | 6 ++ src/backend/postmaster/postmaster.c | 35 ++++++++--- src/include/miscadmin.h | 2 + src/include/pgstat.h | 1 + src/include/postmaster/pgarch.h | 4 +- 7 files changed, 67 insertions(+), 87 deletions(-) diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 8ea033610d..6e38f9a3d2 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -329,6 +329,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case BgWriterProcess: statmsg = pgstat_get_backend_desc(B_BG_WRITER); break; + case ArchiverProcess: + statmsg = pgstat_get_backend_desc(B_ARCHIVER); + break; case CheckpointerProcess: statmsg = pgstat_get_backend_desc(B_CHECKPOINTER); break; @@ -456,6 +459,11 @@ AuxiliaryProcessMain(int argc, char *argv[]) BackgroundWriterMain(); proc_exit(1); /* should never return */ + case ArchiverProcess: + /* don't set signals, archiver has its own agenda */ + PgArchiverMain(); + proc_exit(1); /* should never return */ + case CheckpointerProcess: /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index f84f882c4c..4342ebdab4 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -77,7 +77,6 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* @@ -96,7 +95,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); static void pgarch_exit(SIGNAL_ARGS); static void ArchSigHupHandler(SIGNAL_ARGS); static void ArchSigTermHandler(SIGNAL_ARGS); @@ -114,75 +112,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -222,8 +151,8 @@ pgarch_forkexec(void) * The argc/argv parameters are valid only in EXEC_BACKEND case. However, * since we don't use 'em, it hardly matters... */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -255,8 +184,27 @@ PgArchiverMain(int argc, char *argv[]) static void pgarch_exit(SIGNAL_ARGS) { - /* SIGQUIT means curl up and die ... */ - exit(1); + PG_SETMASK(&BlockSig); + + /* + * We DO NOT want to run proc_exit() callbacks -- we're here because + * shared memory may be corrupted, so we don't want to try to clean up our + * transaction. Just nail the windows shut and get out of town. Now that + * there's an atexit callback to prevent third-party code from breaking + * things by calling exit() directly, we have to reset the callbacks + * explicitly to make this work as intended. + */ + on_exit_reset(); + + /* + * Note we do exit(2) not exit(0). This is to force the postmaster into a + * system reset cycle if some idiot DBA sends a manual SIGQUIT to a random + * backend. This is necessary precisely because we don't clean up our + * shared memory state. (The "dead man switch" mechanism in pmsignal.c + * should ensure the postmaster sees this as a crash, too, but no harm in + * being doubly sure.) + */ + exit(2); } /* SIGHUP signal handler for archiver process */ diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c index fabcf31de8..8299d2a435 100644 --- a/src/backend/postmaster/pgstat.c +++ b/src/backend/postmaster/pgstat.c @@ -2932,6 +2932,9 @@ pgstat_bestart(void) case StartupProcess: lbeentry.st_backendType = B_STARTUP; break; + case ArchiverProcess: + beentry->st_backendType = B_ARCHIVER; + break; case BgWriterProcess: lbeentry.st_backendType = B_BG_WRITER; break; @@ -4275,6 +4278,9 @@ pgstat_get_backend_desc(BackendType backendType) switch (backendType) { + case B_ARCHIVER: + backendDesc = "archiver"; + break; case B_AUTOVAC_LAUNCHER: backendDesc = "autovacuum launcher"; break; diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 9ff2832c00..84fda38249 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -146,7 +146,8 @@ #define BACKEND_TYPE_AUTOVAC 0x0002 /* autovacuum worker process */ #define BACKEND_TYPE_WALSND 0x0004 /* walsender process */ #define BACKEND_TYPE_BGWORKER 0x0008 /* bgworker process */ -#define BACKEND_TYPE_ALL 0x000F /* OR of all the above */ +#define BACKEND_TYPE_ARCHIVER 0x0010 /* archiver process */ +#define BACKEND_TYPE_ALL 0x001F /* OR of all the above */ #define BACKEND_TYPE_WORKER (BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER) @@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1787,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3042,7 +3044,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3187,10 +3189,8 @@ reaper(SIGNAL_ARGS) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3438,7 +3438,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3643,6 +3643,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3915,6 +3927,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5190,7 +5203,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5475,6 +5488,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index bc6e03fbc7..1f4db67f3f 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -399,6 +399,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -411,6 +412,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/pgstat.h b/src/include/pgstat.h index fe076d823d..65713abc2b 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -718,6 +718,7 @@ typedef struct PgStat_GlobalStats */ typedef enum BackendType { + B_ARCHIVER, B_AUTOVAC_LAUNCHER, B_AUTOVAC_WORKER, B_BACKEND, diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index 2474eac26a..88f16863d4 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ -- 2.23.0 ----Next_Part(Tue_Dec__3_17_27_59_2019_887)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v24-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v33 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cdd586fcfb..ee3444284b 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 160afe9f39..9de9396628 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3068,7 +3069,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3203,20 +3204,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3464,7 +3461,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3669,6 +3666,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3941,6 +3950,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5216,7 +5226,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5259,16 +5269,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5501,6 +5501,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 5aa19d3f78..7acc48734e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -187,6 +187,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index e917dfe92d..0783692c83 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index ae4f573ab4..1a8a0c2e15 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -272,6 +272,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.2 ----Next_Part(Fri_May_15_17_30_36_2020_111)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v33-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v29 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlog.c | 46 ++++++++++ src/backend/access/transam/xlogarchive.c | 2 +- src/backend/bootstrap/bootstrap.c | 22 ++--- src/backend/postmaster/pgarch.c | 102 ++++------------------- src/backend/postmaster/postmaster.c | 53 ++++++------ src/include/access/xlog.h | 2 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - 10 files changed, 108 insertions(+), 127 deletions(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 977d448f50..d75a257da2 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -684,6 +684,13 @@ typedef struct XLogCtlData */ Latch recoveryWakeupLatch; + /* + * archiverWakeupLatch is used to wake up the archiver process to process + * completed WAL segments, if it is waiting for WAL to arrive. Protected + * by info_lck. + */ + Latch *archiverWakeupLatch; + /* * During recovery, we keep a copy of the latest checkpoint record here. * lastCheckPointRecPtr points to start of checkpoint record and @@ -8450,6 +8457,45 @@ GetLastSegSwitchData(XLogRecPtr *lastSwitchLSN) return result; } +/* + * XLogArchiveWakeupStart - Set up archiver wakeup stuff + */ +void +XLogArchiveWakeupStart(void) +{ + SpinLockAcquire(&XLogCtl->info_lck); + Assert(XLogCtl->archiverWakeupLatch == NULL); + XLogCtl->archiverWakeupLatch = MyLatch; + SpinLockRelease(&XLogCtl->info_lck); +} + +/* + * XLogArchiveWakeupEnd - Clean up archiver wakeup stuff + */ +void +XLogArchiveWakeupEnd(void) +{ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->archiverWakeupLatch = NULL; + SpinLockRelease(&XLogCtl->info_lck); +} + +/* + * XLogWakeupArchiver - Wake up archiver process + */ +void +XLogArchiveWakeup(void) +{ + Latch *latch; + + SpinLockAcquire(&XLogCtl->info_lck); + latch = XLogCtl->archiverWakeupLatch; + SpinLockRelease(&XLogCtl->info_lck); + + if (latch) + SetLatch(latch); +} + /* * This must be called ONCE during postmaster or standalone-backend shutdown */ diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index d62c12310a..d6c8bcce8b 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -490,7 +490,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + XLogArchiveWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..6fe7a136ba 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,7 +79,6 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* @@ -95,8 +95,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +108,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +141,21 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ +/* Clean up notification stuff on exit */ +static void +PgArchiverKill(int code, Datum arg) +{ + XLogArchiveWakeupEnd(); +} + /* * PgArchiverMain * * The argc/argv parameters are valid only in EXEC_BACKEND case. However, * since we don't use 'em, it hardly matters... */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,7 +167,7 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); @@ -240,24 +176,14 @@ PgArchiverMain(int argc, char *argv[]) MyBackendType = B_ARCHIVER; init_ps_display(NULL); + XLogArchiveWakeupStart(); + on_shmem_exit(PgArchiverKill, 0); + pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 73d278f3b2..a4b9d212a2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -146,7 +146,8 @@ #define BACKEND_TYPE_AUTOVAC 0x0002 /* autovacuum worker process */ #define BACKEND_TYPE_WALSND 0x0004 /* walsender process */ #define BACKEND_TYPE_BGWORKER 0x0008 /* bgworker process */ -#define BACKEND_TYPE_ALL 0x000F /* OR of all the above */ +#define BACKEND_TYPE_ARCHIVER 0x0010 /* archiver process */ +#define BACKEND_TYPE_ALL 0x001F /* OR of all the above */ #define BACKEND_TYPE_WORKER (BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER) @@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1787,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3055,7 +3057,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3190,20 +3192,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3451,7 +3449,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3656,6 +3654,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3928,6 +3938,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5208,7 +5219,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5251,16 +5262,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5493,6 +5494,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 9ec7b31cce..c0e149d526 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -313,6 +313,8 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ -- 2.18.2 ----Next_Part(Wed_Apr__1_15_15_11_2020_923)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v29-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v30 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlog.c | 46 +++++++++ src/backend/access/transam/xlogarchive.c | 2 +- src/backend/bootstrap/bootstrap.c | 22 +++-- src/backend/postmaster/pgarch.c | 115 ++++------------------- src/backend/postmaster/postmaster.c | 53 ++++++----- src/include/access/xlog.h | 2 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - 10 files changed, 112 insertions(+), 136 deletions(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 977d448f50..d75a257da2 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -684,6 +684,13 @@ typedef struct XLogCtlData */ Latch recoveryWakeupLatch; + /* + * archiverWakeupLatch is used to wake up the archiver process to process + * completed WAL segments, if it is waiting for WAL to arrive. Protected + * by info_lck. + */ + Latch *archiverWakeupLatch; + /* * During recovery, we keep a copy of the latest checkpoint record here. * lastCheckPointRecPtr points to start of checkpoint record and @@ -8450,6 +8457,45 @@ GetLastSegSwitchData(XLogRecPtr *lastSwitchLSN) return result; } +/* + * XLogArchiveWakeupStart - Set up archiver wakeup stuff + */ +void +XLogArchiveWakeupStart(void) +{ + SpinLockAcquire(&XLogCtl->info_lck); + Assert(XLogCtl->archiverWakeupLatch == NULL); + XLogCtl->archiverWakeupLatch = MyLatch; + SpinLockRelease(&XLogCtl->info_lck); +} + +/* + * XLogArchiveWakeupEnd - Clean up archiver wakeup stuff + */ +void +XLogArchiveWakeupEnd(void) +{ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->archiverWakeupLatch = NULL; + SpinLockRelease(&XLogCtl->info_lck); +} + +/* + * XLogWakeupArchiver - Wake up archiver process + */ +void +XLogArchiveWakeup(void) +{ + Latch *latch; + + SpinLockAcquire(&XLogCtl->info_lck); + latch = XLogCtl->archiverWakeupLatch; + SpinLockRelease(&XLogCtl->info_lck); + + if (latch) + SetLatch(latch); +} + /* * This must be called ONCE during postmaster or standalone-backend shutdown */ diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index d62c12310a..d6c8bcce8b 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -490,7 +490,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + XLogArchiveWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..7b66cb5613 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,7 +79,6 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* @@ -95,8 +95,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +108,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +141,16 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Clean up notification stuff on exit */ +static void +PgArchiverKill(int code, Datum arg) +{ + XLogArchiveWakeupEnd(); +} + +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +162,23 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); - + XLogArchiveWakeupStart(); + on_shmem_exit(PgArchiverKill, 0); + pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 73d278f3b2..a4b9d212a2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -146,7 +146,8 @@ #define BACKEND_TYPE_AUTOVAC 0x0002 /* autovacuum worker process */ #define BACKEND_TYPE_WALSND 0x0004 /* walsender process */ #define BACKEND_TYPE_BGWORKER 0x0008 /* bgworker process */ -#define BACKEND_TYPE_ALL 0x000F /* OR of all the above */ +#define BACKEND_TYPE_ARCHIVER 0x0010 /* archiver process */ +#define BACKEND_TYPE_ALL 0x001F /* OR of all the above */ #define BACKEND_TYPE_WORKER (BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER) @@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1787,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3055,7 +3057,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3190,20 +3192,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3451,7 +3449,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3656,6 +3654,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3928,6 +3938,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5208,7 +5219,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5251,16 +5262,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5493,6 +5494,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 9ec7b31cce..c0e149d526 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -313,6 +313,8 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ -- 2.18.2 ----Next_Part(Wed_Apr__1_17_37_23_2020_570)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v30-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v31 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index d62c12310a..2f8672ac0c 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 73d278f3b2..e97995f973 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3055,7 +3056,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3190,20 +3191,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3451,7 +3448,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3656,6 +3653,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3928,6 +3937,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5208,7 +5218,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5251,16 +5261,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5493,6 +5493,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 9938cddb57..af4599bd82 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -187,6 +187,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 9ec7b31cce..4435df82b6 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -313,6 +313,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index d21780108b..a87e7dc711 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -272,6 +272,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.2 ----Next_Part(Fri_Apr__3_17_31_17_2020_104)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v31-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v32 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index d62c12310a..2f8672ac0c 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 73d278f3b2..e97995f973 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3055,7 +3056,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3190,20 +3191,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3451,7 +3448,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3656,6 +3653,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3928,6 +3937,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5208,7 +5218,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5251,16 +5261,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5493,6 +5493,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 9938cddb57..af4599bd82 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -187,6 +187,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 9ec7b31cce..4435df82b6 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -313,6 +313,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index d21780108b..a87e7dc711 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -272,6 +272,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.2 ----Next_Part(Tue_Apr__7_16_38_17_2020_299)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v32-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v33 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 55becd65d4..2417de72a0 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 0578e92ba9..2687d2af47 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3055,7 +3056,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3190,20 +3191,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3451,7 +3448,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3656,6 +3653,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3928,6 +3937,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5203,7 +5213,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5246,16 +5256,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5488,6 +5488,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 5aa19d3f78..7acc48734e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -187,6 +187,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 0a12afb59e..099da8cd76 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index ae4f573ab4..1a8a0c2e15 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -272,6 +272,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.2 ----Next_Part(Thu_Apr_30_13_22_05_2020_409)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v33-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v25 4/8] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/bootstrap/bootstrap.c | 22 +++++---- src/backend/postmaster/pgarch.c | 75 +---------------------------- src/backend/postmaster/postmaster.c | 43 +++++++++++------ src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- 5 files changed, 46 insertions(+), 100 deletions(-) diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..4971b3ae42 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -78,7 +78,6 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* @@ -95,7 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); @@ -110,75 +108,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -218,8 +147,8 @@ pgarch_forkexec(void) * The argc/argv parameters are valid only in EXEC_BACKEND case. However, * since we don't use 'em, it hardly matters... */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 2b9ab32293..cab7fb5381 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -146,7 +146,8 @@ #define BACKEND_TYPE_AUTOVAC 0x0002 /* autovacuum worker process */ #define BACKEND_TYPE_WALSND 0x0004 /* walsender process */ #define BACKEND_TYPE_BGWORKER 0x0008 /* bgworker process */ -#define BACKEND_TYPE_ALL 0x000F /* OR of all the above */ +#define BACKEND_TYPE_ARCHIVER 0x0010 /* archiver process */ +#define BACKEND_TYPE_ALL 0x001F /* OR of all the above */ #define BACKEND_TYPE_WORKER (BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER) @@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1787,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3055,7 +3057,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3190,20 +3192,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3451,7 +3449,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3656,6 +3654,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3928,6 +3938,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5208,7 +5219,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5493,6 +5504,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ -- 2.18.2 ----Next_Part(Thu_Mar_19_20_30_04_2020_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v25-0005-Use-latch-instead-of-SIGUSR1-to-wake-up-archiver.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v43 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index f39dc4ddf1..d69e20961d 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index a7ed93fdc1..edda899554 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 5d09822c81..8a4706a870 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -547,6 +547,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1787,7 +1788,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3041,7 +3042,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3176,20 +3177,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3437,7 +3434,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3642,6 +3639,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3938,6 +3947,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5185,7 +5195,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5230,16 +5240,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5481,6 +5481,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 7dc3911590..fc23539137 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index e77f76ae8a..a656910d02 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Dec_11_16_50_03_2020_915)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v43-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v44 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index f39dc4ddf1..d69e20961d 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index a7ed93fdc1..edda899554 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 5d09822c81..8a4706a870 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -547,6 +547,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1787,7 +1788,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3041,7 +3042,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3176,20 +3177,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3437,7 +3434,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3642,6 +3639,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3938,6 +3947,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5185,7 +5195,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5230,16 +5240,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5481,6 +5481,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 7dc3911590..fc23539137 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index e77f76ae8a..a656910d02 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Mon_Dec_21_17_16_20_2020_608)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v44-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v36 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 8f8734dc1d..2e6c322142 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 76b2f5066f..81bfaea869 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 42223c0f61..4c296dd214 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -554,6 +554,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1799,7 +1800,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3051,7 +3052,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3186,20 +3187,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3447,7 +3444,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3652,6 +3649,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3948,6 +3957,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5223,7 +5233,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5268,16 +5278,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5515,6 +5515,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index aa9fbd8054..9cc5226667 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Tue_Sep__8_17_55_57_2020_197)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v36-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v37 3/6] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 8f8734dc1d..2e6c322142 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 76b2f5066f..81bfaea869 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 959e3b8873..b811c961a6 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1800,7 +1801,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3450,7 +3447,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3951,6 +3960,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 88566bd9fa..746bed773e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Fri_Sep_25_09_27_26_2020_419)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v37-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v38 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cae93ab69d..6908bec2f9 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 76b2f5066f..81bfaea869 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 959e3b8873..b811c961a6 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1800,7 +1801,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3450,7 +3447,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3951,6 +3960,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 88566bd9fa..746bed773e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Thu_Oct__1_09_07_22_2020_252)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v38-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v39 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cae93ab69d..6908bec2f9 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 76b2f5066f..81bfaea869 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 959e3b8873..b811c961a6 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1800,7 +1801,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3450,7 +3447,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3951,6 +3960,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 88566bd9fa..746bed773e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Tue_Oct__6_10_06_44_2020_382)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v39-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v40 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cae93ab69d..6908bec2f9 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index a7ed93fdc1..edda899554 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 959e3b8873..b811c961a6 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1800,7 +1801,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3450,7 +3447,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3951,6 +3960,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 88566bd9fa..746bed773e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Wed_Nov__4_17_39_10_2020_208)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v40-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v41 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cae93ab69d..6908bec2f9 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index a7ed93fdc1..edda899554 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 959e3b8873..b811c961a6 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1800,7 +1801,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3450,7 +3447,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3951,6 +3960,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 88566bd9fa..746bed773e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Fri_Nov__6_09_27_56_2020_738)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v41-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v42 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cae93ab69d..6908bec2f9 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index a7ed93fdc1..edda899554 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index ed1b65358d..e3a520def9 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index b7799ed1d2..a1dd6964e9 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -547,6 +547,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3039,7 +3040,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3174,20 +3175,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3435,7 +3432,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3640,6 +3637,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3936,6 +3945,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5177,7 +5187,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5222,16 +5232,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5473,6 +5473,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 88566bd9fa..746bed773e 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -181,6 +181,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 221af87e71..65443063e8 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 72e3352398..bba002ad24 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -418,6 +418,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 9c9a50ae45..de20520b8c 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -345,6 +345,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.4 ----Next_Part(Wed_Nov_11_10_07_22_2020_796)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v42-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v34 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cdd586fcfb..ee3444284b 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 160afe9f39..9de9396628 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3068,7 +3069,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3203,20 +3204,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3464,7 +3461,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3669,6 +3666,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3941,6 +3950,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5216,7 +5226,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5259,16 +5269,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5501,6 +5501,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index f5eef6fa4e..46f0198510 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -187,6 +187,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index e917dfe92d..0783692c83 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 14fa127ab1..619b2f9c71 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1ee9000b2b..8ab6d859bb 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -270,6 +270,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.2 ----Next_Part(Mon_Jun__1_18_00_01_2020_089)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v34-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v35 4/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index cdd586fcfb..ee3444284b 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 5480a024e0..d398ce6f03 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index 37be0e2bbb..063d1323ea 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) pqsignal(SIGQUIT, SignalHandlerForCrashExit); pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index b4d475bb0b..30f3fc6ba1 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1785,7 +1786,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3068,7 +3069,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3203,20 +3204,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3464,7 +3461,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3669,6 +3666,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3941,6 +3950,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5216,7 +5226,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5259,16 +5269,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5501,6 +5501,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index f5eef6fa4e..46f0198510 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -187,6 +187,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index e917dfe92d..0783692c83 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 1c67de2ede..54ce0b97d7 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 18bc8a7b90..cf0b463eba 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index b3200874ca..e3ffc63f14 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index 56c5ec4481..c691acf8cd 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1ee9000b2b..8ab6d859bb 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -270,6 +270,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.18.2 ----Next_Part(Mon_Jun__8_17_32_04_2020_489)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v35-0005-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v51 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 194 ++++------------------- src/backend/postmaster/postmaster.c | 83 +++++----- src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 94 insertions(+), 236 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c219780c60 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,13 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,148 +75,29 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + ProcGlobal->archiverLatch = NULL; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..fd509869aa 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving of remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d71700a565 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -350,6 +350,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Archiver process's latch */ + Latch *archiverLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* The proc of the Startup process, since not in ProcArray */ @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_12_10_39_2021_432)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v51-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v52 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 224 ++++++++--------------- src/backend/postmaster/postmaster.c | 83 ++++----- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- 9 files changed, 139 insertions(+), 222 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..2558bcfb08 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,13 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..c399e6c267 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,68 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver ", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +210,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +248,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +270,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..34c8551288 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and + * PostmasterStateMachine() will advance to the next shutdown step. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + if (PgArchStartupAllowed()) + PgArchPID = StartArchiver(); + continue; + } + /* Was it the system logger? If so, try to start a new one */ if (pid == SysLoggerPID) { @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Wed_Mar_10_17_51_37_2021_192)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v52-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v45 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index db0cfaa360..aabf9d73eb 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Jan__8_10_24_34_2021_185)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v45-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v46 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 0786fcf103..430d438303 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -354,6 +354,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_14_15_14_25_2021_903)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v46-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v47 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 7de27ee4e0..af91c313e2 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1788,7 +1789,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3423,7 +3420,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3932,6 +3941,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index c87ffc6549..a1e51c5b99 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 683ab64f76..6cdaf3753d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -355,6 +355,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Thu_Jan_21_12_03_48_2021_284)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v47-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v48 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 6 +- src/backend/bootstrap/bootstrap.c | 22 ++-- src/backend/postmaster/pgarch.c | 130 +++-------------------- src/backend/postmaster/postmaster.c | 50 +++++---- src/backend/storage/lmgr/proc.c | 1 + src/include/access/xlog.h | 3 + src/include/access/xlogarchive.h | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 4 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 3 + 11 files changed, 69 insertions(+), 154 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..d01859bde5 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,9 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" +#include "storage/latch.h" #include "storage/pmsignal.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..9a2e21bf86 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,13 +79,11 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- @@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false; static pid_t pgarch_forkexec(void); #endif -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog); * ------------------------------------------------------------ */ -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - /* ------------------------------------------------------------ * Local functions called by archiver follow * ------------------------------------------------------------ @@ -212,14 +140,9 @@ pgarch_forkexec(void) #endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; -} - /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +198,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +236,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +258,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..22e1cd244c 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. + * Was it the archiver? Normal exit can be ignored; we'll start a new + * one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. */ if (pid == PgArchPID) { PgArchPID = 0; if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + HandleChildCrash(pid, exitstatus, + _("archiver process")); continue; } @@ -3403,7 +3400,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) + { + ereport(DEBUG2, + (errmsg_internal("sending %s to process %d", + (SendStop ? "SIGSTOP" : "SIGQUIT"), + (int) PgArchPID))); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); + } + /* * Force a power-cycle of the pgarch process too. (This isn't absolutely * necessary, but it seems like a good idea for robustness, and it @@ -3912,6 +3921,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 75ec1073bd..551f518cc2 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void); extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); +extern void XLogArchiveWakeupStart(void); +extern void XLogArchiveWakeupEnd(void); +extern void XLogArchiveWakeup(void); extern void RemovePromoteSignalFiles(void); extern bool PromoteIsTriggered(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..1a59181cf9 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName, extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveWakeup(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..385b002dfe 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -32,8 +32,6 @@ */ extern int pgarch_start(void); -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..491747c113 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,9 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; + /* Current shared estimate of appropriate spins_per_delay value */ } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; -- 2.27.0 ----Next_Part(Fri_Mar__5_17_18_56_2021_497)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v48-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v49 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_16_53_11_2021_575)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v49-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v50 3/7] Make archiver process an auxiliary process @ 2020-03-13 07:59 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw) This is a preliminary patch for shared-memory based stats collector. Archiver process must be a auxiliary process since it uses shared memory after stats data was moved into shared-memory. Make the process an auxiliary process in order to make it work. --- src/backend/access/transam/xlogarchive.c | 7 +- src/backend/bootstrap/bootstrap.c | 22 +-- src/backend/postmaster/pgarch.c | 174 +++-------------------- src/backend/postmaster/postmaster.c | 88 ++++++------ src/backend/storage/lmgr/proc.c | 1 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 10 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 10 +- 9 files changed, 83 insertions(+), 232 deletions(-) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..8b66a30931 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -29,7 +29,8 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" +#include "storage/latch.h" +#include "storage/proc.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog) } /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + if (IsUnderPostmaster && ProcGlobal->archiverLatch) + SetLatch(ProcGlobal->archiverLatch); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..e237cedaff 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -48,6 +48,7 @@ #include "storage/latch.h" #include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -78,25 +79,17 @@ * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); @@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; - - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); -} -#endif /* EXEC_BACKEND */ - - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->archiverLatch = &MyProc->procLatch; pgarch_MainLoop(); - exit(0); -} - -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) -{ - int save_errno = errno; - - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + proc_exit(0); } /* SIGUSR2 signal handler for archiver process */ @@ -282,14 +156,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +194,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +216,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..d9f8d82650 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS) continue; } + /* + * Was it the archiver? We treat it the same way to WAL receiver. + */ + if (pid == PgArchPID) + { + PgArchPID = 0; + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); + continue; + } + /* * Was it the autovacuum launcher? Normal exit can be ignored; we'll * start a new one at the next iteration of the postmaster's main @@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS) continue; } - /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and - * PostmasterStateMachine() will advance to the next shutdown step. - */ - if (pid == PgArchPID) - { - PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); - if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); - continue; - } - /* * Was it the statistics collector? If so, just try to start a new * one; no need to force reset of the rest of the system. (If fail, @@ -3403,7 +3398,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3912,6 +3904,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[]) AuxiliaryProcessMain(argc - 2, argv + 2); /* does not return */ } + if (strcmp(argv[1], "--forkarch") == 0) + { + /* Restore basic shared memory pointers */ + InitShmemAccess(UsedShmemSegAddr); + + /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */ + InitAuxiliaryProcess(); + + /* Attach process to shared data structures */ + CreateSharedMemoryAndSemaphores(); + + PgArchiverMain(); /* does not return */ + } if (strcmp(argv[1], "--forkavlauncher") == 0) { /* Restore basic shared memory pointers */ @@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 897045ee27..bf5d6da89b 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -182,6 +182,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->archiverLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 1bdc97e308..adb9f819bb 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -419,6 +419,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..737ed69e57 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,6 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern void PgArchiverMain(void) pg_attribute_noreturn(); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..d73890b228 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -357,6 +357,8 @@ typedef struct PROC_HDR int startupProcPid; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Archiver process's latch */ + Latch *archiverLatch; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; @@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; -- 2.27.0 ----Next_Part(Tue_Mar__9_18_29_34_2021_806)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v50-0004-Shared-memory-based-stats-collector.patch" ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v53 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 227 ++++++++--------------- src/backend/postmaster/postmaster.c | 74 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 13 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 137 insertions(+), 218 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..818c9a1f3f 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,70 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + Latch *latch; /* latch to wake the archiver up */ + slock_t mutex; /* locks this struct */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) -{ - time_t curtime; - pid_t pgArchPid; + return size; +} - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif + if (!found) { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + SpinLockInit(&PgArch->mutex); + PgArch->latch = NULL; } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); } -#endif /* EXEC_BACKEND */ - -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = MyLatch; + SpinLockRelease(&PgArch->mutex); pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + Latch *latch; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); + /* fetching the latch pointer might not be atomic, so use spinlock */ + SpinLockAcquire(&PgArch->mutex); + latch = PgArch->latch; + SpinLockRelease(&PgArch->mutex); - errno = save_errno; + if (latch) + SetLatch(latch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +213,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +251,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +273,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + SpinLockAcquire(&PgArch->mutex); + PgArch->latch = NULL; + SpinLockRelease(&PgArch->mutex); +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..460e629145 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1793,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3406,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3804,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3911,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..d053bf1564 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,9 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_09_23_13_2021_947)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v54 3/7] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 241 +++++++++-------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 160 insertions(+), 217 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..8e572afea3 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,6 +71,12 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data @@ -80,146 +84,79 @@ */ static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) +{ + Size size = 0; -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ + size = add_size(size, sizeof(PgArchData)); + + return size; +} + +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; + + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); + + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; + } +} /* - * pgarch_start + * PgArchIsSuppressed * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. + * Return true if archiver relaunch is suppressed. * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -int -pgarch_start(void) +bool +PgArchIsSuppressed(void) { - time_t curtime; - pid_t pgArchPid; + time_t curtime = time(NULL); - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; + if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL) + return true; - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; last_pgarch_start_time = curtime; - -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); - - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); - - PgArchiverMain(0, NULL); - break; -#endif - - default: - return (int) pgArchPid; - } - - /* shouldn't get here */ - return 0; -} - -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - -/* - * pgarch_forkexec() - - * - * Format up the arglist for, then fork and exec, archive process - */ -static pid_t -pgarch_forkexec(void) -{ - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; - - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ - - av[ac] = NULL; - Assert(ac < lengthof(av)); - - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will be + * relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +237,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +275,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +297,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..4f8e364284 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + !PgArchIsSuppressed()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for it + * to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and syslogger + * processes are disregarded since they are not connected to shared + * memory; we also disregard dead_end children here. Walsenders and + * archiver are also disregarded, they will be terminated later after + * writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..640692d33e 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchIsSuppressed(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_13_49_06_2021_682)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* [PATCH v55 3/3] Make archiver process an auxiliary process @ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw) This makes it possible to archiver process uses ipc functions and let us monitor archiver process status. --- doc/src/sgml/monitoring.sgml | 1 + src/backend/access/transam/xlogarchive.c | 4 +- src/backend/bootstrap/bootstrap.c | 22 ++- src/backend/postmaster/pgarch.c | 240 ++++++++++------------- src/backend/postmaster/postmaster.c | 81 ++++---- src/backend/storage/ipc/ipci.c | 2 + src/include/miscadmin.h | 2 + src/include/postmaster/pgarch.h | 14 +- src/include/storage/pmsignal.h | 1 - src/include/storage/proc.h | 8 +- src/tools/pgindent/typedefs.list | 1 + 11 files changed, 164 insertions(+), 212 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1ba813bbb9..a96455bdb2 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -935,6 +935,7 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser <literal>logical replication worker</literal>, <literal>parallel worker</literal>, <literal>background writer</literal>, <literal>client backend</literal>, <literal>checkpointer</literal>, + <literal>archiver</literal>, <literal>startup</literal>, <literal>walreceiver</literal>, <literal>walsender</literal> and <literal>walwriter</literal>. In addition, background workers registered by extensions may have diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 1c5a4f8b5a..26b023e754 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -25,11 +25,11 @@ #include "common/archive.h" #include "miscadmin.h" #include "postmaster/startup.h" +#include "postmaster/pgarch.h" #include "replication/walsender.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/lwlock.h" -#include "storage/pmsignal.h" /* * Attempt to retrieve the specified file from off-line archival storage. @@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog) /* Notify archiver that it's got something to do */ if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER); + PgArchWakeup(); } /* diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..41da0c5059 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[]) case StartupProcess: MyBackendType = B_STARTUP; break; + case ArchiverProcess: + MyBackendType = B_ARCHIVER; + break; case BgWriterProcess: MyBackendType = B_BG_WRITER; break; @@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[]) proc_exit(1); /* should never return */ case StartupProcess: - /* don't set signals, startup process has its own agenda */ StartupProcessMain(); - proc_exit(1); /* should never return */ + proc_exit(1); + + case ArchiverProcess: + PgArchiverMain(); + proc_exit(1); case BgWriterProcess: - /* don't set signals, bgwriter has its own agenda */ BackgroundWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case CheckpointerProcess: - /* don't set signals, checkpointer has its own agenda */ CheckpointerMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalWriterProcess: - /* don't set signals, walwriter has its own agenda */ InitXLOGAccess(); WalWriterMain(); - proc_exit(1); /* should never return */ + proc_exit(1); case WalReceiverProcess: - /* don't set signals, walreceiver has its own agenda */ WalReceiverMain(); - proc_exit(1); /* should never return */ + proc_exit(1); default: elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType); diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c index edec311f12..07ba989a37 100644 --- a/src/backend/postmaster/pgarch.c +++ b/src/backend/postmaster/pgarch.c @@ -38,16 +38,14 @@ #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" -#include "postmaster/fork_process.h" #include "postmaster/interrupt.h" #include "postmaster/pgarch.h" -#include "postmaster/postmaster.h" -#include "storage/dsm.h" #include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" -#include "storage/pg_shmem.h" #include "storage/pmsignal.h" +#include "storage/procsignal.h" +#include "storage/spin.h" #include "utils/guc.h" #include "utils/ps_status.h" @@ -73,153 +71,101 @@ */ #define NUM_ORPHAN_CLEANUP_RETRIES 3 +/* Shared memory area for archiver process */ +typedef struct PgArchData +{ + int pgprocno; /* pgprocno of archiver process */ +} PgArchData; + /* ---------- * Local data * ---------- */ -static time_t last_pgarch_start_time; static time_t last_sigterm_time = 0; +static PgArchData *PgArch = NULL; /* * Flags set by interrupt handlers for later service in the main loop. */ -static volatile sig_atomic_t wakened = false; static volatile sig_atomic_t ready_to_stop = false; /* ---------- * Local function forward declarations * ---------- */ -#ifdef EXEC_BACKEND -static pid_t pgarch_forkexec(void); -#endif - -NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -static void pgarch_waken(SIGNAL_ARGS); static void pgarch_waken_stop(SIGNAL_ARGS); static void pgarch_MainLoop(void); static void pgarch_ArchiverCopyLoop(void); static bool pgarch_archiveXlog(char *xlog); static bool pgarch_readyXlog(char *xlog); static void pgarch_archiveDone(char *xlog); +static void pgarch_die(int code, Datum arg); - -/* ------------------------------------------------------------ - * Public functions called from postmaster follow - * ------------------------------------------------------------ - */ - -/* - * pgarch_start - * - * Called from postmaster at startup or after an existing archiver - * died. Attempt to fire up a fresh archiver process. - * - * Returns PID of child process, or 0 if fail. - * - * Note: if fail, we will be called again from the postmaster main loop. - */ -int -pgarch_start(void) +/* Report shared memory space needed by PgArchShmemInit */ +Size +PgArchShmemSize(void) { - time_t curtime; - pid_t pgArchPid; + Size size = 0; - /* - * Do nothing if no archiver needed - */ - if (!XLogArchivingActive()) - return 0; - - /* - * Do nothing if too soon since last archiver start. This is a safety - * valve to protect against continuous respawn attempts if the archiver is - * dying immediately at launch. Note that since we will be re-called from - * the postmaster main loop, we will get another chance later. - */ - curtime = time(NULL); - if ((unsigned int) (curtime - last_pgarch_start_time) < - (unsigned int) PGARCH_RESTART_INTERVAL) - return 0; - last_pgarch_start_time = curtime; + size = add_size(size, sizeof(PgArchData)); -#ifdef EXEC_BACKEND - switch ((pgArchPid = pgarch_forkexec())) -#else - switch ((pgArchPid = fork_process())) -#endif - { - case -1: - ereport(LOG, - (errmsg("could not fork archiver: %m"))); - return 0; - -#ifndef EXEC_BACKEND - case 0: - /* in postmaster child ... */ - InitPostmasterChild(); - - /* Close the postmaster's sockets */ - ClosePostmasterPorts(false); + return size; +} - /* Drop our connection to postmaster's shared memory, as well */ - dsm_detach_all(); - PGSharedMemoryDetach(); +/* Allocate and initialize archiver-related shared memory */ +void +PgArchShmemInit(void) +{ + bool found; - PgArchiverMain(0, NULL); - break; -#endif + PgArch = (PgArchData *) + ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found); - default: - return (int) pgArchPid; + if (!found) + { + /* First time through, so initialize */ + MemSet(PgArch, 0, PgArchShmemSize()); + PgArch->pgprocno = INVALID_PGPROCNO; } - - /* shouldn't get here */ - return 0; } -/* ------------------------------------------------------------ - * Local functions called by archiver follow - * ------------------------------------------------------------ - */ - - -#ifdef EXEC_BACKEND - /* - * pgarch_forkexec() - + * PgArchIsSuppressed * - * Format up the arglist for, then fork and exec, archive process + * Return true if archiver relaunch is suppressed. + * + * This is a safety valve to protect against continuous respawn attempts if the + * archiver is dying immediately at launch. Note that since we will retry to + * launch the archiver from the postmaster main loop, we will get another + * chance later. */ -static pid_t -pgarch_forkexec(void) +bool +PgArchCanRestart(void) { - char *av[10]; - int ac = 0; - - av[ac++] = "postgres"; + static time_t last_pgarch_start_time = 0; + time_t curtime = time(NULL); - av[ac++] = "--forkarch"; - - av[ac++] = NULL; /* filled in by postmaster_forkexec */ + /* + * allow to launch also for the first time and when something's wrong in + * the time values. + */ + if (last_pgarch_start_time == 0 || + curtime < last_pgarch_start_time || + (curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL) + { + last_pgarch_start_time = curtime; - av[ac] = NULL; - Assert(ac < lengthof(av)); + return true; + } - return postmaster_forkexec(ac, av); + return false; } -#endif /* EXEC_BACKEND */ -/* - * PgArchiverMain - * - * The argc/argv parameters are valid only in EXEC_BACKEND case. However, - * since we don't use 'em, it hardly matters... - */ -NON_EXEC_STATIC void -PgArchiverMain(int argc, char *argv[]) +/* Main entry point for archiver process */ +void +PgArchiverMain(void) { /* * Ignore all signals usually bound to some action in the postmaster, @@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[]) /* SIGQUIT handler was already set up by InitPostmasterChild */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); - pqsignal(SIGUSR1, pgarch_waken); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); pqsignal(SIGUSR2, pgarch_waken_stop); + /* Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); + + /* Unblock signals (they were blocked when the postmaster forked us) */ PG_SETMASK(&UnBlockSig); - MyBackendType = B_ARCHIVER; - init_ps_display(NULL); + /* We shouldn't be launched unnecessarily. */ + Assert(XLogArchivingActive()); + + /* Arrange to clean up at archiver exit */ + on_shmem_exit(pgarch_die, 0); + + /* + * Advertise our pgproc index so that backends can use our latch to wake + * us up while we're sleeping. + */ + PgArch->pgprocno = MyProc->pgprocno; pgarch_MainLoop(); - exit(0); + proc_exit(0); } -/* SIGUSR1 signal handler for archiver process */ -static void -pgarch_waken(SIGNAL_ARGS) +/* + * Wake up the archiver + */ +void +PgArchWakeup(void) { - int save_errno = errno; + int arch_pgprocno = PgArch->pgprocno; - /* set flag that there is work to be done */ - wakened = true; - SetLatch(MyLatch); - - errno = save_errno; + /* + * We don't acquire ProcArrayLock here. It's actually fine because + * procLatch isn't ever freed, so we just can potentially set the wrong + * process' (or no process') latch. Even in that case the archiver will + * be relaunched shortly and will start archiving. + */ + if (arch_pgprocno != INVALID_PGPROCNO) + SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch); } + /* SIGUSR2 signal handler for archiver process */ static void pgarch_waken_stop(SIGNAL_ARGS) @@ -282,14 +246,6 @@ pgarch_MainLoop(void) pg_time_t last_copy_time = 0; bool time_to_stop; - /* - * We run the copy loop immediately upon entry, in case there are - * unarchived files left over from a previous database run (or maybe the - * archiver died unexpectedly). After that we wait for a signal or - * timeout before doing more. - */ - wakened = true; - /* * There shouldn't be anything for the archiver to do except to wait for a * signal ... however, the archiver exists to protect our data, so she @@ -328,12 +284,8 @@ pgarch_MainLoop(void) } /* Do what we're here for */ - if (wakened || time_to_stop) - { - wakened = false; - pgarch_ArchiverCopyLoop(); - last_copy_time = time(NULL); - } + pgarch_ArchiverCopyLoop(); + last_copy_time = time(NULL); /* * Sleep until a signal is received, or until a poll is forced by @@ -354,13 +306,9 @@ pgarch_MainLoop(void) WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout * 1000L, WAIT_EVENT_ARCHIVER_MAIN); - if (rc & WL_TIMEOUT) - wakened = true; if (rc & WL_POSTMASTER_DEATH) time_to_stop = true; } - else - wakened = true; } /* @@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog) StatusFilePath(rlogdone, xlog, ".done"); (void) durable_rename(rlogready, rlogdone, WARNING); } + + +/* + * pgarch_die + * + * Exit-time cleanup handler + */ +static void +pgarch_die(int code, Datum arg) +{ + PgArch->pgprocno = INVALID_PGPROCNO; +} diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index edab95a19e..e8af05c04e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void); * even during recovery. */ #define PgArchStartupAllowed() \ - ((XLogArchivingActive() && pmState == PM_RUN) || \ - (XLogArchivingAlways() && \ - (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) + (((XLogArchivingActive() && pmState == PM_RUN) || \ + (XLogArchivingAlways() && \ + (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \ + PgArchCanRestart()) #ifdef EXEC_BACKEND @@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #endif /* EXEC_BACKEND */ #define StartupDataBase() StartChildProcess(StartupProcess) +#define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) @@ -1792,7 +1794,7 @@ ServerLoop(void) /* If we have lost the archiver, try to start a new one. */ if (PgArchPID == 0 && PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* If we need to signal the autovacuum launcher, do so now */ if (avlauncher_needs_signal) @@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS) if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0) AutoVacPID = StartAutoVacLauncher(); if (PgArchStartupAllowed() && PgArchPID == 0) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); if (PgStatPID == 0) PgStatPID = pgstat_start(); @@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS) } /* - * Was it the archiver? If so, just try to start a new one; no need - * to force reset of the rest of the system. (If fail, we'll try - * again in future cycles of the main loop.). Unless we were waiting - * for it to shut down; don't restart it in that case, and + * Was it the archiver? If exit status is zero (normal) or one (FATAL + * exit), we assume everything is all right just like normal backends + * and just try to restart a new one so that we immediately retry + * archiving remaining files. (If fail, we'll try again in future + * cycles of the postmaster's main loop.) Unless we were waiting for + * it to shut down; don't restart it in that case, and * PostmasterStateMachine() will advance to the next shutdown step. */ if (pid == PgArchPID) { PgArchPID = 0; - if (!EXIT_STATUS_0(exitstatus)) - LogChildExit(LOG, _("archiver process"), - pid, exitstatus); + if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("archiver process")); if (PgArchStartupAllowed()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); continue; } @@ -3403,7 +3407,7 @@ CleanupBackend(int pid, /* * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, - * walwriter, autovacuum, or background worker. + * walwriter, autovacuum, archiver or background worker. * * The objectives here are to clean up our local state about the child * process, and to signal all other remaining children to quickdie. @@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT)); } - /* - * Force a power-cycle of the pgarch process too. (This isn't absolutely - * necessary, but it seems like a good idea for robustness, and it - * simplifies the state-machine logic in the case where a shutdown request - * arrives during crash processing.) - */ - if (PgArchPID != 0 && take_action) + /* Take care of the archiver too */ + if (pid == PgArchPID) + PgArchPID = 0; + else if (PgArchPID != 0 && take_action) { ereport(DEBUG2, (errmsg_internal("sending %s to process %d", - "SIGQUIT", + (SendStop ? "SIGSTOP" : "SIGQUIT"), (int) PgArchPID))); - signal_child(PgArchPID, SIGQUIT); + signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT)); } /* @@ -3804,12 +3805,11 @@ PostmasterStateMachine(void) * (including autovac workers), no bgworkers (including unconnected * ones), and no walwriter, autovac launcher or bgwriter. If we are * doing crash recovery or an immediate shutdown then we expect the - * checkpointer to exit as well, otherwise not. The archiver, stats, - * and syslogger processes are disregarded since they are not - * connected to shared memory; we also disregard dead_end children - * here. Walsenders are also disregarded, they will be terminated - * later after writing the checkpoint record, like the archiver - * process. + * checkpointer to exit as well, otherwise not. The stats and + * syslogger processes are disregarded since they are not connected to + * shared memory; we also disregard dead_end children here. Walsenders + * and archiver are also disregarded, they will be terminated later + * after writing the checkpoint record. */ if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 && StartupPID == 0 && @@ -3912,6 +3912,7 @@ PostmasterStateMachine(void) Assert(CheckpointerPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); + Assert(PgArchPID == 0); /* syslogger is not considered here */ pmState = PM_NO_CHILDREN; } @@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[]) StartBackgroundWorker(); } - if (strcmp(argv[1], "--forkarch") == 0) - { - /* Do not want to attach to shared memory */ - - PgArchiverMain(argc, argv); /* does not return */ - } if (strcmp(argv[1], "--forkcol") == 0) { /* Do not want to attach to shared memory */ @@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS) */ Assert(PgArchPID == 0); if (XLogArchivingAlways()) - PgArchPID = pgarch_start(); + PgArchPID = StartArchiver(); /* * If we aren't planning to enter hot standby mode later, treat @@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS) if (StartWorkerNeeded || HaveCrashedWorker) maybe_start_bgworkers(); - if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) && - PgArchPID != 0) - { - /* - * Send SIGUSR1 to archiver process, to wake it up and begin archiving - * next WAL file. - */ - signal_child(PgArchPID, SIGUSR1); - } - /* Tell syslogger to rotate logfile if requested */ if (SysLoggerPID != 0) { @@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type) ereport(LOG, (errmsg("could not fork startup process: %m"))); break; + case ArchiverProcess: + ereport(LOG, + (errmsg("could not fork archiver process: %m"))); + break; case BgWriterProcess: ereport(LOG, (errmsg("could not fork background writer process: %m"))); diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index f9bbe97b50..3e4ec53a97 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, ReplicationOriginShmemSize()); size = add_size(size, WalSndShmemSize()); size = add_size(size, WalRcvShmemSize()); + size = add_size(size, PgArchShmemSize()); size = add_size(size, ApplyLauncherShmemSize()); size = add_size(size, SnapMgrShmemSize()); size = add_size(size, BTreeShmemSize()); @@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void) ReplicationOriginShmemInit(); WalSndShmemInit(); WalRcvShmemInit(); + PgArchShmemInit(); ApplyLauncherShmemInit(); /* diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index 54693e047a..013850ac28 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -417,6 +417,7 @@ typedef enum BootstrapProcess, StartupProcess, BgWriterProcess, + ArchiverProcess, CheckpointerProcess, WalWriterProcess, WalReceiverProcess, @@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType; #define AmBootstrapProcess() (MyAuxProcType == BootstrapProcess) #define AmStartupProcess() (MyAuxProcType == StartupProcess) #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) +#define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h index d102a21ab7..1e47a143e1 100644 --- a/src/include/postmaster/pgarch.h +++ b/src/include/postmaster/pgarch.h @@ -26,14 +26,10 @@ #define MAX_XFN_CHARS 40 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial" -/* ---------- - * Functions called from postmaster - * ---------- - */ -extern int pgarch_start(void); - -#ifdef EXEC_BACKEND -extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn(); -#endif +extern Size PgArchShmemSize(void); +extern void PgArchShmemInit(void); +extern bool PgArchCanRestart(void); +extern void PgArchiverMain(void) pg_attribute_noreturn(); +extern void PgArchWakeup(void); #endif /* _PGARCH_H */ diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h index dbbed18f61..8ed4d87ae6 100644 --- a/src/include/storage/pmsignal.h +++ b/src/include/storage/pmsignal.h @@ -34,7 +34,6 @@ typedef enum { PMSIGNAL_RECOVERY_STARTED, /* recovery has started */ PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */ - PMSIGNAL_WAKEN_ARCHIVER, /* send a NOTIFY signal to xlog archiver */ PMSIGNAL_ROTATE_LOGFILE, /* send SIGUSR1 to syslogger to rotate logfile */ PMSIGNAL_START_AUTOVAC_LAUNCHER, /* start an autovacuum launcher */ PMSIGNAL_START_AUTOVAC_WORKER, /* start an autovacuum worker */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a777cb64a1..2fd1ff09a7 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer and WAL writer run during normal operation. - * Startup process and WAL receiver also consume 2 slots, but WAL writer is - * launched only after startup has exited, so we only need 4 slots. + * Background writer, checkpointer, WAL writer and archiver run during normal + * operation. Startup process and WAL receiver also consume 2 slots, but WAL + * writer is launched only after startup has exited, so we only need 5 slots. */ -#define NUM_AUXILIARY_PROCS 4 +#define NUM_AUXILIARY_PROCS 5 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 99a34be465..78e852569e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1572,6 +1572,7 @@ PGresAttValue PGresParamDesc PGresult PGresult_data +PgArchData PHANDLE PLAINTREE PLUID_AND_ATTRIBUTES -- 2.27.0 ----Next_Part(Fri_Mar_12_17_24_43_2021_866)---- ^ permalink raw reply [nested|flat] 281+ messages in thread
* Re: Add the ability to limit the amount of memory that can be allocated to backends. @ 2024-01-23 11:47 Anton A. Melnikov <[email protected]> 0 siblings, 1 reply; 281+ messages in thread From: Anton A. Melnikov @ 2024-01-23 11:47 UTC (permalink / raw) To: Tomas Vondra <[email protected]>; Andres Freund <[email protected]>; Andrei Lepikhov <[email protected]>; +Cc: Stephen Frost <[email protected]>; [email protected]; Arne Roland <[email protected]>; [email protected] <[email protected]>; vignesh C <[email protected]>; Justin Pryzby <[email protected]>; Ibrar Ahmed <[email protected]>; stephen.frost <[email protected]> Hi! Thanks for your interest and reply! On 26.12.2023 20:28, Tomas Vondra wrote: > Can you share some info about the hardware? For example the CPU model, > number of cores, and so on. 12GB RAM is not quite huge, so presumably it > was a small machine. > It is HP ProLanit 2x socket server. 2x6 cores Intel(R) Xeon(R) CPU X5675 @ 3.07GHz, 2x12GB RAM, RAID from SSD drives. Linux 5.10.0-21-amd64 #1 SMP Debian 5.10.162-1 (2023-01-21) x86_64 GNU/Linux One cpu was disabled and some tweaks was made as Andres advised to avoid NUMA and other side effects. Full set of the configuration commands for server was like that: numactl --cpunodebind=0 --membind=0 --physcpubind=1,3,5,7,9,11 bash sudo cpupower frequency-set -g performance sudo cpupower idle-set -D0 echo 3059000 | sudo tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq (Turbo Boost and hyperthreading was disabled in BIOS.) > I think what would be interesting are runs with > > pgbench -M prepared -S -c $N -j $N > > i.e. read-only tests (to not hit I/O), and $N being sufficiently large > to maybe also show some concurrency/locking bottlenecks, etc. > > I may do some benchmarks if I happen to find a bit of time, but maybe > you could collect such numbers too? Firstly, i repeated the same -c and -j values in read-only mode as you advised. As one can see in the read-only.png, the absolute TPS value has increased significantly, by about 13 times. Patched version with limit 200Mb was slightly slower than with limit 0 by ~2%. The standard error in all series was ~0.5%. Since the deviation has increased in comparison with rw test the difference between unpatched version and patched ones with limits 0, 8Gb and 16Gb is not sensible. There is a raw data in the raw_data-read-only.txt. > I think 6350 is a pretty terrible number, especially for scale 8, which > is maybe 150MB of data. I think that's a pretty clear sign the system > was hitting some other bottleneck, which can easily mask regressions in > the memory allocation code. AFAICS the pgbench runs were regular r/w > benchmarks, so I'd bet it was hitting I/O, and possibly even subject to > some random effects at that level. > To avoid possible I/O bottleneck i followed these steps: - gave all 24G mem to cpu 0 rather than 12G as in [1]; - created a ramdisk of 12G size; - disable swap like that: numactl --cpunodebind=0 --physcpubind=1,3,5,7,9,11 bash sudo swapoff -a sudo mkdir /mnt/ramdisk sudo mount -t tmpfs -o rw,size=12G tmpfs /mnt/ramdisk The inst dir, data dir and log file were all on ramdisk. Pgbench in rw mode gave the following results: - the difference between unpatched version and patched ones with limits 0 and 16Gb almost the same: ~7470+-0.2% TPS. (orange, green and blue distributions on the RW-ramdisk.png respectively) - patched version with limit 8GB is slightly slower than three above; (yellow distribution) - patched version with limit 200MB slower than the first three by a measurable value ~0,4% (~7440 TPS); (black distribution) The standard error in all series was ~0.2%. There is a raw data in the raw_data-rw-ramdisk.txt For the sake of completeness i'm going to repeat read-only measurements with ramdisk. Аnd perform some tests with increased -c and -j values as you advised to find the possible point where concurrency/blocking bottlenecks start to play a role. And do this, of cause, for the last version of the patch. Thanks for rebased it! In general, i don't observe any considerable degradation in performance from this patch of several or even 10%, which were mentioned in [2]. With the best regards, -- Anton A. Melnikov Postgres Professional: http://www.postgrespro.com The Russian Postgres Company [1] https://www.postgresql.org/message-id/1d3a7d8f-cb7c-4468-a578-d8a1194ea2de%40postgrespro.ru [2] https://www.postgresql.org/message-id/3178e9a1b7acbcf023fafed68ca48d76afc07907.camel%40crunchydata.c... REL_16_BETA1 (e0b82fc8e83) unpatched 85761.111563 85021.605432 85454.083033 85917.957666 85876.042244 85642.072514 86296.248572 85619.937094 85297.361215 85862.202724 84540.978854 (x) 85396.633119 85690.647063 84988.591565 85823.448629 84773.324608 86216.489115 85501.651461 86009.350080 85358.496042 85486.594373 85779.622224 85814.955234 84737.148907 85732.179382 85586.101863 85978.317659 85288.636666 85710.628041 85152.516444 85907.719844 84770.623411 85886.087293 85793.628493 85009.003868 85291.167576 86049.283058 85240.478343 86482.472191 85178.651590 85081.329863 85819.632868 85828.367169 86140.325742 85910.775960 85317.224079 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory undefined (default = 0) 86111.507420 86191.677434 85884.145207 86548.583375 85925.729848 86073.041345 85556.167244 86515.518378 85882.827060 86089.279375 84442.238391 (x) 86181.390728 86605.506000 86131.111260 85850.438380 86285.492544 85878.295476 85485.605781 86280.781506 85481.309046 86791.510072 85878.009945 86855.543915 85724.634195 84685.561101 (x) 85810.684502 84852.093784 (x) 86393.727723 86950.634063 (x) 85296.535016 85952.156912 85833.631996 85533.831539 85972.110542 85918.424161 85144.936232 (x) 86078.101155 86042.642900 86309.387185 85563.696537 85984.949710 86189.425869 85346.739647 86672.086794 86576.575964 85683.585455 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory = 16GB 85786.954867 86099.397176 86161.602185 86263.763959 85538.865680 85432.794926 85728.016002 85979.774947 85075.008854 86327.744016 85537.786933 86245.287068 86487.177382 85934.602769 85621.782529 85874.416847 86418.906684 85653.498016 86167.811566 85640.948196 86767.193839 (x) 86159.553447 86199.056598 85947.101168 85542.140478 86082.251029 85523.251587 85856.236524 85924.012803 85972.899323 85644.499894 85462.754650 85724.552728 85787.436042 85965.040630 85687.389455 84922.795072 85358.044611 86205.357569 85064.849443 84984.181808 85256.160481 85680.558543 85334.634567 85280.112157 84868.810444 (x) REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory = 8GB 85100.232214 (x) 86145.956362 86454.848486 85973.080571 86175.046121 86002.597626 85908.845992 85843.346909 86276.874013 86941.448180 (x) 85335.027277 86315.033717 85044.675027 (x) 86212.423345 85594.552032 85787.800684 85980.895557 85758.813670 85410.670102 85640.278088 86270.514436 86126.509444 86472.934287 86352.242914 86266.541944 85643.059914 86490.924339 84973.214587 (x) 86219.673171 86898.294513 (x) 85280.591982 86790.409937 85804.289889 86145.406187 86092.140989 84692.229690 (x) 85253.872633 85057.863152 (x) 85630.225186 84910.186408 (x) 86260.305705 86153.212996 85936.390876 86208.713158 84413.248101 (x) 86529.579668 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory = 200MB 71.710505 (x) out of memory errors in log 84243.587084 84576.485240 84546.191505 84769.692835 84811.989459 83941.333178 84390.922436 84080.510960 84406.063419 84815.054344 84926.435865 83382.114485 (x) 84233.526059 83737.372571 84710.087530 84266.060690 83979.118354 84966.343014 85145.211891 84821.723252 84575.757291 83986.231873 85087.270906 85140.140349 84125.963441 84090.664968 83898.033737 83646.132496 83868.054474 84194.324422 84295.701512 84154.903928 83877.842592 84018.297675 84840.741742 84893.298428 83717.601912 84367.085598 84675.434517 84871.418337 84412.975964 83599.945813 84713.575852 83989.731131 84818.386157 REL_16_BETA1 (e0b82fc8e83) unpatched 7467.419891 7472.014013 7493.242036 7408.774587 7496.802158 7457.542737 7487.910772 7475.640175 7485.466664 7499.874236 7474.825139 7479.573388 7456.172459 7454.242942 7500.062756 7440.119529 7429.548826 7464.584901 7466.640344 7472.130154 7457.652816 7498.109421 7505.506842 7475.923936 7465.309986 7470.681113 7411.998612 7457.822630 7509.467781 7449.197064 7504.898429 7464.936431 7447.685630 7497.218840 7465.513425 7481.328682 7463.571360 7429.434920 7462.178302 7505.404955 7490.309328 7488.477102 7462.639174 7471.688637 7461.336425 7499.165045 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory undefined (default = 0) 7464.611403 7478.403075 7450.917444 7483.562575 7500.521682 7479.266432 7459.974700 7507.553000 7495.172003 7452.101295 7513.070841 7463.382158 7456.085082 7472.833051 7503.577746 7433.234381 7461.966344 7483.855314 7495.659665 7493.387966 7397.391891 7471.962202 7476.375392 7460.974030 7514.881548 7505.659485 7455.310069 7453.988434 7448.730999 7445.222442 7501.325753 7420.613952 7409.553181 7482.888561 7493.232293 7507.268369 7482.801647 7429.492431 7470.676577 7482.153079 7457.478934 7469.759722 7416.620216 7471.906157 7454.781634 7466.844149 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory = 16GB 7481.056709 7468.899961 7489.134861 7498.626080 7504.534880 7503.127220 7471.474104 7488.119337 7458.440996 7464.739382 7488.627320 7455.193405 7459.978467 7482.468559 7491.174587 7432.616983 7492.806772 7469.908569 7449.892009 7508.213210 7458.613016 7476.039933 7492.311968 7496.616756 7435.722964 7476.914236 7478.436463 7474.484447 7431.591836 7475.391966 7495.125213 7481.887843 7436.923440 7421.318947 7461.459195 7491.085440 7491.841513 7467.331830 7506.848057 7509.429479 7483.237177 7488.256111 7459.021238 7387.323083 (x) 7428.320688 7471.441284 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory = 8GB 38.884155 (x) out of memory errors in log 7418.194045 7484.248051 7429.342711 7445.906427 7479.215456 7482.549510 7479.521513 7489.821055 7425.255640 7473.898287 7475.271906 7410.911195 7482.227422 7471.891959 7441.920472 7461.338663 7414.412202 7472.875753 7430.044709 7465.442867 7473.856803 7415.170436 7457.467000 7474.149360 7462.451469 7454.570057 7486.853451 7476.660190 7441.361623 7464.706562 7477.256048 7465.801516 7476.568591 7475.006562 7493.299365 7456.332872 7454.174261 7432.872466 7477.096962 7431.126181 7452.820622 7469.352342 7430.955516 7481.356856 7458.982820 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.c... max_total_backend_memory = 200MB 36.223742 (x) 7399.245419 7451.173946 7396.641811 7454.101001 7479.472891 7427.912475 7441.225376 7450.589681 7412.533841 7437.228197 7446.286700 7441.405104 7477.718911 7398.548184 7392.161290 7458.758503 7467.946442 7424.785796 7459.894852 7440.628290 7454.374715 7445.956025 7425.295741 7448.542992 7437.003008 7440.505807 7462.882483 7453.967328 7449.913158 7431.653525 7465.553274 7420.272079 7458.774888 7476.748517 7469.100314 7433.124333 7424.384757 7462.361532 7475.693894 7431.876259 7414.515549 7451.841013 7407.344808 7455.825825 7384.738105 Attachments: [image/png] read-only.png (213.7K, ../../[email protected]/2-read-only.png) download | view image [text/plain] raw_data-read-only.txt (3.8K, ../../[email protected]/3-raw_data-read-only.txt) download | inline: REL_16_BETA1 (e0b82fc8e83) unpatched 85761.111563 85021.605432 85454.083033 85917.957666 85876.042244 85642.072514 86296.248572 85619.937094 85297.361215 85862.202724 84540.978854 (x) 85396.633119 85690.647063 84988.591565 85823.448629 84773.324608 86216.489115 85501.651461 86009.350080 85358.496042 85486.594373 85779.622224 85814.955234 84737.148907 85732.179382 85586.101863 85978.317659 85288.636666 85710.628041 85152.516444 85907.719844 84770.623411 85886.087293 85793.628493 85009.003868 85291.167576 86049.283058 85240.478343 86482.472191 85178.651590 85081.329863 85819.632868 85828.367169 86140.325742 85910.775960 85317.224079 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory undefined (default = 0) 86111.507420 86191.677434 85884.145207 86548.583375 85925.729848 86073.041345 85556.167244 86515.518378 85882.827060 86089.279375 84442.238391 (x) 86181.390728 86605.506000 86131.111260 85850.438380 86285.492544 85878.295476 85485.605781 86280.781506 85481.309046 86791.510072 85878.009945 86855.543915 85724.634195 84685.561101 (x) 85810.684502 84852.093784 (x) 86393.727723 86950.634063 (x) 85296.535016 85952.156912 85833.631996 85533.831539 85972.110542 85918.424161 85144.936232 (x) 86078.101155 86042.642900 86309.387185 85563.696537 85984.949710 86189.425869 85346.739647 86672.086794 86576.575964 85683.585455 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory = 16GB 85786.954867 86099.397176 86161.602185 86263.763959 85538.865680 85432.794926 85728.016002 85979.774947 85075.008854 86327.744016 85537.786933 86245.287068 86487.177382 85934.602769 85621.782529 85874.416847 86418.906684 85653.498016 86167.811566 85640.948196 86767.193839 (x) 86159.553447 86199.056598 85947.101168 85542.140478 86082.251029 85523.251587 85856.236524 85924.012803 85972.899323 85644.499894 85462.754650 85724.552728 85787.436042 85965.040630 85687.389455 84922.795072 85358.044611 86205.357569 85064.849443 84984.181808 85256.160481 85680.558543 85334.634567 85280.112157 84868.810444 (x) REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory = 8GB 85100.232214 (x) 86145.956362 86454.848486 85973.080571 86175.046121 86002.597626 85908.845992 85843.346909 86276.874013 86941.448180 (x) 85335.027277 86315.033717 85044.675027 (x) 86212.423345 85594.552032 85787.800684 85980.895557 85758.813670 85410.670102 85640.278088 86270.514436 86126.509444 86472.934287 86352.242914 86266.541944 85643.059914 86490.924339 84973.214587 (x) 86219.673171 86898.294513 (x) 85280.591982 86790.409937 85804.289889 86145.406187 86092.140989 84692.229690 (x) 85253.872633 85057.863152 (x) 85630.225186 84910.186408 (x) 86260.305705 86153.212996 85936.390876 86208.713158 84413.248101 (x) 86529.579668 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory = 200MB 71.710505 (x) out of memory errors in log 84243.587084 84576.485240 84546.191505 84769.692835 84811.989459 83941.333178 84390.922436 84080.510960 84406.063419 84815.054344 84926.435865 83382.114485 (x) 84233.526059 83737.372571 84710.087530 84266.060690 83979.118354 84966.343014 85145.211891 84821.723252 84575.757291 83986.231873 85087.270906 85140.140349 84125.963441 84090.664968 83898.033737 83646.132496 83868.054474 84194.324422 84295.701512 84154.903928 83877.842592 84018.297675 84840.741742 84893.298428 83717.601912 84367.085598 84675.434517 84871.418337 84412.975964 83599.945813 84713.575852 83989.731131 84818.386157 [image/png] RW-ramdisk.png (214.6K, ../../[email protected]/4-RW-ramdisk.png) download | view image [text/plain] raw_data-rw-ramdisk.txt (3.5K, ../../[email protected]/5-raw_data-rw-ramdisk.txt) download | inline: REL_16_BETA1 (e0b82fc8e83) unpatched 7467.419891 7472.014013 7493.242036 7408.774587 7496.802158 7457.542737 7487.910772 7475.640175 7485.466664 7499.874236 7474.825139 7479.573388 7456.172459 7454.242942 7500.062756 7440.119529 7429.548826 7464.584901 7466.640344 7472.130154 7457.652816 7498.109421 7505.506842 7475.923936 7465.309986 7470.681113 7411.998612 7457.822630 7509.467781 7449.197064 7504.898429 7464.936431 7447.685630 7497.218840 7465.513425 7481.328682 7463.571360 7429.434920 7462.178302 7505.404955 7490.309328 7488.477102 7462.639174 7471.688637 7461.336425 7499.165045 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory undefined (default = 0) 7464.611403 7478.403075 7450.917444 7483.562575 7500.521682 7479.266432 7459.974700 7507.553000 7495.172003 7452.101295 7513.070841 7463.382158 7456.085082 7472.833051 7503.577746 7433.234381 7461.966344 7483.855314 7495.659665 7493.387966 7397.391891 7471.962202 7476.375392 7460.974030 7514.881548 7505.659485 7455.310069 7453.988434 7448.730999 7445.222442 7501.325753 7420.613952 7409.553181 7482.888561 7493.232293 7507.268369 7482.801647 7429.492431 7470.676577 7482.153079 7457.478934 7469.759722 7416.620216 7471.906157 7454.781634 7466.844149 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory = 16GB 7481.056709 7468.899961 7489.134861 7498.626080 7504.534880 7503.127220 7471.474104 7488.119337 7458.440996 7464.739382 7488.627320 7455.193405 7459.978467 7482.468559 7491.174587 7432.616983 7492.806772 7469.908569 7449.892009 7508.213210 7458.613016 7476.039933 7492.311968 7496.616756 7435.722964 7476.914236 7478.436463 7474.484447 7431.591836 7475.391966 7495.125213 7481.887843 7436.923440 7421.318947 7461.459195 7491.085440 7491.841513 7467.331830 7506.848057 7509.429479 7483.237177 7488.256111 7459.021238 7387.323083 (x) 7428.320688 7471.441284 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory = 8GB 38.884155 (x) out of memory errors in log 7418.194045 7484.248051 7429.342711 7445.906427 7479.215456 7482.549510 7479.521513 7489.821055 7425.255640 7473.898287 7475.271906 7410.911195 7482.227422 7471.891959 7441.920472 7461.338663 7414.412202 7472.875753 7430.044709 7465.442867 7473.856803 7415.170436 7457.467000 7474.149360 7462.451469 7454.570057 7486.853451 7476.660190 7441.361623 7464.706562 7477.256048 7465.801516 7476.568591 7475.006562 7493.299365 7456.332872 7454.174261 7432.872466 7477.096962 7431.126181 7452.820622 7469.352342 7430.955516 7481.356856 7458.982820 REL_16_BETA1 (e0b82fc8e83) patched with https://www.postgresql.org/message-id/4edafedc0f8acb12a2979088ac1317bd7dd42145.camel%40crunchydata.com max_total_backend_memory = 200MB 36.223742 (x) 7399.245419 7451.173946 7396.641811 7454.101001 7479.472891 7427.912475 7441.225376 7450.589681 7412.533841 7437.228197 7446.286700 7441.405104 7477.718911 7398.548184 7392.161290 7458.758503 7467.946442 7424.785796 7459.894852 7440.628290 7454.374715 7445.956025 7425.295741 7448.542992 7437.003008 7440.505807 7462.882483 7453.967328 7449.913158 7431.653525 7465.553274 7420.272079 7458.774888 7476.748517 7469.100314 7433.124333 7424.384757 7462.361532 7475.693894 7431.876259 7414.515549 7451.841013 7407.344808 7455.825825 7384.738105 ^ permalink raw reply [nested|flat] 281+ messages in thread
* Re: Add the ability to limit the amount of memory that can be allocated to backends. @ 2024-01-28 19:11 Tomas Vondra <[email protected]> parent: Anton A. Melnikov <[email protected]> 0 siblings, 1 reply; 281+ messages in thread From: Tomas Vondra @ 2024-01-28 19:11 UTC (permalink / raw) To: Anton A. Melnikov <[email protected]>; Andres Freund <[email protected]>; Andrei Lepikhov <[email protected]>; +Cc: Stephen Frost <[email protected]>; [email protected]; Arne Roland <[email protected]>; [email protected] <[email protected]>; vignesh C <[email protected]>; Justin Pryzby <[email protected]>; Ibrar Ahmed <[email protected]>; stephen.frost <[email protected]> Hi, I took a closer look at this patch over the last couple days, and I did a bunch of benchmarks to see how expensive the accounting is. The good news is that I haven't observed any overhead - I did two simple tests, that I think would be particularly sensitive to this: 1) regular "pgbench -S" with scale 10, so tiny and not hitting I/O 2) "select count(*) from generate_series(1,N)" where N is either 10k or 1M, which should be enough to cause a fair number of allocations And I tested this on three branches - master (no patches applied), patched (but limit=0, so just accounting) and patched-limit (with limit set to 4.5GB, so high enough not to be hit). Attached are script and raw results for both benchmarks from two machines, i5 (small, 4C) and xeon (bigger, 16C/32C), and a PDF showing the results as candlestick charts (with 1 and 2 sigma intervals). AFAICS there's no measurable difference between master and patched builds. Which is good, clearly the local allowance makes the overhead negligible (at least in these benchmarks). Now, for the patch itself - I already said some of the stuff about a month ago [1], but I'll repeat some of it for the sake of completeness before I get to comments about the code etc. Firstly, I agree with the goal of having a way to account for memory used by the backends, and also ability to enforce some sort of limit. It's difficult to track the memory at the OS level (interpreting RSS values is not trivial), and work_mem is not sufficient to enforce a backend-level limit, not even talking about a global limit. But as I said earlier, it seems quite strange to start by introducing some sort of global limit, combining memory for all backends. I do understand that the intent is to have such global limit in order to prevent issues with the OOM killer and/or not to interfere with other stuff running on the same machine. And while I'm not saying we should not have such limit, every time I wished to have a memory limit it was a backend-level one. Ideally a workmem-like limit that would "adjust" the work_mem values used by the optimizer (but that's not what this patch aims to do), or at least a backstop in case something goes wrong (say, a memory leak, OLTP application issuing complex queries, etc.). The accounting and infrastructure introduced by the patch seems to be suitable for both types of limits (global and per-backend), but then it goes for the global limit first. It may seem simpler to implement, but in practice there's a bunch of problems mentioned earlier, but ignored. For example, I really don't believe it's OK to just report the error in the first backend that happens to hit the limit. Bertrand mentioned that [2], asking about a situation when a runaway process allocates 99% of memory. The response to that was > Initially, we believe that punishing the detector is reasonable if we > can help administrators avoid the OOM killer/resource starvation. But > we can and should expand on this idea. which I find rather unsatisfactory. Belief is not an argument, and it relies on the assumption that this helps the administrator to avoid the OOM killer etc. ISTM it can easily mean the administrator can't even connect to the database, run a query (to inspect the new system views), etc. because any of that would hit the memory limit. That seems more like a built-in DoS facility ... If this was up to me, I'd probably start with the per-backend limit. But that's my personal opinion. Now, some comments about the code etc. Stephen was promising a new patch version in October [6], but that didn't happen yet, so I looked at the patches I rebased in December. 0001 ---- 1) I don't see why we should separate memory by context type - without knowing which exact backends are using the memory, this seems pretty irrelevant/useless. Either it's private or shared memory, I don't think the accounting should break this into more counters. Also, while I'm not aware of anyone proposing a new memory context type, I doubt we'd want to add more and more counters if that happens. suggestion: only two counters, for local and shared memory If we absolutely want to have per-type counters, we should not mix the private memory and shared memory ones. 2) I have my doubts about the tracking of shared memory. It seems weird to count them only into the backend that allocated them, and transfer them to "global" on process exit. Surely we should know which shared memory is meant to be long-lived from the start, no? For example, it's not uncommon that an extension allocates a chunk of shared memory to store some sort of global state (e.g. BDR/pglogical does that, I'm sure other extensions do that). But the process that allocates the shared memory keeps running. AFAICS this would be tracked as backend DSM memory, which I'm not sure this is what we want ... And I'm not alone in thinking this should work differently - [3], [4]. 3) We limit the floor of allocation counters to zero. This seems really weird. Why would it be necessary? I mean, how could we get a negative amount of memory? Seems like it might easily mask issues with incorrect accounting, or something. 4) pg_stat_memory_allocation Maybe pg_stat_memory_usage would be a better name ... 5) The comments/docs repeatedly talk about "dynamic nature" and that it makes the values not exact: > Due to the dynamic nature of memory allocations the allocated bytes > values may not be exact but should be sufficient for the intended > purposes. I don't understand what "dynamic nature" refers to, and why would it make the values not exact. Presumably this refers to the "allowance" but how is that "dynamic nature"? This definitely needs to explain this better, with some basic estimate how how accurate the values are expected to be. 6) The SGML docs keep recommending to use pg_size_pretty(). I find that unnecessary, no other docs reporting values in bytes do that. 7) I see no reason to include shared_memory_size_mb in the view, and same for shared_memory_size_in_huge_pages. It has little to do with "allocated" memory, IMO. And a value in "MB" goes directly against the suggestion to use pg_size_pretty(). suggestion: drop this from the view 8) In a lot of places we do context->mem_allocated += blksize; pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); Maybe we should integrate the two types of accounting, wrap them into a single function call, or something? This makes it very simple to forget updating one of those places. AFAIC the patch tries to minimize the number of updates of the new shared counters, but with the allowance that should not be an issue I think. 9) This seems wrong. Why would it be OK to ever overflow? Isn't that a sign of incorrect accounting? /* Avoid allocated_bytes unsigned integer overflow on decrease */ if (pg_sub_u64_overflow(*my_allocated_bytes, proc_allocated_bytes, &temp)) { /* On overflow, set allocated bytes and allocator type bytes to zero */ *my_allocated_bytes = 0; *my_aset_allocated_bytes = 0; *my_dsm_allocated_bytes = 0; *my_generation_allocated_bytes = 0; *my_slab_allocated_bytes = 0; } 9) How could any of these values be negative? It's all capped to 0 and also stored in uint64. Seems pretty useless. +SELECT + datid > 0, pg_size_bytes(shared_memory_size) >= 0, shared_memory_size_in_huge_pages >= -1, global_dsm_allocated_bytes >= 0 +FROM + pg_stat_global_memory_allocation; + ?column? | ?column? | ?column? | ?column? +----------+----------+----------+---------- + t | t | t | t +(1 row) + +-- ensure that pg_stat_memory_allocation view exists +SELECT + pid > 0, allocated_bytes >= 0, aset_allocated_bytes >= 0, dsm_allocated_bytes >= 0, generation_allocated_bytes >= 0, slab_allocated_bytes >= 0 0003 ---- 1) The commit message says: > Further requests will not be allocated until dropping below the limit. > Keep this in mind when setting this value. The SGML docs have a similar "keep this in mind" suggestion in relation to the 1MB local allowance. I find this pretty useless, as it doesn't really say what to do with the information / what it means. I mean, should I set the value higher, or what am I supposed to do? This needs to be understandable for average user reading the SGML docs, who is unlikely to know the implementation details. 2) > This limit does not affect auxiliary backend processes. This seems pretty unfortunate, because in the cases where I actually saw OOM killer to intervene, it was often because of auxiliary processes allocating a lot of memory (say, autovacuum with maintenance_work_mem set very high, etc.). In a way, not excluding these auxiliary processes from the limit seems to go against the idea of preventing the OOM killer. 3) I don't think the patch ever explains what the "local allowance" is, how the refill works, why it's done this way, etc. I do think I understand that now, but I had to go through the thread, That's not really how it should be. There should be an explanation of how this works somewhere (comment in mcxt.c? separate README?). 4) > doc/src/sgml/monitoring.sgml Not sure why this removes the part about DSM being included only in the backend that created it. 5) > total_bkend_mem_bytes_available The "bkend" name is strange (to save 2 characters), and the fact how it combines local and shared memory seems confusing too. 6) + /* + * Local counter to manage shared memory allocations. At backend startup, set to + * initial_allocation_allowance via pgstat_init_allocated_bytes(). Decrease as + * memory is malloc'd. When exhausted, atomically refill if available from + * ProcGlobal->max_total_bkend_mem via exceeds_max_total_bkend_mem(). + */ +uint64 allocation_allowance = 0; But this allowance is for shared memory too, and shared memory is not allocated using malloc. 7) There's a lot of new global variables. Maybe it'd be better to group them into a struct, or something? 8) Why does pgstat_set_allocated_bytes_storage need the new return? 9) Unnecessary changes in src/backend/utils/hash/dynahash.c (whitespace, new comment that seems not very useful) 10) Shouldn't we have a new malloc wrapper that does the check? That way we wouldn't need to have the call in every memory context place calling malloc. 11) I'm not sure about the ereport() calls after hitting the limit. Adres thinks it might lead to recursion [4], but Stephen [5] seems to think this does not really make the situation worse. I'm not sure about that, though - I agree the ENOMEM can already happen, but but maybe having a limit (which clearly needs to be more stricter than the limit used by kernel for OOM) would be more likely to hit? 12) In general, I agree with Andres [4] that we'd be better of to focus on the accounting part, see how it works in practice, and then add some ability to limit memory after a while. regards [1] https://www.postgresql.org/message-id/4fb99fb7-8a6a-2828-dd77-e2f1d75c7dd0%40enterprisedb.com [2] https://www.postgresql.org/message-id/3b9b90c6-f4ae-a7df-6519-847ea9d5fe1e%40amazon.com [3] https://www.postgresql.org/message-id/20230110023118.qqbjbtyecofh3uvd%40awork3.anarazel.de [4] https://www.postgresql.org/message-id/20230113180411.rdqbrivz5ano2uat%40awork3.anarazel.de [5] https://www.postgresql.org/message-id/ZTArWsctGn5fEVPR%40tamriel.snowman.net [6] https://www.postgresql.org/message-id/ZTGycSYuFrsixv6q%40tamriel.snowman.net -- Tomas Vondra EnterpriseDB: http://www.enterprisedb.com The Enterprise PostgreSQL Company Attachments: [application/pdf] results-count.pdf (388.3K, ../../[email protected]/2-results-count.pdf) download [application/pdf] results-pgbench.pdf (228.4K, ../../[email protected]/3-results-pgbench.pdf) download [application/x-compressed-tar] scripts.tgz (768B, ../../[email protected]/4-scripts.tgz) download [application/x-compressed-tar] xeon-count.tgz (49.7K, ../../[email protected]/5-xeon-count.tgz) download [application/x-compressed-tar] xeon-pgbench.tgz (29.9K, ../../[email protected]/6-xeon-pgbench.tgz) download [application/x-compressed-tar] i5-count.tgz (44.5K, ../../[email protected]/7-i5-count.tgz) download [application/x-compressed-tar] i5-pgbench.tgz (28.5K, ../../[email protected]/8-i5-pgbench.tgz) download ^ permalink raw reply [nested|flat] 281+ messages in thread
* Re: Add the ability to limit the amount of memory that can be allocated to backends. @ 2024-03-12 13:30 Aleksander Alekseev <[email protected]> parent: Tomas Vondra <[email protected]> 0 siblings, 1 reply; 281+ messages in thread From: Aleksander Alekseev @ 2024-03-12 13:30 UTC (permalink / raw) To: [email protected] <[email protected]>; +Cc: Tomas Vondra <[email protected]>; Anton A. Melnikov <[email protected]>; Andres Freund <[email protected]>; Andrei Lepikhov <[email protected]>; Stephen Frost <[email protected]>; [email protected]; Arne Roland <[email protected]>; vignesh C <[email protected]>; Justin Pryzby <[email protected]>; Ibrar Ahmed <[email protected]>; stephen.frost <[email protected]> Hi, > I took a closer look at this patch over the last couple days, and I did > a bunch of benchmarks to see how expensive the accounting is. The good > news is that I haven't observed any overhead - I did two simple tests, > that I think would be particularly sensitive to this: > > [...] Just wanted to let you know that v20231226 doesn't apply. The patch needs love from somebody interested in it. Best regards, Aleksander Alekseev (wearing a co-CFM hat) ^ permalink raw reply [nested|flat] 281+ messages in thread
* Re: Add the ability to limit the amount of memory that can be allocated to backends. @ 2024-03-13 07:41 Anton A. Melnikov <[email protected]> parent: Aleksander Alekseev <[email protected]> 0 siblings, 1 reply; 281+ messages in thread From: Anton A. Melnikov @ 2024-03-13 07:41 UTC (permalink / raw) To: Aleksander Alekseev <[email protected]>; [email protected] <[email protected]>; +Cc: Tomas Vondra <[email protected]>; Andres Freund <[email protected]>; Andrei Lepikhov <[email protected]>; Stephen Frost <[email protected]>; [email protected]; Arne Roland <[email protected]>; vignesh C <[email protected]>; Justin Pryzby <[email protected]>; Ibrar Ahmed <[email protected]>; stephen.frost <[email protected]> On 12.03.2024 16:30, Aleksander Alekseev wrote: > Just wanted to let you know that v20231226 doesn't apply. The patch > needs love from somebody interested in it. Thanks for pointing to this! Here is a version updated for the current master. With the best regards, -- Anton A. Melnikov Postgres Professional: http://www.postgrespro.com The Russian Postgres Company Attachments: [text/x-patch] v20140313-0001-Add-tracking-of-backend-memory-allocated.patch (49.9K, ../../[email protected]/2-v20140313-0001-Add-tracking-of-backend-memory-allocated.patch) download | inline diff: From e31012217fb63f57fe16d7232fec27bb6cd45597 Mon Sep 17 00:00:00 2001 From: Tomas Vondra <[email protected]> Date: Tue, 26 Dec 2023 17:54:40 +0100 Subject: [PATCH 1/3] Add tracking of backend memory allocated Add tracking of backend memory allocated in total and by allocation type (aset, dsm, generation, slab) by process. allocated_bytes tracks the current bytes of memory allocated to the backend process. aset_allocated_bytes, dsm_allocated_bytes, generation_allocated_bytes and slab_allocated_bytes track the allocation by type for the backend process. They are updated for the process as memory is malloc'd/freed. Memory allocated to items on the freelist is included. Dynamic shared memory allocations are included only in the value displayed for the backend that created them, they are not included in the value for backends that are attached to them to avoid double counting. DSM allocations that are not destroyed by the creating process prior to it's exit are considered long lived and are tracked in a global counter global_dsm_allocated_bytes. We limit the floor of allocation counters to zero. Created views pg_stat_global_memory_allocation and pg_stat_memory_allocation for access to these trackers. --- doc/src/sgml/monitoring.sgml | 246 ++++++++++++++++++++ src/backend/catalog/system_views.sql | 34 +++ src/backend/storage/ipc/dsm.c | 11 +- src/backend/storage/ipc/dsm_impl.c | 78 +++++++ src/backend/storage/lmgr/proc.c | 1 + src/backend/utils/activity/backend_status.c | 114 +++++++++ src/backend/utils/adt/pgstatfuncs.c | 84 +++++++ src/backend/utils/init/miscinit.c | 3 + src/backend/utils/mmgr/aset.c | 17 ++ src/backend/utils/mmgr/generation.c | 14 ++ src/backend/utils/mmgr/slab.c | 22 ++ src/include/catalog/pg_proc.dat | 17 ++ src/include/storage/proc.h | 2 + src/include/utils/backend_status.h | 144 +++++++++++- src/test/regress/expected/rules.out | 27 +++ src/test/regress/expected/stats.out | 36 +++ src/test/regress/sql/stats.sql | 20 ++ 17 files changed, 868 insertions(+), 2 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 8aca08140e..5f827fe0b0 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -4598,6 +4598,252 @@ description | Waiting for a newly initialized WAL file to reach durable storage </sect2> + <sect2 id="monitoring-pg-stat-memory-allocation-view"> + <title><structname>pg_stat_memory_allocation</structname></title> + + <indexterm> + <primary>pg_stat_memory_allocation</primary> + </indexterm> + + <para> + The <structname>pg_stat_memory_allocation</structname> view will have one + row per server process, showing information related to the current memory + allocation of that process in total and by allocator type. Due to the + dynamic nature of memory allocations the allocated bytes values may not be + exact but should be sufficient for the intended purposes. Dynamic shared + memory allocations are included only in the value displayed for the backend + that created them, they are not included in the value for backends that are + attached to them to avoid double counting. Use + <function>pg_size_pretty</function> described in + <xref linkend="functions-admin-dbsize"/> to make these values more easily + readable. + </para> + + <table id="pg-stat-memory-allocation-view" xreflabel="pg_stat_memory_allocation"> + <title><structname>pg_stat_memory_allocation</structname> View</title> + <tgroup cols="1"> + <thead> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + + <tbody> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>datid</structfield> <type>oid</type> + </para> + <para> + OID of the database this backend is connected to + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>pid</structfield> <type>integer</type> + </para> + <para> + Process ID of this backend + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes. This is the balance + of bytes allocated and freed by this backend. Dynamic shared memory + allocations are included only in the value displayed for the backend that + created them, they are not included in the value for backends that are + attached to them to avoid double counting. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>aset_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the allocation + set allocator. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>dsm_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the dynamic + shared memory allocator. Upon process exit, dsm allocations that have + not been freed are considered long lived and added to + <structfield>global_dsm_allocated_bytes</structfield> found in the + <link linkend="monitoring-pg-stat-global-memory-allocation-view"> + <structname>pg_stat_global_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>generation_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the generation + allocator. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>slab_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the slab + allocator. + </para></entry> + </row> + + </tbody> + </tgroup> + </table> + + </sect2> + + <sect2 id="monitoring-pg-stat-global-memory-allocation-view"> + <title><structname>pg_stat_global_memory_allocation</structname></title> + + <indexterm> + <primary>pg_stat_global-memory_allocation</primary> + </indexterm> + + <para> + The <structname>pg_stat_global_memory_allocation</structname> view will + have one row showing information related to current shared memory + allocations. Due to the dynamic nature of memory allocations the allocated + bytes values may not be exact but should be sufficient for the intended + purposes. Use <function>pg_size_pretty</function> described in + <xref linkend="functions-admin-dbsize"/> to make the byte populated values + more easily readable. + </para> + + <table id="pg-stat-global-memory-allocation-view" xreflabel="pg_stat_global_memory_allocation"> + <title><structname>pg_stat_global_memory_allocation</structname> View</title> + <tgroup cols="1"> + <thead> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + + <tbody> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>datid</structfield> <type>oid</type> + </para> + <para> + OID of the database this backend is connected to + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>shared_memory_size_mb</structfield> <type>integer</type> + </para> + <para> + Reports the size of the main shared memory area, rounded up to the + nearest megabyte. See <xref linkend="guc-shared-memory-size"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>shared_memory_size_in_huge_pages</structfield> <type>bigint</type> + </para> + <para> + Reports the number of huge pages that are needed for the main shared + memory area based on the specified huge_page_size. If huge pages are not + supported, this will be -1. See + <xref linkend="guc-shared-memory-size-in-huge-pages"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>global_dsm_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Long lived dynamically allocated memory currently allocated to the + database. Upon process exit, dsm allocations that have not been freed + are considered long lived and added to + <structfield>global_dsm_allocated_bytes</structfield>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_aset_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>aset_allocated_bytes</structfield> for all + backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_dsm_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>dsm_allocated_bytes</structfield> for all + backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_generation_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>generation_allocated_bytes</structfield> for + all backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_slab_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>slab_allocated_bytes</structfield> for all + backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + </tbody> + </tgroup> + </table> + + </sect2> + <sect2 id="monitoring-stats-functions"> <title>Statistics Functions</title> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 04227a72d1..61ff4a59b6 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1375,3 +1375,37 @@ CREATE VIEW pg_stat_subscription_stats AS CREATE VIEW pg_wait_events AS SELECT * FROM pg_get_wait_events(); + +CREATE VIEW pg_stat_memory_allocation AS + SELECT + S.datid AS datid, + S.pid, + S.allocated_bytes, + S.aset_allocated_bytes, + S.dsm_allocated_bytes, + S.generation_allocated_bytes, + S.slab_allocated_bytes + FROM pg_stat_get_memory_allocation(NULL) AS S + LEFT JOIN pg_database AS D ON (S.datid = D.oid); + +CREATE VIEW pg_stat_global_memory_allocation AS +WITH sums AS ( + SELECT + SUM(aset_allocated_bytes) AS total_aset_allocated_bytes, + SUM(dsm_allocated_bytes) AS total_dsm_allocated_bytes, + SUM(generation_allocated_bytes) AS total_generation_allocated_bytes, + SUM(slab_allocated_bytes) AS total_slab_allocated_bytes + FROM + pg_stat_memory_allocation +) +SELECT + S.datid AS datid, + current_setting('shared_memory_size', true) as shared_memory_size, + (current_setting('shared_memory_size_in_huge_pages', true))::integer as shared_memory_size_in_huge_pages, + S.global_dsm_allocated_bytes, + sums.total_aset_allocated_bytes, + sums.total_dsm_allocated_bytes, + sums.total_generation_allocated_bytes, + sums.total_slab_allocated_bytes + FROM sums, pg_stat_get_global_memory_allocation() AS S + LEFT JOIN pg_database AS D ON (S.datid = D.oid); diff --git a/src/backend/storage/ipc/dsm.c b/src/backend/storage/ipc/dsm.c index c2e33a7e43..b950640643 100644 --- a/src/backend/storage/ipc/dsm.c +++ b/src/backend/storage/ipc/dsm.c @@ -802,6 +802,15 @@ dsm_detach_all(void) void dsm_detach(dsm_segment *seg) { + /* + * Retain mapped_size to pass into destroy call in cases where the detach + * is the last reference. mapped_size is zeroed as part of the detach + * process, but is needed later in these cases for dsm_allocated_bytes + * accounting. + */ + Size local_seg_mapped_size = seg->mapped_size; + Size *ptr_local_seg_mapped_size = &local_seg_mapped_size; + /* * Invoke registered callbacks. Just in case one of those callbacks * throws a further error that brings us back here, pop the callback @@ -882,7 +891,7 @@ dsm_detach(dsm_segment *seg) */ if (is_main_region_dsm_handle(seg->handle) || dsm_impl_op(DSM_OP_DESTROY, seg->handle, 0, &seg->impl_private, - &seg->mapped_address, &seg->mapped_size, WARNING)) + &seg->mapped_address, ptr_local_seg_mapped_size, WARNING)) { LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); if (is_main_region_dsm_handle(seg->handle)) diff --git a/src/backend/storage/ipc/dsm_impl.c b/src/backend/storage/ipc/dsm_impl.c index 8dd669e0ce..af67e55bdf 100644 --- a/src/backend/storage/ipc/dsm_impl.c +++ b/src/backend/storage/ipc/dsm_impl.c @@ -66,6 +66,7 @@ #include "postmaster/postmaster.h" #include "storage/dsm_impl.h" #include "storage/fd.h" +#include "utils/backend_status.h" #include "utils/guc.h" #include "utils/memutils.h" @@ -232,6 +233,14 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + if (op == DSM_OP_DESTROY) + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *mapped_address = NULL; *mapped_size = 0; if (op == DSM_OP_DESTROY && shm_unlink(name) != 0) @@ -332,6 +341,33 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + { + /* + * Posix creation calls dsm_impl_posix_resize implying that resizing + * occurs or may be added in the future. As implemented + * dsm_impl_posix_resize utilizes fallocate or truncate, passing the + * whole new size as input, growing the allocation as needed (only + * truncate supports shrinking). We update by replacing the old + * allocation with the new. + */ +#if defined(HAVE_POSIX_FALLOCATE) && defined(__linux__) + /* + * posix_fallocate does not shrink allocations, adjust only on + * allocation increase. + */ + if (request_size > *mapped_size) + pgstat_report_allocated_bytes_increase(request_size - *mapped_size, PG_ALLOC_DSM); +#else + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); + pgstat_report_allocated_bytes_increase(request_size, PG_ALLOC_DSM); +#endif + } *mapped_address = address; *mapped_size = request_size; close(fd); @@ -538,6 +574,14 @@ dsm_impl_sysv(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + if (op == DSM_OP_DESTROY) + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *mapped_address = NULL; *mapped_size = 0; if (op == DSM_OP_DESTROY && shmctl(ident, IPC_RMID, NULL) < 0) @@ -585,6 +629,13 @@ dsm_impl_sysv(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + pgstat_report_allocated_bytes_increase(request_size, PG_ALLOC_DSM); *mapped_address = address; *mapped_size = request_size; @@ -653,6 +704,13 @@ dsm_impl_windows(dsm_op op, dsm_handle handle, Size request_size, return false; } + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + if (op == DSM_OP_DESTROY) + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *impl_private = NULL; *mapped_address = NULL; *mapped_size = 0; @@ -769,6 +827,12 @@ dsm_impl_windows(dsm_op op, dsm_handle handle, Size request_size, return false; } + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + pgstat_report_allocated_bytes_increase(info.RegionSize, PG_ALLOC_DSM); *mapped_address = address; *mapped_size = info.RegionSize; *impl_private = hmap; @@ -813,6 +877,13 @@ dsm_impl_mmap(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *mapped_address = NULL; *mapped_size = 0; if (op == DSM_OP_DESTROY && unlink(name) != 0) @@ -934,6 +1005,13 @@ dsm_impl_mmap(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + pgstat_report_allocated_bytes_increase(request_size, PG_ALLOC_DSM); *mapped_address = address; *mapped_size = request_size; diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index f3e20038f4..1959b5f4e6 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -180,6 +180,7 @@ InitProcGlobal(void) ProcGlobal->checkpointerLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PROC_NUMBER); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PROC_NUMBER); + pg_atomic_init_u64(&ProcGlobal->global_dsm_allocation, 0); /* * Create and initialize all the PGPROC structures we'll need. There are diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c index 1ccf4c6d83..25b545441b 100644 --- a/src/backend/utils/activity/backend_status.c +++ b/src/backend/utils/activity/backend_status.c @@ -48,6 +48,24 @@ int pgstat_track_activity_query_size = 1024; /* exposed so that backend_progress.c can access it */ PgBackendStatus *MyBEEntry = NULL; +/* + * Memory allocated to this backend prior to pgstats initialization. Migrated to + * shared memory on pgstats initialization. + */ +uint64 local_my_allocated_bytes = 0; +uint64 *my_allocated_bytes = &local_my_allocated_bytes; + +/* Memory allocated to this backend by type prior to pgstats initialization. + * Migrated to shared memory on pgstats initialization + */ +uint64 local_my_aset_allocated_bytes = 0; +uint64 *my_aset_allocated_bytes = &local_my_aset_allocated_bytes; +uint64 local_my_dsm_allocated_bytes = 0; +uint64 *my_dsm_allocated_bytes = &local_my_dsm_allocated_bytes; +uint64 local_my_generation_allocated_bytes = 0; +uint64 *my_generation_allocated_bytes = &local_my_generation_allocated_bytes; +uint64 local_my_slab_allocated_bytes = 0; +uint64 *my_slab_allocated_bytes = &local_my_slab_allocated_bytes; static PgBackendStatus *BackendStatusArray = NULL; static char *BackendAppnameBuffer = NULL; @@ -382,6 +400,32 @@ pgstat_bestart(void) lbeentry.st_progress_command_target = InvalidOid; lbeentry.st_query_id = UINT64CONST(0); + /* Alter allocation reporting from local storage to shared memory */ + pgstat_set_allocated_bytes_storage(&MyBEEntry->allocated_bytes, + &MyBEEntry->aset_allocated_bytes, + &MyBEEntry->dsm_allocated_bytes, + &MyBEEntry->generation_allocated_bytes, + &MyBEEntry->slab_allocated_bytes); + + /* + * Populate sum of memory allocated prior to pgstats initialization to + * pgstats and zero the local variable. This is a += assignment because + * InitPostgres allocates memory after pgstat_beinit but prior to + * pgstat_bestart so we have allocations to both local and shared memory + * to combine. + */ + lbeentry.allocated_bytes += local_my_allocated_bytes; + local_my_allocated_bytes = 0; + lbeentry.aset_allocated_bytes += local_my_aset_allocated_bytes; + local_my_aset_allocated_bytes = 0; + + lbeentry.dsm_allocated_bytes += local_my_dsm_allocated_bytes; + local_my_dsm_allocated_bytes = 0; + lbeentry.generation_allocated_bytes += local_my_generation_allocated_bytes; + local_my_generation_allocated_bytes = 0; + lbeentry.slab_allocated_bytes += local_my_slab_allocated_bytes; + local_my_slab_allocated_bytes = 0; + /* * we don't zero st_progress_param here to save cycles; nobody should * examine it until st_progress_command has been set to something other @@ -441,6 +485,9 @@ pgstat_beshutdown_hook(int code, Datum arg) { volatile PgBackendStatus *beentry = MyBEEntry; + /* Stop reporting memory allocation changes to shared memory */ + pgstat_reset_allocated_bytes_storage(); + /* * Clear my status entry, following the protocol of bumping st_changecount * before and after. We use a volatile pointer here to ensure the @@ -1195,3 +1242,70 @@ pgstat_clip_activity(const char *raw_activity) return activity; } + +/* + * Configure bytes allocated reporting to report allocated bytes to + * shared memory. + * + * Expected to be called during backend startup (in pgstat_bestart), to point + * allocated bytes accounting into shared memory. + */ +void +pgstat_set_allocated_bytes_storage(uint64 *allocated_bytes, + uint64 *aset_allocated_bytes, + uint64 *dsm_allocated_bytes, + uint64 *generation_allocated_bytes, + uint64 *slab_allocated_bytes) +{ + /* Map allocations to shared memory */ + my_allocated_bytes = allocated_bytes; + *allocated_bytes = local_my_allocated_bytes; + + my_aset_allocated_bytes = aset_allocated_bytes; + *aset_allocated_bytes = local_my_aset_allocated_bytes; + + my_dsm_allocated_bytes = dsm_allocated_bytes; + *dsm_allocated_bytes = local_my_dsm_allocated_bytes; + + my_generation_allocated_bytes = generation_allocated_bytes; + *generation_allocated_bytes = local_my_generation_allocated_bytes; + + my_slab_allocated_bytes = slab_allocated_bytes; + *slab_allocated_bytes = local_my_slab_allocated_bytes; +} + +/* + * Reset allocated bytes storage location. + * + * Expected to be called during backend shutdown, before the locations set up + * by pgstat_set_allocated_bytes_storage become invalid. + */ +void +pgstat_reset_allocated_bytes_storage(void) +{ + if (ProcGlobal) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + /* + * Add dsm allocations that have not been freed to global dsm + * accounting + */ + pg_atomic_add_fetch_u64(&procglobal->global_dsm_allocation, + *my_dsm_allocated_bytes); + } + + /* Reset memory allocation variables */ + *my_allocated_bytes = local_my_allocated_bytes = 0; + *my_aset_allocated_bytes = local_my_aset_allocated_bytes = 0; + *my_dsm_allocated_bytes = local_my_dsm_allocated_bytes = 0; + *my_generation_allocated_bytes = local_my_generation_allocated_bytes = 0; + *my_slab_allocated_bytes = local_my_slab_allocated_bytes = 0; + + /* Point my_{*_}allocated_bytes from shared memory back to local */ + my_allocated_bytes = &local_my_allocated_bytes; + my_aset_allocated_bytes = &local_my_aset_allocated_bytes; + my_dsm_allocated_bytes = &local_my_dsm_allocated_bytes; + my_generation_allocated_bytes = &local_my_generation_allocated_bytes; + my_slab_allocated_bytes = &local_my_slab_allocated_bytes; +} diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 3876339ee1..fec7ae2d5f 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2032,3 +2032,87 @@ pg_stat_have_stats(PG_FUNCTION_ARGS) PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objoid)); } + +/* + * Get the memory allocation of PG backends. + */ +Datum +pg_stat_get_memory_allocation(PG_FUNCTION_ARGS) +{ +#define PG_STAT_GET_MEMORY_ALLOCATION_COLS 7 + int num_backends = pgstat_fetch_stat_numbackends(); + int curr_backend; + int pid = PG_ARGISNULL(0) ? -1 : PG_GETARG_INT32(0); + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + + InitMaterializedSRF(fcinfo, 0); + + /* 1-based index */ + for (curr_backend = 1; curr_backend <= num_backends; curr_backend++) + { + /* for each row */ + Datum values[PG_STAT_GET_MEMORY_ALLOCATION_COLS] = {0}; + bool nulls[PG_STAT_GET_MEMORY_ALLOCATION_COLS] = {0}; + LocalPgBackendStatus *local_beentry; + PgBackendStatus *beentry; + + /* Get the next one in the list */ + local_beentry = pgstat_fetch_stat_local_beentry(curr_backend); + beentry = &local_beentry->backendStatus; + + /* If looking for specific PID, ignore all the others */ + if (pid != -1 && beentry->st_procpid != pid) + continue; + + /* Values available to all callers */ + if (beentry->st_databaseid != InvalidOid) + values[0] = ObjectIdGetDatum(beentry->st_databaseid); + else + nulls[0] = true; + + values[1] = Int32GetDatum(beentry->st_procpid); + values[2] = UInt64GetDatum(beentry->allocated_bytes); + values[3] = UInt64GetDatum(beentry->aset_allocated_bytes); + values[4] = UInt64GetDatum(beentry->dsm_allocated_bytes); + values[5] = UInt64GetDatum(beentry->generation_allocated_bytes); + values[6] = UInt64GetDatum(beentry->slab_allocated_bytes); + + tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); + + /* If only a single backend was requested, and we found it, break. */ + if (pid != -1) + break; + } + + return (Datum) 0; +} + +/* + * Get the global memory allocation statistics. + */ +Datum +pg_stat_get_global_memory_allocation(PG_FUNCTION_ARGS) +{ +#define PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS 2 + TupleDesc tupdesc; + Datum values[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; + bool nulls[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; + volatile PROC_HDR *procglobal = ProcGlobal; + + /* Initialise attributes information in the tuple descriptor */ + tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "datid", + OIDOID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 2, "global_dsm_allocated_bytes", + INT8OID, -1, 0); + BlessTupleDesc(tupdesc); + + /* datid */ + values[0] = ObjectIdGetDatum(MyDatabaseId); + + /* get global_dsm_allocated_bytes */ + values[1] = Int64GetDatum(pg_atomic_read_u64(&procglobal->global_dsm_allocation)); + + /* Returns the record as Datum */ + PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls))); +} diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c index 537d92c0cf..9b47450813 100644 --- a/src/backend/utils/init/miscinit.c +++ b/src/backend/utils/init/miscinit.c @@ -170,6 +170,9 @@ InitPostmasterChild(void) (errcode_for_socket_access(), errmsg_internal("could not set postmaster death monitoring pipe to FD_CLOEXEC mode: %m"))); #endif + + /* Init allocated bytes to avoid double counting parent allocation */ + pgstat_init_allocated_bytes(); } /* diff --git a/src/backend/utils/mmgr/aset.c b/src/backend/utils/mmgr/aset.c index d2dcf526d6..a599a3a6e4 100644 --- a/src/backend/utils/mmgr/aset.c +++ b/src/backend/utils/mmgr/aset.c @@ -47,6 +47,7 @@ #include "postgres.h" #include "port/pg_bitutils.h" +#include "utils/backend_status.h" #include "utils/memdebug.h" #include "utils/memutils.h" #include "utils/memutils_memorychunk.h" @@ -517,6 +518,7 @@ AllocSetContextCreateInternal(MemoryContext parent, name); ((MemoryContext) set)->mem_allocated = firstBlockSize; + pgstat_report_allocated_bytes_increase(firstBlockSize, PG_ALLOC_ASET); return (MemoryContext) set; } @@ -539,6 +541,7 @@ AllocSetReset(MemoryContext context) AllocSet set = (AllocSet) context; AllocBlock block; Size keepersize PG_USED_FOR_ASSERTS_ONLY; + uint64 deallocation = 0; Assert(AllocSetIsValid(set)); @@ -581,6 +584,7 @@ AllocSetReset(MemoryContext context) { /* Normal case, release the block */ context->mem_allocated -= block->endptr - ((char *) block); + deallocation += block->endptr - ((char *) block); #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->freeptr - ((char *) block)); @@ -591,6 +595,7 @@ AllocSetReset(MemoryContext context) } Assert(context->mem_allocated == keepersize); + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_ASET); /* Reset block size allocation sequence, too */ set->nextBlockSize = set->initBlockSize; @@ -609,6 +614,7 @@ AllocSetDelete(MemoryContext context) AllocSet set = (AllocSet) context; AllocBlock block = set->blocks; Size keepersize PG_USED_FOR_ASSERTS_ONLY; + uint64 deallocation = 0; Assert(AllocSetIsValid(set)); @@ -647,11 +653,13 @@ AllocSetDelete(MemoryContext context) freelist->first_free = (AllocSetContext *) oldset->header.nextchild; freelist->num_free--; + deallocation += oldset->header.mem_allocated; /* All that remains is to free the header/initial block */ free(oldset); } Assert(freelist->num_free == 0); + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_ASET); } /* Now add the just-deleted context to the freelist. */ @@ -668,7 +676,10 @@ AllocSetDelete(MemoryContext context) AllocBlock next = block->next; if (!IsKeeperBlock(set, block)) + { context->mem_allocated -= block->endptr - ((char *) block); + deallocation += block->endptr - ((char *) block); + } #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->freeptr - ((char *) block)); @@ -681,6 +692,7 @@ AllocSetDelete(MemoryContext context) } Assert(context->mem_allocated == keepersize); + pgstat_report_allocated_bytes_decrease(deallocation + context->mem_allocated, PG_ALLOC_ASET); /* Finally, free the context header, including the keeper block */ free(set); @@ -717,6 +729,7 @@ AllocSetAllocLarge(MemoryContext context, Size size, int flags) return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); block->aset = set; block->freeptr = block->endptr = ((char *) block) + blksize; @@ -923,6 +936,7 @@ AllocSetAllocFromNewBlock(MemoryContext context, Size size, int flags, return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); block->aset = set; block->freeptr = ((char *) block) + ALLOC_BLOCKHDRSZ; @@ -1100,6 +1114,7 @@ AllocSetFree(void *pointer) block->next->prev = block->prev; set->header.mem_allocated -= block->endptr - ((char *) block); + pgstat_report_allocated_bytes_decrease(block->endptr - ((char *) block), PG_ALLOC_ASET); #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->freeptr - ((char *) block)); @@ -1233,7 +1248,9 @@ AllocSetRealloc(void *pointer, Size size, int flags) /* updated separately, not to underflow when (oldblksize > blksize) */ set->header.mem_allocated -= oldblksize; + pgstat_report_allocated_bytes_decrease(oldblksize, PG_ALLOC_ASET); set->header.mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); block->freeptr = block->endptr = ((char *) block) + blksize; diff --git a/src/backend/utils/mmgr/generation.c b/src/backend/utils/mmgr/generation.c index 9124d9b952..d511b67b08 100644 --- a/src/backend/utils/mmgr/generation.c +++ b/src/backend/utils/mmgr/generation.c @@ -37,6 +37,7 @@ #include "lib/ilist.h" #include "port/pg_bitutils.h" +#include "utils/backend_status.h" #include "utils/memdebug.h" #include "utils/memutils.h" #include "utils/memutils_memorychunk.h" @@ -266,6 +267,7 @@ GenerationContextCreate(MemoryContext parent, name); ((MemoryContext) set)->mem_allocated = firstBlockSize; + pgstat_report_allocated_bytes_increase(firstBlockSize, PG_ALLOC_GENERATION); return (MemoryContext) set; } @@ -284,6 +286,7 @@ GenerationReset(MemoryContext context) { GenerationContext *set = (GenerationContext *) context; dlist_mutable_iter miter; + uint64 deallocation = 0; Assert(GenerationIsValid(set)); @@ -306,9 +309,14 @@ GenerationReset(MemoryContext context) if (IsKeeperBlock(set, block)) GenerationBlockMarkEmpty(block); else + { + deallocation += block->blksize; GenerationBlockFree(set, block); + } } + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_GENERATION); + /* set it so new allocations to make use of the keeper block */ set->block = KeeperBlock(set); @@ -329,6 +337,9 @@ GenerationDelete(MemoryContext context) { /* Reset to release all releasable GenerationBlocks */ GenerationReset(context); + + pgstat_report_allocated_bytes_decrease(context->mem_allocated, PG_ALLOC_GENERATION); + /* And free the context header and keeper block */ free(context); } @@ -366,6 +377,7 @@ GenerationAllocLarge(MemoryContext context, Size size, int flags) return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_GENERATION); /* block with a single (used) chunk */ block->context = set; @@ -488,6 +500,7 @@ GenerationAllocFromNewBlock(MemoryContext context, Size size, int flags, return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_GENERATION); /* initialize the new block */ GenerationBlockInit(set, block, blksize); @@ -672,6 +685,7 @@ GenerationBlockFree(GenerationContext *set, GenerationBlock *block) dlist_delete(&block->node); ((MemoryContext) set)->mem_allocated -= block->blksize; + pgstat_report_allocated_bytes_decrease(block->blksize, PG_ALLOC_GENERATION); #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->blksize); diff --git a/src/backend/utils/mmgr/slab.c b/src/backend/utils/mmgr/slab.c index 516e1c95aa..98a8bbaf91 100644 --- a/src/backend/utils/mmgr/slab.c +++ b/src/backend/utils/mmgr/slab.c @@ -69,6 +69,7 @@ #include "postgres.h" #include "lib/ilist.h" +#include "utils/backend_status.h" #include "utils/memdebug.h" #include "utils/memutils.h" #include "utils/memutils_memorychunk.h" @@ -417,6 +418,13 @@ SlabContextCreate(MemoryContext parent, parent, name); + /* + * If SlabContextCreate is updated to add context header size to + * context->mem_allocated, then update here and SlabDelete appropriately + */ + pgstat_report_allocated_bytes_increase(Slab_CONTEXT_HDRSZ(slab->chunksPerBlock), + PG_ALLOC_SLAB); + return (MemoryContext) slab; } @@ -433,6 +441,7 @@ SlabReset(MemoryContext context) SlabContext *slab = (SlabContext *) context; dlist_mutable_iter miter; int i; + uint64 deallocation = 0; Assert(SlabIsValid(slab)); @@ -453,6 +462,7 @@ SlabReset(MemoryContext context) #endif free(block); context->mem_allocated -= slab->blockSize; + deallocation += slab->blockSize; } /* walk over blocklist and free the blocks */ @@ -469,9 +479,11 @@ SlabReset(MemoryContext context) #endif free(block); context->mem_allocated -= slab->blockSize; + deallocation += slab->blockSize; } } + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_SLAB); slab->curBlocklistIndex = 0; Assert(context->mem_allocated == 0); @@ -486,6 +498,14 @@ SlabDelete(MemoryContext context) { /* Reset to release all the SlabBlocks */ SlabReset(context); + + /* + * Until context header allocation is included in context->mem_allocated, + * cast to slab and decrement the header allocation + */ + pgstat_report_allocated_bytes_decrease(Slab_CONTEXT_HDRSZ(((SlabContext *) context)->chunksPerBlock), + PG_ALLOC_SLAB); + /* And free the context header */ free(context); } @@ -569,6 +589,7 @@ SlabAllocFromNewBlock(MemoryContext context, Size size, int flags) block->slab = slab; context->mem_allocated += slab->blockSize; + pgstat_report_allocated_bytes_increase(slab->blockSize, PG_ALLOC_SLAB); /* use the first chunk in the new block */ chunk = SlabBlockGetChunk(slab, block, 0); @@ -797,6 +818,7 @@ SlabFree(void *pointer) #endif free(block); slab->header.mem_allocated -= slab->blockSize; + pgstat_report_allocated_bytes_decrease(slab->blockSize, PG_ALLOC_SLAB); } /* diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 291ed876fc..47903e755e 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -5435,6 +5435,23 @@ proname => 'pg_stat_get_backend_idset', prorows => '100', proretset => 't', provolatile => 's', proparallel => 'r', prorettype => 'int4', proargtypes => '', prosrc => 'pg_stat_get_backend_idset' }, +{ oid => '9890', + descr => 'statistics: memory allocation information for backends', + proname => 'pg_stat_get_memory_allocation', prorows => '100', proisstrict => 'f', + proretset => 't', provolatile => 's', proparallel => 'r', + prorettype => 'record', proargtypes => 'int4', + proallargtypes => '{int4,oid,int4,int8,int8,int8,int8,int8}', + proargmodes => '{i,o,o,o,o,o,o,o}', + proargnames => '{pid,datid,pid,allocated_bytes,aset_allocated_bytes,dsm_allocated_bytes,generation_allocated_bytes,slab_allocated_bytes}', + prosrc => 'pg_stat_get_memory_allocation' }, +{ oid => '9891', + descr => 'statistics: global memory allocation information', + proname => 'pg_stat_get_global_memory_allocation', proisstrict => 'f', + provolatile => 's', proparallel => 'r', prorettype => 'record', + proargtypes => '', proallargtypes => '{oid,int8}', + proargmodes => '{o,o}', + proargnames => '{datid,global_dsm_allocated_bytes}', + prosrc =>'pg_stat_get_global_memory_allocation' }, { oid => '2022', descr => 'statistics: information about currently active backends', proname => 'pg_stat_get_activity', prorows => '100', proisstrict => 'f', diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1095aefddf..a350f455cd 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -422,6 +422,8 @@ typedef struct PROC_HDR int spins_per_delay; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Global dsm allocations */ + pg_atomic_uint64 global_dsm_allocation; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; diff --git a/src/include/utils/backend_status.h b/src/include/utils/backend_status.h index 7b7f6f59d0..cbf801884d 100644 --- a/src/include/utils/backend_status.h +++ b/src/include/utils/backend_status.h @@ -10,6 +10,7 @@ #ifndef BACKEND_STATUS_H #define BACKEND_STATUS_H +#include "common/int.h" #include "datatype/timestamp.h" #include "libpq/pqcomm.h" #include "miscadmin.h" /* for BackendType */ @@ -32,6 +33,14 @@ typedef enum BackendState STATE_DISABLED, } BackendState; +/* Enum helper for reporting memory allocator type */ +enum pg_allocator_type +{ + PG_ALLOC_ASET = 1, + PG_ALLOC_DSM, + PG_ALLOC_GENERATION, + PG_ALLOC_SLAB +}; /* ---------- * Shared-memory data structures @@ -170,6 +179,15 @@ typedef struct PgBackendStatus /* query identifier, optionally computed using post_parse_analyze_hook */ uint64 st_query_id; + + /* Current memory allocated to this backend */ + uint64 allocated_bytes; + + /* Current memory allocated to this backend by type */ + uint64 aset_allocated_bytes; + uint64 dsm_allocated_bytes; + uint64 generation_allocated_bytes; + uint64 slab_allocated_bytes; } PgBackendStatus; @@ -292,6 +310,11 @@ extern PGDLLIMPORT int pgstat_track_activity_query_size; * ---------- */ extern PGDLLIMPORT PgBackendStatus *MyBEEntry; +extern PGDLLIMPORT uint64 *my_allocated_bytes; +extern PGDLLIMPORT uint64 *my_aset_allocated_bytes; +extern PGDLLIMPORT uint64 *my_dsm_allocated_bytes; +extern PGDLLIMPORT uint64 *my_generation_allocated_bytes; +extern PGDLLIMPORT uint64 *my_slab_allocated_bytes; /* ---------- @@ -323,7 +346,12 @@ extern const char *pgstat_get_backend_current_activity(int pid, bool checkUser); extern const char *pgstat_get_crashed_backend_activity(int pid, char *buffer, int buflen); extern uint64 pgstat_get_my_query_id(void); - +extern void pgstat_set_allocated_bytes_storage(uint64 *allocated_bytes, + uint64 *aset_allocated_bytes, + uint64 *dsm_allocated_bytes, + uint64 *generation_allocated_bytes, + uint64 *slab_allocated_bytes); +extern void pgstat_reset_allocated_bytes_storage(void); /* ---------- * Support functions for the SQL-callable functions to @@ -336,5 +364,119 @@ extern LocalPgBackendStatus *pgstat_get_local_beentry_by_proc_number(ProcNumber extern LocalPgBackendStatus *pgstat_get_local_beentry_by_index(int idx); extern char *pgstat_clip_activity(const char *raw_activity); +/* ---------- + * pgstat_report_allocated_bytes_decrease() - + * Called to report decrease in memory allocated for this backend. + * + * my_{*_}allocated_bytes initially points to local memory, making it safe to + * call this before pgstats has been initialized. + * ---------- + */ +static inline void +pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, + int pg_allocator_type) +{ + uint64 temp; + + /* Avoid allocated_bytes unsigned integer overflow on decrease */ + if (pg_sub_u64_overflow(*my_allocated_bytes, proc_allocated_bytes, &temp)) + { + /* On overflow, set allocated bytes and allocator type bytes to zero */ + *my_allocated_bytes = 0; + *my_aset_allocated_bytes = 0; + *my_dsm_allocated_bytes = 0; + *my_generation_allocated_bytes = 0; + *my_slab_allocated_bytes = 0; + } + else + { + /* decrease allocation */ + *my_allocated_bytes -= proc_allocated_bytes; + + /* Decrease allocator type allocated bytes. */ + switch (pg_allocator_type) + { + case PG_ALLOC_ASET: + *my_aset_allocated_bytes -= proc_allocated_bytes; + break; + case PG_ALLOC_DSM: + + /* + * Some dsm allocations live beyond process exit. These are + * accounted for in a global counter in + * pgstat_reset_allocated_bytes_storage at process exit. + */ + *my_dsm_allocated_bytes -= proc_allocated_bytes; + break; + case PG_ALLOC_GENERATION: + *my_generation_allocated_bytes -= proc_allocated_bytes; + break; + case PG_ALLOC_SLAB: + *my_slab_allocated_bytes -= proc_allocated_bytes; + break; + } + } + + return; +} + +/* ---------- + * pgstat_report_allocated_bytes_increase() - + * Called to report increase in memory allocated for this backend. + * + * my_allocated_bytes initially points to local memory, making it safe to call + * this before pgstats has been initialized. + * ---------- + */ +static inline void +pgstat_report_allocated_bytes_increase(int64 proc_allocated_bytes, + int pg_allocator_type) +{ + *my_allocated_bytes += proc_allocated_bytes; + + /* Increase allocator type allocated bytes */ + switch (pg_allocator_type) + { + case PG_ALLOC_ASET: + *my_aset_allocated_bytes += proc_allocated_bytes; + break; + case PG_ALLOC_DSM: + + /* + * Some dsm allocations live beyond process exit. These are + * accounted for in a global counter in + * pgstat_reset_allocated_bytes_storage at process exit. + */ + *my_dsm_allocated_bytes += proc_allocated_bytes; + break; + case PG_ALLOC_GENERATION: + *my_generation_allocated_bytes += proc_allocated_bytes; + break; + case PG_ALLOC_SLAB: + *my_slab_allocated_bytes += proc_allocated_bytes; + break; + } + + return; +} + +/* --------- + * pgstat_init_allocated_bytes() - + * + * Called to initialize allocated bytes variables after fork and to + * avoid double counting allocations. + * --------- + */ +static inline void +pgstat_init_allocated_bytes(void) +{ + *my_allocated_bytes = 0; + *my_aset_allocated_bytes = 0; + *my_dsm_allocated_bytes = 0; + *my_generation_allocated_bytes = 0; + *my_slab_allocated_bytes = 0; + + return; +} #endif /* BACKEND_STATUS_H */ diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 0cd2c64fca..2f62f5e4ea 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1877,6 +1877,24 @@ pg_stat_database_conflicts| SELECT oid AS datid, pg_stat_get_db_conflict_startup_deadlock(oid) AS confl_deadlock, pg_stat_get_db_conflict_logicalslot(oid) AS confl_active_logicalslot FROM pg_database d; +pg_stat_global_memory_allocation| WITH sums AS ( + SELECT sum(pg_stat_memory_allocation.aset_allocated_bytes) AS total_aset_allocated_bytes, + sum(pg_stat_memory_allocation.dsm_allocated_bytes) AS total_dsm_allocated_bytes, + sum(pg_stat_memory_allocation.generation_allocated_bytes) AS total_generation_allocated_bytes, + sum(pg_stat_memory_allocation.slab_allocated_bytes) AS total_slab_allocated_bytes + FROM pg_stat_memory_allocation + ) + SELECT s.datid, + current_setting('shared_memory_size'::text, true) AS shared_memory_size, + (current_setting('shared_memory_size_in_huge_pages'::text, true))::integer AS shared_memory_size_in_huge_pages, + s.global_dsm_allocated_bytes, + sums.total_aset_allocated_bytes, + sums.total_dsm_allocated_bytes, + sums.total_generation_allocated_bytes, + sums.total_slab_allocated_bytes + FROM sums, + (pg_stat_get_global_memory_allocation() s(datid, global_dsm_allocated_bytes) + LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_gssapi| SELECT pid, gss_auth AS gss_authenticated, gss_princ AS principal, @@ -1903,6 +1921,15 @@ pg_stat_io| SELECT backend_type, fsync_time, stats_reset FROM pg_stat_get_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset); +pg_stat_memory_allocation| SELECT s.datid, + s.pid, + s.allocated_bytes, + s.aset_allocated_bytes, + s.dsm_allocated_bytes, + s.generation_allocated_bytes, + s.slab_allocated_bytes + FROM (pg_stat_get_memory_allocation(NULL::integer) s(datid, pid, allocated_bytes, aset_allocated_bytes, dsm_allocated_bytes, generation_allocated_bytes, slab_allocated_bytes) + LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_progress_analyze| SELECT s.pid, s.datid, d.datname, diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out index 6e08898b18..902d827998 100644 --- a/src/test/regress/expected/stats.out +++ b/src/test/regress/expected/stats.out @@ -1646,4 +1646,40 @@ SELECT COUNT(*) FROM brin_hot_3 WHERE a = 2; DROP TABLE brin_hot_3; SET enable_seqscan = on; +-- ensure that allocated_bytes exist for backends +SELECT + allocated_bytes > 0 AS result +FROM + pg_stat_activity ps + JOIN pg_stat_memory_allocation pa ON (pa.pid = ps.pid) +WHERE + backend_type IN ('checkpointer', 'background writer', 'walwriter', 'autovacuum launcher'); + result +-------- + t + t + t + t +(4 rows) + +-- ensure that pg_stat_global_memory_allocation view exists +SELECT + datid > 0, pg_size_bytes(shared_memory_size) >= 0, shared_memory_size_in_huge_pages >= -1, global_dsm_allocated_bytes >= 0 +FROM + pg_stat_global_memory_allocation; + ?column? | ?column? | ?column? | ?column? +----------+----------+----------+---------- + t | t | t | t +(1 row) + +-- ensure that pg_stat_memory_allocation view exists +SELECT + pid > 0, allocated_bytes >= 0, aset_allocated_bytes >= 0, dsm_allocated_bytes >= 0, generation_allocated_bytes >= 0, slab_allocated_bytes >= 0 +FROM + pg_stat_memory_allocation limit 1; + ?column? | ?column? | ?column? | ?column? | ?column? | ?column? +----------+----------+----------+----------+----------+---------- + t | t | t | t | t | t +(1 row) + -- End of Stats Test diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql index d8ac0d06f4..40746c9258 100644 --- a/src/test/regress/sql/stats.sql +++ b/src/test/regress/sql/stats.sql @@ -849,4 +849,24 @@ DROP TABLE brin_hot_3; SET enable_seqscan = on; +-- ensure that allocated_bytes exist for backends +SELECT + allocated_bytes > 0 AS result +FROM + pg_stat_activity ps + JOIN pg_stat_memory_allocation pa ON (pa.pid = ps.pid) +WHERE + backend_type IN ('checkpointer', 'background writer', 'walwriter', 'autovacuum launcher'); + +-- ensure that pg_stat_global_memory_allocation view exists +SELECT + datid > 0, pg_size_bytes(shared_memory_size) >= 0, shared_memory_size_in_huge_pages >= -1, global_dsm_allocated_bytes >= 0 +FROM + pg_stat_global_memory_allocation; + +-- ensure that pg_stat_memory_allocation view exists +SELECT + pid > 0, allocated_bytes >= 0, aset_allocated_bytes >= 0, dsm_allocated_bytes >= 0, generation_allocated_bytes >= 0, slab_allocated_bytes >= 0 +FROM + pg_stat_memory_allocation limit 1; -- End of Stats Test -- 2.43.2 [text/x-patch] v20140313-0002-fixup-pgstat_get_local_beentry_by_index.patch (909B, ../../[email protected]/3-v20140313-0002-fixup-pgstat_get_local_beentry_by_index.patch) download | inline diff: From 0934a92f51ccb19266a2faa2f0b9146e3f9a665c Mon Sep 17 00:00:00 2001 From: Tomas Vondra <[email protected]> Date: Tue, 26 Dec 2023 18:05:02 +0100 Subject: [PATCH 2/3] fixup: pgstat_get_local_beentry_by_index --- src/backend/utils/adt/pgstatfuncs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index fec7ae2d5f..9c82ec48cb 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2057,7 +2057,7 @@ pg_stat_get_memory_allocation(PG_FUNCTION_ARGS) PgBackendStatus *beentry; /* Get the next one in the list */ - local_beentry = pgstat_fetch_stat_local_beentry(curr_backend); + local_beentry = pgstat_get_local_beentry_by_index(curr_backend); beentry = &local_beentry->backendStatus; /* If looking for specific PID, ignore all the others */ -- 2.43.2 [text/x-patch] v20140313-0003-Add-the-ability-to-limit-the-amount-of-memory-that-c.patch (37.7K, ../../[email protected]/4-v20140313-0003-Add-the-ability-to-limit-the-amount-of-memory-that-c.patch) download | inline diff: From 3e65eb6c298d3160db9e528ab3c2b857acd57937 Mon Sep 17 00:00:00 2001 From: Tomas Vondra <[email protected]> Date: Tue, 26 Dec 2023 17:55:23 +0100 Subject: [PATCH 3/3] Add the ability to limit the amount of memory that can be allocated to backends. This builds on the work that adds backend memory allocated tracking. Add GUC variable max_total_backend_memory. Specifies a limit to the amount of memory (in MB) that may be allocated to backends in total (i.e. this is not a per user or per backend limit). If unset, or set to 0 it is disabled. It is intended as a resource to help avoid the OOM killer on LINUX and manage resources in general. A backend request that would exhaust max_total_backend_memory memory will be denied with an out of memory error causing that backend's current query/transaction to fail. Further requests will not be allocated until dropping below the limit. Keep this in mind when setting this value. Due to the dynamic nature of memory allocations, this limit is not exact. This limit does not affect auxiliary backend processes. Backend memory allocations are displayed in the pg_stat_memory_allocation and pg_stat_global_memory_allocation views. --- doc/src/sgml/config.sgml | 30 +++ doc/src/sgml/monitoring.sgml | 38 +++- src/backend/catalog/system_views.sql | 2 + src/backend/port/sysv_shmem.c | 9 + src/backend/postmaster/postmaster.c | 5 + src/backend/storage/ipc/dsm_impl.c | 18 ++ src/backend/storage/lmgr/proc.c | 45 +++++ src/backend/utils/activity/backend_status.c | 175 ++++++++++++++++++ src/backend/utils/adt/pgstatfuncs.c | 16 +- src/backend/utils/hash/dynahash.c | 3 +- src/backend/utils/init/miscinit.c | 8 + src/backend/utils/misc/guc_tables.c | 11 ++ src/backend/utils/misc/postgresql.conf.sample | 3 + src/backend/utils/mmgr/aset.c | 33 ++++ src/backend/utils/mmgr/generation.c | 16 ++ src/backend/utils/mmgr/slab.c | 15 +- src/include/catalog/pg_proc.dat | 6 +- src/include/storage/proc.h | 7 + src/include/utils/backend_status.h | 103 ++++++++++- src/test/regress/expected/rules.out | 4 +- 20 files changed, 526 insertions(+), 21 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 65a6e6c408..4f26284ee1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -2306,6 +2306,36 @@ include_dir 'conf.d' </listitem> </varlistentry> + <varlistentry id="guc-max-total-backend-memory" xreflabel="max_total_backend_memory"> + <term><varname>max_total_backend_memory</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_total_backend_memory</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies a limit to the amount of memory (MB) that may be allocated to + backends in total (i.e. this is not a per user or per backend limit). + If unset, or set to 0 it is disabled. At databse startup + max_total_backend_memory is reduced by shared_memory_size_mb + (includes shared buffers and other memory required for initialization). + Each backend process is intialized with a 1MB local allowance which + also reduces total_bkend_mem_bytes_available. Keep this in mind when + setting this value. A backend request that would exhaust the limit will + be denied with an out of memory error causing that backend's current + query/transaction to fail. Further requests will not be allocated until + dropping below the limit. This limit does not affect auxiliary backend + processes + <xref linkend="glossary-auxiliary-proc"/> or the postmaster process. + Backend memory allocations (<varname>allocated_bytes</varname>) are + displayed in the + <link linkend="monitoring-pg-stat-memory-allocation-view"><structname>pg_stat_memory_allocation</structname></link> + view. Due to the dynamic nature of memory allocations, this limit is + not exact. + </para> + </listitem> + </varlistentry> + </variablelist> </sect2> diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 5f827fe0b0..dbe40b8810 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -4658,10 +4658,7 @@ description | Waiting for a newly initialized WAL file to reach durable storage </para> <para> Memory currently allocated to this backend in bytes. This is the balance - of bytes allocated and freed by this backend. Dynamic shared memory - allocations are included only in the value displayed for the backend that - created them, they are not included in the value for backends that are - attached to them to avoid double counting. + of bytes allocated and freed by this backend. </para></entry> </row> @@ -4778,6 +4775,39 @@ description | Waiting for a newly initialized WAL file to reach durable storage </para></entry> </row> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>max_total_backend_memory_bytes</structfield> <type>bigint</type> + </para> + <para> + Reports the user defined backend maximum allowed shared memory in bytes. + 0 if disabled or not set. See + <xref linkend="guc-max-total-backend-memory"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_bkend_mem_bytes_available</structfield> <type>bigint</type> + </para> + <para> + Tracks max_total_backend_memory (in bytes) available for allocation. At + database startup, total_bkend_mem_bytes_available is reduced by the + byte equivalent of shared_memory_size_mb. Each backend process is + intialized with a 1MB local allowance which also reduces + total_bkend_mem_bytes_available. A process's allocation requests reduce + it's local allowance. If a process's allocation request exceeds it's + remaining allowance, an attempt is made to refill the local allowance + from total_bkend_mem_bytes_available. If the refill request fails, then + the requesting process will fail with an out of memory error resulting + in the cancellation of that process's active query/transaction. The + default refill allocation quantity is 1MB. If a request is greater than + 1MB, an attempt will be made to allocate the full amount. If + max_total_backend_memory is disabled, this will be -1. + <xref linkend="guc-max-total-backend-memory"/>. + </para></entry> + </row> + <row> <entry role="catalog_table_entry"><para role="column_definition"> <structfield>global_dsm_allocated_bytes</structfield> <type>bigint</type> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 61ff4a59b6..c646b28f16 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1402,6 +1402,8 @@ SELECT S.datid AS datid, current_setting('shared_memory_size', true) as shared_memory_size, (current_setting('shared_memory_size_in_huge_pages', true))::integer as shared_memory_size_in_huge_pages, + pg_size_bytes(current_setting('max_total_backend_memory', true)) as max_total_backend_memory_bytes, + S.total_bkend_mem_bytes_available, S.global_dsm_allocated_bytes, sums.total_aset_allocated_bytes, sums.total_dsm_allocated_bytes, diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 1a6d8fa0fb..c0788732df 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -34,6 +34,7 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/pg_shmem.h" +#include "utils/backend_status.h" #include "utils/guc.h" #include "utils/guc_hooks.h" #include "utils/pidfile.h" @@ -918,6 +919,14 @@ PGSharedMemoryReAttach(void) dsm_set_control_handle(hdr->dsm_control); UsedShmemSegAddr = hdr; /* probably redundant */ + + /* + * Init allocated bytes to avoid double counting parent allocation for + * fork/exec processes. Forked processes perform this action in + * InitPostmasterChild. For EXEC_BACKEND processes we have to wait for + * shared memory to be reattached. + */ + pgstat_init_allocated_bytes(); } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 49fc6f979e..abb10ed7c8 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -556,6 +556,7 @@ typedef struct #endif char my_exec_path[MAXPGPATH]; char pkglib_path[MAXPGPATH]; + int max_total_bkend_mem; } BackendParameters; static void read_backend_variables(char *id, ClientSocket **client_sock, BackgroundWorker **worker); @@ -6152,6 +6153,8 @@ save_backend_variables(BackendParameters *param, ClientSocket *client_sock, Back strlcpy(param->pkglib_path, pkglib_path, MAXPGPATH); + param->max_total_bkend_mem = max_total_bkend_mem; + return true; } @@ -6391,6 +6394,8 @@ restore_backend_variables(BackendParameters *param, ClientSocket **client_sock, strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH); + max_total_bkend_mem = param->max_total_bkend_mem; + /* * We need to restore fd.c's counts of externally-opened FDs; to avoid * confusion, be sure to do this after restoring max_safe_fds. (Note: diff --git a/src/backend/storage/ipc/dsm_impl.c b/src/backend/storage/ipc/dsm_impl.c index af67e55bdf..b6dee75423 100644 --- a/src/backend/storage/ipc/dsm_impl.c +++ b/src/backend/storage/ipc/dsm_impl.c @@ -254,6 +254,16 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, return true; } + /* Do not exceed maximum allowed memory allocation */ + if (op == DSM_OP_CREATE && exceeds_max_total_bkend_mem(request_size)) + { + ereport(elevel, + (errcode_for_dynamic_shared_memory(), + errmsg("out of memory for segment \"%s\" - exceeds max_total_backend_memory: %m", + name))); + return false; + } + /* * Create new segment or open an existing one for attach. * @@ -523,6 +533,10 @@ dsm_impl_sysv(dsm_op op, dsm_handle handle, Size request_size, int flags = IPCProtection; size_t segsize; + /* Do not exceed maximum allowed memory allocation */ + if (op == DSM_OP_CREATE && exceeds_max_total_bkend_mem(request_size)) + return false; + /* * Allocate the memory BEFORE acquiring the resource, so that we don't * leak the resource if memory allocation fails. @@ -717,6 +731,10 @@ dsm_impl_windows(dsm_op op, dsm_handle handle, Size request_size, return true; } + /* Do not exceed maximum allowed memory allocation */ + if (op == DSM_OP_CREATE && exceeds_max_total_bkend_mem(request_size)) + return false; + /* Create new segment or open an existing one for attach. */ if (op == DSM_OP_CREATE) { diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 1959b5f4e6..6dbe4373f8 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -50,6 +50,7 @@ #include "storage/procsignal.h" #include "storage/spin.h" #include "storage/standby.h" +#include "utils/guc.h" #include "utils/timeout.h" #include "utils/timestamp.h" @@ -182,6 +183,50 @@ InitProcGlobal(void) pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PROC_NUMBER); pg_atomic_init_u64(&ProcGlobal->global_dsm_allocation, 0); + /* Setup backend memory limiting if configured */ + if (max_total_bkend_mem > 0) + { + /* + * Convert max_total_bkend_mem to bytes, account for + * shared_memory_size, and initialize total_bkend_mem_bytes. + */ + int result = 0; + + /* Get integer value of shared_memory_size */ + if (parse_int(GetConfigOption("shared_memory_size", true, false), &result, 0, NULL)) + { + /* + * Error on startup if backend memory limit is less than shared + * memory size. Warn on startup if backend memory available is + * less than arbitrarily picked value of 100MB. + */ + + if (max_total_bkend_mem - result <= 0) + { + ereport(ERROR, + errmsg("configured max_total_backend_memory %dMB is <= shared_memory_size %dMB", + max_total_bkend_mem, result), + errhint("Disable or increase the configuration parameter \"max_total_backend_memory\".")); + } + else if (max_total_bkend_mem - result <= 100) + { + ereport(WARNING, + errmsg("max_total_backend_memory %dMB - shared_memory_size %dMB is <= 100MB", + max_total_bkend_mem, result), + errhint("Consider increasing the configuration parameter \"max_total_backend_memory\".")); + } + + /* + * Account for shared memory size and initialize + * total_bkend_mem_bytes. + */ + pg_atomic_init_u64(&ProcGlobal->total_bkend_mem_bytes, + (uint64) max_total_bkend_mem * 1024 * 1024 - (uint64) result * 1024 * 1024); + } + else + ereport(ERROR, errmsg("max_total_backend_memory initialization is unable to parse shared_memory_size")); + } + /* * Create and initialize all the PGPROC structures we'll need. There are * five separate consumers: (1) normal backends, (2) autovacuum workers diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c index 25b545441b..c125dc3abb 100644 --- a/src/backend/utils/activity/backend_status.c +++ b/src/backend/utils/activity/backend_status.c @@ -44,6 +44,12 @@ bool pgstat_track_activities = false; int pgstat_track_activity_query_size = 1024; +/* + * Max backend memory allocation allowed (MB). 0 = disabled. + * Centralized bucket ProcGlobal->max_total_bkend_mem is initialized + * as a byte representation of this value in InitProcGlobal(). + */ +int max_total_bkend_mem = 0; /* exposed so that backend_progress.c can access it */ PgBackendStatus *MyBEEntry = NULL; @@ -67,6 +73,31 @@ uint64 *my_generation_allocated_bytes = &local_my_generation_allocated_bytes; uint64 local_my_slab_allocated_bytes = 0; uint64 *my_slab_allocated_bytes = &local_my_slab_allocated_bytes; +/* + * Define initial allocation allowance for a backend. + * + * NOTE: initial_allocation_allowance && allocation_allowance_refill_qty + * may be candidates for future GUC variables. Arbitrary 1MB selected initially. + */ +uint64 initial_allocation_allowance = 1024 * 1024; +uint64 allocation_allowance_refill_qty = 1024 * 1024; + +/* + * Local counter to manage shared memory allocations. At backend startup, set to + * initial_allocation_allowance via pgstat_init_allocated_bytes(). Decrease as + * memory is malloc'd. When exhausted, atomically refill if available from + * ProcGlobal->max_total_bkend_mem via exceeds_max_total_bkend_mem(). + */ +uint64 allocation_allowance = 0; + +/* + * Local counter of free'd shared memory. Return to global + * max_total_bkend_mem when return threshold is met. Arbitrary 1MB bytes + * selected initially. + */ +uint64 allocation_return = 0; +uint64 allocation_return_threshold = 1024 * 1024; + static PgBackendStatus *BackendStatusArray = NULL; static char *BackendAppnameBuffer = NULL; static char *BackendClientHostnameBuffer = NULL; @@ -1272,6 +1303,8 @@ pgstat_set_allocated_bytes_storage(uint64 *allocated_bytes, my_slab_allocated_bytes = slab_allocated_bytes; *slab_allocated_bytes = local_my_slab_allocated_bytes; + + return; } /* @@ -1295,6 +1328,23 @@ pgstat_reset_allocated_bytes_storage(void) *my_dsm_allocated_bytes); } + /* + * When limiting maximum backend memory, return this backend's memory + * allocations to global. + */ + if (max_total_bkend_mem) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + pg_atomic_add_fetch_u64(&procglobal->total_bkend_mem_bytes, + *my_allocated_bytes + allocation_allowance + + allocation_return); + + /* Reset memory allocation variables */ + allocation_allowance = 0; + allocation_return = 0; + } + /* Reset memory allocation variables */ *my_allocated_bytes = local_my_allocated_bytes = 0; *my_aset_allocated_bytes = local_my_aset_allocated_bytes = 0; @@ -1308,4 +1358,129 @@ pgstat_reset_allocated_bytes_storage(void) my_dsm_allocated_bytes = &local_my_dsm_allocated_bytes; my_generation_allocated_bytes = &local_my_generation_allocated_bytes; my_slab_allocated_bytes = &local_my_slab_allocated_bytes; + + return; +} + +/* + * Determine if allocation request will exceed max backend memory allowed. + * Do not apply to auxiliary processes. + * Refill allocation request bucket when needed/possible. + */ +bool +exceeds_max_total_bkend_mem(uint64 allocation_request) +{ + bool result = false; + + /* + * When limiting maximum backend memory, attempt to refill allocation + * request bucket if needed. + */ + if (max_total_bkend_mem && allocation_request > allocation_allowance && + ProcGlobal != NULL) + { + volatile PROC_HDR *procglobal = ProcGlobal; + uint64 available_max_total_bkend_mem = 0; + bool sts = false; + + /* + * If allocation request is larger than memory refill quantity then + * attempt to increase allocation allowance with requested amount, + * otherwise fall through. If this refill fails we do not have enough + * memory to meet the request. + */ + if (allocation_request >= allocation_allowance_refill_qty) + { + while ((available_max_total_bkend_mem = pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)) >= allocation_request) + { + if ((result = pg_atomic_compare_exchange_u64(&procglobal->total_bkend_mem_bytes, + &available_max_total_bkend_mem, + available_max_total_bkend_mem - allocation_request))) + { + allocation_allowance = allocation_allowance + allocation_request; + break; + } + } + + /* + * Exclude auxiliary and Postmaster processes from the check. + * Return false. While we want to exclude them from the check, we + * do not want to exclude them from the above allocation handling. + */ + switch (MyBackendType) + { + case B_STARTUP: + case B_ARCHIVER: + case B_BG_WRITER: + case B_CHECKPOINTER: + case B_WAL_WRITER: + case B_WAL_RECEIVER: + case B_WAL_SUMMARIZER: + return false; + default: + break; + } + + if (MyProcPid == PostmasterPid) + return false; + + /* + * If the atomic exchange fails (result == false), we do not have + * enough reserve memory to meet the request. Negate result to + * return the proper value. + */ + + return !result; + } + + /* + * Attempt to increase allocation allowance by memory refill quantity. + * If available memory is/becomes less than memory refill quantity, + * fall through to attempt to allocate remaining available memory. + */ + while ((available_max_total_bkend_mem = pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)) >= allocation_allowance_refill_qty) + { + if ((sts = pg_atomic_compare_exchange_u64(&procglobal->total_bkend_mem_bytes, + &available_max_total_bkend_mem, + available_max_total_bkend_mem - allocation_allowance_refill_qty))) + { + allocation_allowance = allocation_allowance + allocation_allowance_refill_qty; + break; + } + } + + /* Do not attempt to increase allocation if available memory is below + * allocation_allowance_refill_qty . + */ + + /* + * If refill is not successful, we return true, memory limit exceeded + */ + if (!sts) + result = true; + } + + /* + * Exclude auxiliary and postmaster processes from the check. Return false. + * While we want to exclude them from the check, we do not want to exclude + * them from the above allocation handling. + */ + switch (MyBackendType) + { + case B_STARTUP: + case B_ARCHIVER: + case B_BG_WRITER: + case B_CHECKPOINTER: + case B_WAL_WRITER: + case B_WAL_RECEIVER: + case B_WAL_SUMMARIZER: + result = false; + default: + break; + } + + if (MyProcPid == PostmasterPid) + result = false; + + return result; } diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 9c82ec48cb..15d2800d5b 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2093,7 +2093,7 @@ pg_stat_get_memory_allocation(PG_FUNCTION_ARGS) Datum pg_stat_get_global_memory_allocation(PG_FUNCTION_ARGS) { -#define PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS 2 +#define PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS 3 TupleDesc tupdesc; Datum values[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; bool nulls[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; @@ -2103,15 +2103,23 @@ pg_stat_get_global_memory_allocation(PG_FUNCTION_ARGS) tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS); TupleDescInitEntry(tupdesc, (AttrNumber) 1, "datid", OIDOID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 2, "global_dsm_allocated_bytes", + TupleDescInitEntry(tupdesc, (AttrNumber) 2, "total_bkend_mem_bytes_available", + INT8OID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 3, "global_dsm_allocated_bytes", INT8OID, -1, 0); BlessTupleDesc(tupdesc); /* datid */ values[0] = ObjectIdGetDatum(MyDatabaseId); - /* get global_dsm_allocated_bytes */ - values[1] = Int64GetDatum(pg_atomic_read_u64(&procglobal->global_dsm_allocation)); + /* Get total_bkend_mem_bytes - return -1 if disabled */ + if (max_total_bkend_mem == 0) + values[1] = Int64GetDatum(-1); + else + values[1] = Int64GetDatum(pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)); + + /* Get global_dsm_allocated_bytes */ + values[2] = Int64GetDatum(pg_atomic_read_u64(&procglobal->global_dsm_allocation)); /* Returns the record as Datum */ PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls))); diff --git a/src/backend/utils/hash/dynahash.c b/src/backend/utils/hash/dynahash.c index a4152080b5..9450032a89 100644 --- a/src/backend/utils/hash/dynahash.c +++ b/src/backend/utils/hash/dynahash.c @@ -104,7 +104,6 @@ #include "utils/dynahash.h" #include "utils/memutils.h" - /* * Constants * @@ -359,7 +358,6 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) Assert(flags & HASH_ELEM); Assert(info->keysize > 0); Assert(info->entrysize >= info->keysize); - /* * For shared hash tables, we have a local hash header (HTAB struct) that * we allocate in TopMemoryContext; all else is in shared memory. @@ -377,6 +375,7 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) } else { + /* Set up to allocate the hash header */ /* Create the hash table's private memory context */ if (flags & HASH_CONTEXT) CurrentDynaHashCxt = info->hcxt; diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c index 9b47450813..d72ec3a0db 100644 --- a/src/backend/utils/init/miscinit.c +++ b/src/backend/utils/init/miscinit.c @@ -171,8 +171,16 @@ InitPostmasterChild(void) errmsg_internal("could not set postmaster death monitoring pipe to FD_CLOEXEC mode: %m"))); #endif + /* + * Init pgstat allocated bytes counters here for forked backends. + * Fork/exec backends have not yet reattached to shared memory at this + * point. They will init pgstat allocated bytes counters in + * PGSharedMemoryReAttach. + */ +#ifndef EXEC_BACKEND /* Init allocated bytes to avoid double counting parent allocation */ pgstat_init_allocated_bytes(); +#endif } /* diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index d77214795d..56aca7d5bc 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -3626,6 +3626,17 @@ struct config_int ConfigureNamesInt[] = NULL, NULL, NULL }, + { + {"max_total_backend_memory", PGC_SU_BACKEND, RESOURCES_MEM, + gettext_noop("Restrict total backend memory allocations to this max."), + gettext_noop("0 turns this feature off."), + GUC_UNIT_MB + }, + &max_total_bkend_mem, + 0, 0, INT_MAX, + NULL, NULL, NULL + }, + /* End-of-list marker */ { {NULL, 0, 0, NULL, NULL}, NULL, 0, 0, 0, NULL, NULL, NULL diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2244ee52f7..50e2bb2bcf 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -169,6 +169,9 @@ #vacuum_buffer_usage_limit = 256kB # size of vacuum and analyze buffer access strategy ring; # 0 to disable vacuum buffer access strategy; # range 128kB to 16GB +#max_total_backend_memory = 0MB # Restrict total backend memory allocations + # to this max (in MB). 0 turns this feature + # off. # - Disk - diff --git a/src/backend/utils/mmgr/aset.c b/src/backend/utils/mmgr/aset.c index a599a3a6e4..be56585853 100644 --- a/src/backend/utils/mmgr/aset.c +++ b/src/backend/utils/mmgr/aset.c @@ -438,6 +438,18 @@ AllocSetContextCreateInternal(MemoryContext parent, else firstBlockSize = Max(firstBlockSize, initBlockSize); + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(firstBlockSize)) + { + if (TopMemoryContext) + MemoryContextStats(TopMemoryContext); + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory - exceeds max_total_backend_memory"), + errdetail("Failed while creating memory context \"%s\".", + name))); + } + /* * Allocate the initial block. Unlike other aset.c blocks, it starts with * the context header and its block header follows that. @@ -724,6 +736,11 @@ AllocSetAllocLarge(MemoryContext context, Size size, int flags) #endif blksize = chunk_size + ALLOC_BLOCKHDRSZ + ALLOC_CHUNKHDRSZ; + + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (AllocBlock) malloc(blksize); if (block == NULL) return MemoryContextAllocationFailure(context, size, flags); @@ -917,6 +934,10 @@ AllocSetAllocFromNewBlock(MemoryContext context, Size size, int flags, while (blksize < required_size) blksize <<= 1; + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + /* Try to allocate it */ block = (AllocBlock) malloc(blksize); @@ -1238,6 +1259,18 @@ AllocSetRealloc(void *pointer, Size size, int flags) blksize = chksize + ALLOC_BLOCKHDRSZ + ALLOC_CHUNKHDRSZ; oldblksize = block->endptr - ((char *) block); + /* + * Do not exceed maximum allowed memory allocation. NOTE: checking for + * the full size here rather than just the amount of increased + * allocation to prevent a potential underflow of *my_allocation + * allowance in cases where blksize - oldblksize does not trigger a + * refill but blksize is greater than *my_allocation_allowance. + * Underflow would occur with the call below to + * pgstat_report_allocated_bytes_increase() + */ + if (blksize > oldblksize && exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (AllocBlock) realloc(block, blksize); if (block == NULL) { diff --git a/src/backend/utils/mmgr/generation.c b/src/backend/utils/mmgr/generation.c index d511b67b08..ea4dc2cb27 100644 --- a/src/backend/utils/mmgr/generation.c +++ b/src/backend/utils/mmgr/generation.c @@ -203,6 +203,16 @@ GenerationContextCreate(MemoryContext parent, else allocSize = Max(allocSize, initBlockSize); + if (exceeds_max_total_bkend_mem(allocSize)) + { + MemoryContextStats(TopMemoryContext); + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory - exceeds max_total_backend_memory"), + errdetail("Failed while creating memory context \"%s\".", + name))); + } + /* * Allocate the initial block. Unlike other generation.c blocks, it * starts with the context header and its block header follows that. @@ -372,6 +382,9 @@ GenerationAllocLarge(MemoryContext context, Size size, int flags) required_size = chunk_size + Generation_CHUNKHDRSZ; blksize = required_size + Generation_BLOCKHDRSZ; + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (GenerationBlock *) malloc(blksize); if (block == NULL) return MemoryContextAllocationFailure(context, size, flags); @@ -494,6 +507,9 @@ GenerationAllocFromNewBlock(MemoryContext context, Size size, int flags, if (blksize < required_size) blksize = pg_nextpower2_size_t(required_size); + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (GenerationBlock *) malloc(blksize); if (block == NULL) diff --git a/src/backend/utils/mmgr/slab.c b/src/backend/utils/mmgr/slab.c index 98a8bbaf91..d0f80f10a2 100644 --- a/src/backend/utils/mmgr/slab.c +++ b/src/backend/utils/mmgr/slab.c @@ -360,7 +360,16 @@ SlabContextCreate(MemoryContext parent, elog(ERROR, "block size %zu for slab is too small for %zu-byte chunks", blockSize, chunkSize); - + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(Slab_CONTEXT_HDRSZ(chunksPerBlock))) + { + MemoryContextStats(TopMemoryContext); + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory - exceeds max_total_backend_memory"), + errdetail("Failed while creating memory context \"%s\".", + name))); + } slab = (SlabContext *) malloc(Slab_CONTEXT_HDRSZ(chunksPerBlock)); if (slab == NULL) @@ -582,6 +591,10 @@ SlabAllocFromNewBlock(MemoryContext context, Size size, int flags) } else { + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(slab->blockSize)) + return MemoryContextAllocationFailure(context, size, flags); + block = (SlabBlock *) malloc(slab->blockSize); if (unlikely(block == NULL)) diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 47903e755e..13f1c15b6d 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -5448,9 +5448,9 @@ descr => 'statistics: global memory allocation information', proname => 'pg_stat_get_global_memory_allocation', proisstrict => 'f', provolatile => 's', proparallel => 'r', prorettype => 'record', - proargtypes => '', proallargtypes => '{oid,int8}', - proargmodes => '{o,o}', - proargnames => '{datid,global_dsm_allocated_bytes}', + proargtypes => '', proallargtypes => '{oid,int8,int8}', + proargmodes => '{o,o,o}', + proargnames => '{datid,total_bkend_mem_bytes_available,global_dsm_allocated_bytes}', prosrc =>'pg_stat_get_global_memory_allocation' }, { oid => '2022', descr => 'statistics: information about currently active backends', diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a350f455cd..fa7c94c6c9 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -424,6 +424,13 @@ typedef struct PROC_HDR int startupBufferPinWaitBufId; /* Global dsm allocations */ pg_atomic_uint64 global_dsm_allocation; + + /* + * Max backend memory allocation tracker. Used/Initialized when + * max_total_bkend_mem > 0 as max_total_bkend_mem (MB) converted to bytes. + * Decreases/increases with free/malloc of backend memory. + */ + pg_atomic_uint64 total_bkend_mem_bytes; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; diff --git a/src/include/utils/backend_status.h b/src/include/utils/backend_status.h index cbf801884d..a833941272 100644 --- a/src/include/utils/backend_status.h +++ b/src/include/utils/backend_status.h @@ -14,7 +14,7 @@ #include "datatype/timestamp.h" #include "libpq/pqcomm.h" #include "miscadmin.h" /* for BackendType */ -#include "storage/procnumber.h" +#include "storage/proc.h" #include "utils/backend_progress.h" @@ -303,6 +303,7 @@ typedef struct LocalPgBackendStatus */ extern PGDLLIMPORT bool pgstat_track_activities; extern PGDLLIMPORT int pgstat_track_activity_query_size; +extern PGDLLIMPORT int max_total_bkend_mem; /* ---------- @@ -315,6 +316,10 @@ extern PGDLLIMPORT uint64 *my_aset_allocated_bytes; extern PGDLLIMPORT uint64 *my_dsm_allocated_bytes; extern PGDLLIMPORT uint64 *my_generation_allocated_bytes; extern PGDLLIMPORT uint64 *my_slab_allocated_bytes; +extern PGDLLIMPORT uint64 allocation_allowance; +extern PGDLLIMPORT uint64 initial_allocation_allowance; +extern PGDLLIMPORT uint64 allocation_return; +extern PGDLLIMPORT uint64 allocation_return_threshold; /* ---------- @@ -363,6 +368,7 @@ extern PgBackendStatus *pgstat_get_beentry_by_proc_number(ProcNumber procNumber) extern LocalPgBackendStatus *pgstat_get_local_beentry_by_proc_number(ProcNumber procNumber); extern LocalPgBackendStatus *pgstat_get_local_beentry_by_index(int idx); extern char *pgstat_clip_activity(const char *raw_activity); +extern bool exceeds_max_total_bkend_mem(uint64 allocation_request); /* ---------- * pgstat_report_allocated_bytes_decrease() - @@ -378,7 +384,7 @@ pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, { uint64 temp; - /* Avoid allocated_bytes unsigned integer overflow on decrease */ + /* Sanity check: my allocated bytes should never drop below zero */ if (pg_sub_u64_overflow(*my_allocated_bytes, proc_allocated_bytes, &temp)) { /* On overflow, set allocated bytes and allocator type bytes to zero */ @@ -387,13 +393,35 @@ pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, *my_dsm_allocated_bytes = 0; *my_generation_allocated_bytes = 0; *my_slab_allocated_bytes = 0; + + /* Add freed memory to allocation return counter. */ + allocation_return += proc_allocated_bytes; + + /* + * Return freed memory to the global counter if return threshold is + * met. + */ + if (max_total_bkend_mem && allocation_return >= allocation_return_threshold) + { + if (ProcGlobal) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + /* Add to global tracker */ + pg_atomic_add_fetch_u64(&procglobal->total_bkend_mem_bytes, + allocation_return); + + /* Restart the count */ + allocation_return = 0; + } + } } else { - /* decrease allocation */ - *my_allocated_bytes -= proc_allocated_bytes; + /* Add freed memory to allocation return counter */ + allocation_return += proc_allocated_bytes; - /* Decrease allocator type allocated bytes. */ + /* Decrease allocator type allocated bytes */ switch (pg_allocator_type) { case PG_ALLOC_ASET: @@ -415,6 +443,30 @@ pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, *my_slab_allocated_bytes -= proc_allocated_bytes; break; } + + /* decrease allocation */ + *my_allocated_bytes = *my_aset_allocated_bytes + + *my_dsm_allocated_bytes + *my_generation_allocated_bytes + + *my_slab_allocated_bytes; + + /* + * Return freed memory to the global counter if return threshold is + * met. + */ + if (max_total_bkend_mem && allocation_return >= allocation_return_threshold) + { + if (ProcGlobal) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + /* Add to global tracker */ + pg_atomic_add_fetch_u64(&procglobal->total_bkend_mem_bytes, + allocation_return); + + /* Restart the count */ + allocation_return = 0; + } + } } return; @@ -432,7 +484,13 @@ static inline void pgstat_report_allocated_bytes_increase(int64 proc_allocated_bytes, int pg_allocator_type) { - *my_allocated_bytes += proc_allocated_bytes; + uint64 temp; + + /* Sanity check: my allocated bytes should never drop below zero */ + if (pg_sub_u64_overflow(allocation_allowance, proc_allocated_bytes, &temp)) + allocation_allowance = 0; + else + allocation_allowance -= proc_allocated_bytes; /* Increase allocator type allocated bytes */ switch (pg_allocator_type) @@ -457,6 +515,9 @@ pgstat_report_allocated_bytes_increase(int64 proc_allocated_bytes, break; } + *my_allocated_bytes = *my_aset_allocated_bytes + *my_dsm_allocated_bytes + + *my_generation_allocated_bytes + *my_slab_allocated_bytes; + return; } @@ -476,6 +537,36 @@ pgstat_init_allocated_bytes(void) *my_generation_allocated_bytes = 0; *my_slab_allocated_bytes = 0; + /* If we're limiting backend memory */ + if (max_total_bkend_mem) + { + volatile PROC_HDR *procglobal = ProcGlobal; + uint64 available_max_total_bkend_mem = 0; + + allocation_return = 0; + allocation_allowance = 0; + + /* Account for the initial allocation allowance */ + while ((available_max_total_bkend_mem = pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)) >= initial_allocation_allowance) + { + /* + * On success populate allocation_allowance. Failure here will + * result in the backend's first invocation of + * exceeds_max_total_bkend_mem allocating requested, default, or + * available memory or result in an out of memory error. + */ + if (pg_atomic_compare_exchange_u64(&procglobal->total_bkend_mem_bytes, + &available_max_total_bkend_mem, + available_max_total_bkend_mem - + initial_allocation_allowance)) + { + allocation_allowance = initial_allocation_allowance; + + break; + } + } + } + return; } diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 2f62f5e4ea..01dee8ddea 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1887,13 +1887,15 @@ pg_stat_global_memory_allocation| WITH sums AS ( SELECT s.datid, current_setting('shared_memory_size'::text, true) AS shared_memory_size, (current_setting('shared_memory_size_in_huge_pages'::text, true))::integer AS shared_memory_size_in_huge_pages, + pg_size_bytes(current_setting('max_total_backend_memory'::text, true)) AS max_total_backend_memory_bytes, + s.total_bkend_mem_bytes_available, s.global_dsm_allocated_bytes, sums.total_aset_allocated_bytes, sums.total_dsm_allocated_bytes, sums.total_generation_allocated_bytes, sums.total_slab_allocated_bytes FROM sums, - (pg_stat_get_global_memory_allocation() s(datid, global_dsm_allocated_bytes) + (pg_stat_get_global_memory_allocation() s(datid, total_bkend_mem_bytes_available, global_dsm_allocated_bytes) LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_gssapi| SELECT pid, gss_auth AS gss_authenticated, -- 2.43.2 ^ permalink raw reply [nested|flat] 281+ messages in thread
* Re: Add the ability to limit the amount of memory that can be allocated to backends. @ 2024-03-14 20:36 Anton A. Melnikov <[email protected]> parent: Anton A. Melnikov <[email protected]> 0 siblings, 1 reply; 281+ messages in thread From: Anton A. Melnikov @ 2024-03-14 20:36 UTC (permalink / raw) To: Aleksander Alekseev <[email protected]>; [email protected] <[email protected]>; +Cc: Tomas Vondra <[email protected]>; Andres Freund <[email protected]>; Andrei Lepikhov <[email protected]>; Stephen Frost <[email protected]>; [email protected]; Arne Roland <[email protected]>; vignesh C <[email protected]>; Justin Pryzby <[email protected]>; Ibrar Ahmed <[email protected]>; stephen.frost <[email protected]> On 13.03.2024 10:41, Anton A. Melnikov wrote: > Here is a version updated for the current master. > During patch updating i mistakenly added double counting of deallocatated blocks. That's why the tests in the patch tester failed. Fixed it and squashed fix 0002 with 0001. Here is fixed version. With the best wishes! -- Anton A. Melnikov Postgres Professional: http://www.postgrespro.com The Russian Postgres Company Attachments: [text/x-patch] v20240314-0001-Add-tracking-of-backend-memory-allocated.patch (49.6K, ../../[email protected]/2-v20240314-0001-Add-tracking-of-backend-memory-allocated.patch) download | inline diff: From 7a0925a38acfb9a945087318a5d91fae4680db0e Mon Sep 17 00:00:00 2001 From: Tomas Vondra <[email protected]> Date: Tue, 26 Dec 2023 17:54:40 +0100 Subject: [PATCH 1/2] Add tracking of backend memory allocated Add tracking of backend memory allocated in total and by allocation type (aset, dsm, generation, slab) by process. allocated_bytes tracks the current bytes of memory allocated to the backend process. aset_allocated_bytes, dsm_allocated_bytes, generation_allocated_bytes and slab_allocated_bytes track the allocation by type for the backend process. They are updated for the process as memory is malloc'd/freed. Memory allocated to items on the freelist is included. Dynamic shared memory allocations are included only in the value displayed for the backend that created them, they are not included in the value for backends that are attached to them to avoid double counting. DSM allocations that are not destroyed by the creating process prior to it's exit are considered long lived and are tracked in a global counter global_dsm_allocated_bytes. We limit the floor of allocation counters to zero. Created views pg_stat_global_memory_allocation and pg_stat_memory_allocation for access to these trackers. --- doc/src/sgml/monitoring.sgml | 246 ++++++++++++++++++++ src/backend/catalog/system_views.sql | 34 +++ src/backend/storage/ipc/dsm.c | 11 +- src/backend/storage/ipc/dsm_impl.c | 78 +++++++ src/backend/storage/lmgr/proc.c | 1 + src/backend/utils/activity/backend_status.c | 114 +++++++++ src/backend/utils/adt/pgstatfuncs.c | 84 +++++++ src/backend/utils/init/miscinit.c | 3 + src/backend/utils/mmgr/aset.c | 17 ++ src/backend/utils/mmgr/generation.c | 13 ++ src/backend/utils/mmgr/slab.c | 22 ++ src/include/catalog/pg_proc.dat | 17 ++ src/include/storage/proc.h | 2 + src/include/utils/backend_status.h | 144 +++++++++++- src/test/regress/expected/rules.out | 27 +++ src/test/regress/expected/stats.out | 36 +++ src/test/regress/sql/stats.sql | 20 ++ 17 files changed, 867 insertions(+), 2 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 8736eac284..41d788be45 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -4599,6 +4599,252 @@ description | Waiting for a newly initialized WAL file to reach durable storage </sect2> + <sect2 id="monitoring-pg-stat-memory-allocation-view"> + <title><structname>pg_stat_memory_allocation</structname></title> + + <indexterm> + <primary>pg_stat_memory_allocation</primary> + </indexterm> + + <para> + The <structname>pg_stat_memory_allocation</structname> view will have one + row per server process, showing information related to the current memory + allocation of that process in total and by allocator type. Due to the + dynamic nature of memory allocations the allocated bytes values may not be + exact but should be sufficient for the intended purposes. Dynamic shared + memory allocations are included only in the value displayed for the backend + that created them, they are not included in the value for backends that are + attached to them to avoid double counting. Use + <function>pg_size_pretty</function> described in + <xref linkend="functions-admin-dbsize"/> to make these values more easily + readable. + </para> + + <table id="pg-stat-memory-allocation-view" xreflabel="pg_stat_memory_allocation"> + <title><structname>pg_stat_memory_allocation</structname> View</title> + <tgroup cols="1"> + <thead> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + + <tbody> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>datid</structfield> <type>oid</type> + </para> + <para> + OID of the database this backend is connected to + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>pid</structfield> <type>integer</type> + </para> + <para> + Process ID of this backend + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes. This is the balance + of bytes allocated and freed by this backend. Dynamic shared memory + allocations are included only in the value displayed for the backend that + created them, they are not included in the value for backends that are + attached to them to avoid double counting. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>aset_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the allocation + set allocator. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>dsm_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the dynamic + shared memory allocator. Upon process exit, dsm allocations that have + not been freed are considered long lived and added to + <structfield>global_dsm_allocated_bytes</structfield> found in the + <link linkend="monitoring-pg-stat-global-memory-allocation-view"> + <structname>pg_stat_global_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>generation_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the generation + allocator. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>slab_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Memory currently allocated to this backend in bytes via the slab + allocator. + </para></entry> + </row> + + </tbody> + </tgroup> + </table> + + </sect2> + + <sect2 id="monitoring-pg-stat-global-memory-allocation-view"> + <title><structname>pg_stat_global_memory_allocation</structname></title> + + <indexterm> + <primary>pg_stat_global-memory_allocation</primary> + </indexterm> + + <para> + The <structname>pg_stat_global_memory_allocation</structname> view will + have one row showing information related to current shared memory + allocations. Due to the dynamic nature of memory allocations the allocated + bytes values may not be exact but should be sufficient for the intended + purposes. Use <function>pg_size_pretty</function> described in + <xref linkend="functions-admin-dbsize"/> to make the byte populated values + more easily readable. + </para> + + <table id="pg-stat-global-memory-allocation-view" xreflabel="pg_stat_global_memory_allocation"> + <title><structname>pg_stat_global_memory_allocation</structname> View</title> + <tgroup cols="1"> + <thead> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + + <tbody> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>datid</structfield> <type>oid</type> + </para> + <para> + OID of the database this backend is connected to + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>shared_memory_size_mb</structfield> <type>integer</type> + </para> + <para> + Reports the size of the main shared memory area, rounded up to the + nearest megabyte. See <xref linkend="guc-shared-memory-size"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>shared_memory_size_in_huge_pages</structfield> <type>bigint</type> + </para> + <para> + Reports the number of huge pages that are needed for the main shared + memory area based on the specified huge_page_size. If huge pages are not + supported, this will be -1. See + <xref linkend="guc-shared-memory-size-in-huge-pages"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>global_dsm_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Long lived dynamically allocated memory currently allocated to the + database. Upon process exit, dsm allocations that have not been freed + are considered long lived and added to + <structfield>global_dsm_allocated_bytes</structfield>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_aset_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>aset_allocated_bytes</structfield> for all + backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_dsm_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>dsm_allocated_bytes</structfield> for all + backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_generation_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>generation_allocated_bytes</structfield> for + all backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_slab_allocated_bytes</structfield> <type>bigint</type> + </para> + <para> + Sum total of <structfield>slab_allocated_bytes</structfield> for all + backend processes from + <link linkend="monitoring-pg-stat-memory-allocation-view"> + <structname>pg_stat_memory_allocation</structname></link> view. + </para></entry> + </row> + + </tbody> + </tgroup> + </table> + + </sect2> + <sect2 id="monitoring-stats-functions"> <title>Statistics Functions</title> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 04227a72d1..61ff4a59b6 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1375,3 +1375,37 @@ CREATE VIEW pg_stat_subscription_stats AS CREATE VIEW pg_wait_events AS SELECT * FROM pg_get_wait_events(); + +CREATE VIEW pg_stat_memory_allocation AS + SELECT + S.datid AS datid, + S.pid, + S.allocated_bytes, + S.aset_allocated_bytes, + S.dsm_allocated_bytes, + S.generation_allocated_bytes, + S.slab_allocated_bytes + FROM pg_stat_get_memory_allocation(NULL) AS S + LEFT JOIN pg_database AS D ON (S.datid = D.oid); + +CREATE VIEW pg_stat_global_memory_allocation AS +WITH sums AS ( + SELECT + SUM(aset_allocated_bytes) AS total_aset_allocated_bytes, + SUM(dsm_allocated_bytes) AS total_dsm_allocated_bytes, + SUM(generation_allocated_bytes) AS total_generation_allocated_bytes, + SUM(slab_allocated_bytes) AS total_slab_allocated_bytes + FROM + pg_stat_memory_allocation +) +SELECT + S.datid AS datid, + current_setting('shared_memory_size', true) as shared_memory_size, + (current_setting('shared_memory_size_in_huge_pages', true))::integer as shared_memory_size_in_huge_pages, + S.global_dsm_allocated_bytes, + sums.total_aset_allocated_bytes, + sums.total_dsm_allocated_bytes, + sums.total_generation_allocated_bytes, + sums.total_slab_allocated_bytes + FROM sums, pg_stat_get_global_memory_allocation() AS S + LEFT JOIN pg_database AS D ON (S.datid = D.oid); diff --git a/src/backend/storage/ipc/dsm.c b/src/backend/storage/ipc/dsm.c index c2e33a7e43..b950640643 100644 --- a/src/backend/storage/ipc/dsm.c +++ b/src/backend/storage/ipc/dsm.c @@ -802,6 +802,15 @@ dsm_detach_all(void) void dsm_detach(dsm_segment *seg) { + /* + * Retain mapped_size to pass into destroy call in cases where the detach + * is the last reference. mapped_size is zeroed as part of the detach + * process, but is needed later in these cases for dsm_allocated_bytes + * accounting. + */ + Size local_seg_mapped_size = seg->mapped_size; + Size *ptr_local_seg_mapped_size = &local_seg_mapped_size; + /* * Invoke registered callbacks. Just in case one of those callbacks * throws a further error that brings us back here, pop the callback @@ -882,7 +891,7 @@ dsm_detach(dsm_segment *seg) */ if (is_main_region_dsm_handle(seg->handle) || dsm_impl_op(DSM_OP_DESTROY, seg->handle, 0, &seg->impl_private, - &seg->mapped_address, &seg->mapped_size, WARNING)) + &seg->mapped_address, ptr_local_seg_mapped_size, WARNING)) { LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); if (is_main_region_dsm_handle(seg->handle)) diff --git a/src/backend/storage/ipc/dsm_impl.c b/src/backend/storage/ipc/dsm_impl.c index 8dd669e0ce..af67e55bdf 100644 --- a/src/backend/storage/ipc/dsm_impl.c +++ b/src/backend/storage/ipc/dsm_impl.c @@ -66,6 +66,7 @@ #include "postmaster/postmaster.h" #include "storage/dsm_impl.h" #include "storage/fd.h" +#include "utils/backend_status.h" #include "utils/guc.h" #include "utils/memutils.h" @@ -232,6 +233,14 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + if (op == DSM_OP_DESTROY) + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *mapped_address = NULL; *mapped_size = 0; if (op == DSM_OP_DESTROY && shm_unlink(name) != 0) @@ -332,6 +341,33 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + { + /* + * Posix creation calls dsm_impl_posix_resize implying that resizing + * occurs or may be added in the future. As implemented + * dsm_impl_posix_resize utilizes fallocate or truncate, passing the + * whole new size as input, growing the allocation as needed (only + * truncate supports shrinking). We update by replacing the old + * allocation with the new. + */ +#if defined(HAVE_POSIX_FALLOCATE) && defined(__linux__) + /* + * posix_fallocate does not shrink allocations, adjust only on + * allocation increase. + */ + if (request_size > *mapped_size) + pgstat_report_allocated_bytes_increase(request_size - *mapped_size, PG_ALLOC_DSM); +#else + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); + pgstat_report_allocated_bytes_increase(request_size, PG_ALLOC_DSM); +#endif + } *mapped_address = address; *mapped_size = request_size; close(fd); @@ -538,6 +574,14 @@ dsm_impl_sysv(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + if (op == DSM_OP_DESTROY) + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *mapped_address = NULL; *mapped_size = 0; if (op == DSM_OP_DESTROY && shmctl(ident, IPC_RMID, NULL) < 0) @@ -585,6 +629,13 @@ dsm_impl_sysv(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + pgstat_report_allocated_bytes_increase(request_size, PG_ALLOC_DSM); *mapped_address = address; *mapped_size = request_size; @@ -653,6 +704,13 @@ dsm_impl_windows(dsm_op op, dsm_handle handle, Size request_size, return false; } + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + if (op == DSM_OP_DESTROY) + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *impl_private = NULL; *mapped_address = NULL; *mapped_size = 0; @@ -769,6 +827,12 @@ dsm_impl_windows(dsm_op op, dsm_handle handle, Size request_size, return false; } + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + pgstat_report_allocated_bytes_increase(info.RegionSize, PG_ALLOC_DSM); *mapped_address = address; *mapped_size = info.RegionSize; *impl_private = hmap; @@ -813,6 +877,13 @@ dsm_impl_mmap(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Detach and destroy pass through here, only decrease the memory + * shown allocated in pg_stat_activity when the creator destroys the + * allocation. + */ + pgstat_report_allocated_bytes_decrease(*mapped_size, PG_ALLOC_DSM); *mapped_address = NULL; *mapped_size = 0; if (op == DSM_OP_DESTROY && unlink(name) != 0) @@ -934,6 +1005,13 @@ dsm_impl_mmap(dsm_op op, dsm_handle handle, Size request_size, name))); return false; } + + /* + * Attach and create pass through here, only update backend memory + * allocated in pg_stat_activity for the creator process. + */ + if (op == DSM_OP_CREATE) + pgstat_report_allocated_bytes_increase(request_size, PG_ALLOC_DSM); *mapped_address = address; *mapped_size = request_size; diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index f3e20038f4..1959b5f4e6 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -180,6 +180,7 @@ InitProcGlobal(void) ProcGlobal->checkpointerLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PROC_NUMBER); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PROC_NUMBER); + pg_atomic_init_u64(&ProcGlobal->global_dsm_allocation, 0); /* * Create and initialize all the PGPROC structures we'll need. There are diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c index 1ccf4c6d83..25b545441b 100644 --- a/src/backend/utils/activity/backend_status.c +++ b/src/backend/utils/activity/backend_status.c @@ -48,6 +48,24 @@ int pgstat_track_activity_query_size = 1024; /* exposed so that backend_progress.c can access it */ PgBackendStatus *MyBEEntry = NULL; +/* + * Memory allocated to this backend prior to pgstats initialization. Migrated to + * shared memory on pgstats initialization. + */ +uint64 local_my_allocated_bytes = 0; +uint64 *my_allocated_bytes = &local_my_allocated_bytes; + +/* Memory allocated to this backend by type prior to pgstats initialization. + * Migrated to shared memory on pgstats initialization + */ +uint64 local_my_aset_allocated_bytes = 0; +uint64 *my_aset_allocated_bytes = &local_my_aset_allocated_bytes; +uint64 local_my_dsm_allocated_bytes = 0; +uint64 *my_dsm_allocated_bytes = &local_my_dsm_allocated_bytes; +uint64 local_my_generation_allocated_bytes = 0; +uint64 *my_generation_allocated_bytes = &local_my_generation_allocated_bytes; +uint64 local_my_slab_allocated_bytes = 0; +uint64 *my_slab_allocated_bytes = &local_my_slab_allocated_bytes; static PgBackendStatus *BackendStatusArray = NULL; static char *BackendAppnameBuffer = NULL; @@ -382,6 +400,32 @@ pgstat_bestart(void) lbeentry.st_progress_command_target = InvalidOid; lbeentry.st_query_id = UINT64CONST(0); + /* Alter allocation reporting from local storage to shared memory */ + pgstat_set_allocated_bytes_storage(&MyBEEntry->allocated_bytes, + &MyBEEntry->aset_allocated_bytes, + &MyBEEntry->dsm_allocated_bytes, + &MyBEEntry->generation_allocated_bytes, + &MyBEEntry->slab_allocated_bytes); + + /* + * Populate sum of memory allocated prior to pgstats initialization to + * pgstats and zero the local variable. This is a += assignment because + * InitPostgres allocates memory after pgstat_beinit but prior to + * pgstat_bestart so we have allocations to both local and shared memory + * to combine. + */ + lbeentry.allocated_bytes += local_my_allocated_bytes; + local_my_allocated_bytes = 0; + lbeentry.aset_allocated_bytes += local_my_aset_allocated_bytes; + local_my_aset_allocated_bytes = 0; + + lbeentry.dsm_allocated_bytes += local_my_dsm_allocated_bytes; + local_my_dsm_allocated_bytes = 0; + lbeentry.generation_allocated_bytes += local_my_generation_allocated_bytes; + local_my_generation_allocated_bytes = 0; + lbeentry.slab_allocated_bytes += local_my_slab_allocated_bytes; + local_my_slab_allocated_bytes = 0; + /* * we don't zero st_progress_param here to save cycles; nobody should * examine it until st_progress_command has been set to something other @@ -441,6 +485,9 @@ pgstat_beshutdown_hook(int code, Datum arg) { volatile PgBackendStatus *beentry = MyBEEntry; + /* Stop reporting memory allocation changes to shared memory */ + pgstat_reset_allocated_bytes_storage(); + /* * Clear my status entry, following the protocol of bumping st_changecount * before and after. We use a volatile pointer here to ensure the @@ -1195,3 +1242,70 @@ pgstat_clip_activity(const char *raw_activity) return activity; } + +/* + * Configure bytes allocated reporting to report allocated bytes to + * shared memory. + * + * Expected to be called during backend startup (in pgstat_bestart), to point + * allocated bytes accounting into shared memory. + */ +void +pgstat_set_allocated_bytes_storage(uint64 *allocated_bytes, + uint64 *aset_allocated_bytes, + uint64 *dsm_allocated_bytes, + uint64 *generation_allocated_bytes, + uint64 *slab_allocated_bytes) +{ + /* Map allocations to shared memory */ + my_allocated_bytes = allocated_bytes; + *allocated_bytes = local_my_allocated_bytes; + + my_aset_allocated_bytes = aset_allocated_bytes; + *aset_allocated_bytes = local_my_aset_allocated_bytes; + + my_dsm_allocated_bytes = dsm_allocated_bytes; + *dsm_allocated_bytes = local_my_dsm_allocated_bytes; + + my_generation_allocated_bytes = generation_allocated_bytes; + *generation_allocated_bytes = local_my_generation_allocated_bytes; + + my_slab_allocated_bytes = slab_allocated_bytes; + *slab_allocated_bytes = local_my_slab_allocated_bytes; +} + +/* + * Reset allocated bytes storage location. + * + * Expected to be called during backend shutdown, before the locations set up + * by pgstat_set_allocated_bytes_storage become invalid. + */ +void +pgstat_reset_allocated_bytes_storage(void) +{ + if (ProcGlobal) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + /* + * Add dsm allocations that have not been freed to global dsm + * accounting + */ + pg_atomic_add_fetch_u64(&procglobal->global_dsm_allocation, + *my_dsm_allocated_bytes); + } + + /* Reset memory allocation variables */ + *my_allocated_bytes = local_my_allocated_bytes = 0; + *my_aset_allocated_bytes = local_my_aset_allocated_bytes = 0; + *my_dsm_allocated_bytes = local_my_dsm_allocated_bytes = 0; + *my_generation_allocated_bytes = local_my_generation_allocated_bytes = 0; + *my_slab_allocated_bytes = local_my_slab_allocated_bytes = 0; + + /* Point my_{*_}allocated_bytes from shared memory back to local */ + my_allocated_bytes = &local_my_allocated_bytes; + my_aset_allocated_bytes = &local_my_aset_allocated_bytes; + my_dsm_allocated_bytes = &local_my_dsm_allocated_bytes; + my_generation_allocated_bytes = &local_my_generation_allocated_bytes; + my_slab_allocated_bytes = &local_my_slab_allocated_bytes; +} diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 3876339ee1..9c82ec48cb 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2032,3 +2032,87 @@ pg_stat_have_stats(PG_FUNCTION_ARGS) PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objoid)); } + +/* + * Get the memory allocation of PG backends. + */ +Datum +pg_stat_get_memory_allocation(PG_FUNCTION_ARGS) +{ +#define PG_STAT_GET_MEMORY_ALLOCATION_COLS 7 + int num_backends = pgstat_fetch_stat_numbackends(); + int curr_backend; + int pid = PG_ARGISNULL(0) ? -1 : PG_GETARG_INT32(0); + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + + InitMaterializedSRF(fcinfo, 0); + + /* 1-based index */ + for (curr_backend = 1; curr_backend <= num_backends; curr_backend++) + { + /* for each row */ + Datum values[PG_STAT_GET_MEMORY_ALLOCATION_COLS] = {0}; + bool nulls[PG_STAT_GET_MEMORY_ALLOCATION_COLS] = {0}; + LocalPgBackendStatus *local_beentry; + PgBackendStatus *beentry; + + /* Get the next one in the list */ + local_beentry = pgstat_get_local_beentry_by_index(curr_backend); + beentry = &local_beentry->backendStatus; + + /* If looking for specific PID, ignore all the others */ + if (pid != -1 && beentry->st_procpid != pid) + continue; + + /* Values available to all callers */ + if (beentry->st_databaseid != InvalidOid) + values[0] = ObjectIdGetDatum(beentry->st_databaseid); + else + nulls[0] = true; + + values[1] = Int32GetDatum(beentry->st_procpid); + values[2] = UInt64GetDatum(beentry->allocated_bytes); + values[3] = UInt64GetDatum(beentry->aset_allocated_bytes); + values[4] = UInt64GetDatum(beentry->dsm_allocated_bytes); + values[5] = UInt64GetDatum(beentry->generation_allocated_bytes); + values[6] = UInt64GetDatum(beentry->slab_allocated_bytes); + + tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); + + /* If only a single backend was requested, and we found it, break. */ + if (pid != -1) + break; + } + + return (Datum) 0; +} + +/* + * Get the global memory allocation statistics. + */ +Datum +pg_stat_get_global_memory_allocation(PG_FUNCTION_ARGS) +{ +#define PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS 2 + TupleDesc tupdesc; + Datum values[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; + bool nulls[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; + volatile PROC_HDR *procglobal = ProcGlobal; + + /* Initialise attributes information in the tuple descriptor */ + tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "datid", + OIDOID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 2, "global_dsm_allocated_bytes", + INT8OID, -1, 0); + BlessTupleDesc(tupdesc); + + /* datid */ + values[0] = ObjectIdGetDatum(MyDatabaseId); + + /* get global_dsm_allocated_bytes */ + values[1] = Int64GetDatum(pg_atomic_read_u64(&procglobal->global_dsm_allocation)); + + /* Returns the record as Datum */ + PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls))); +} diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c index 537d92c0cf..9b47450813 100644 --- a/src/backend/utils/init/miscinit.c +++ b/src/backend/utils/init/miscinit.c @@ -170,6 +170,9 @@ InitPostmasterChild(void) (errcode_for_socket_access(), errmsg_internal("could not set postmaster death monitoring pipe to FD_CLOEXEC mode: %m"))); #endif + + /* Init allocated bytes to avoid double counting parent allocation */ + pgstat_init_allocated_bytes(); } /* diff --git a/src/backend/utils/mmgr/aset.c b/src/backend/utils/mmgr/aset.c index 751cc3408c..cd074add17 100644 --- a/src/backend/utils/mmgr/aset.c +++ b/src/backend/utils/mmgr/aset.c @@ -47,6 +47,7 @@ #include "postgres.h" #include "port/pg_bitutils.h" +#include "utils/backend_status.h" #include "utils/memdebug.h" #include "utils/memutils.h" #include "utils/memutils_internal.h" @@ -517,6 +518,7 @@ AllocSetContextCreateInternal(MemoryContext parent, name); ((MemoryContext) set)->mem_allocated = firstBlockSize; + pgstat_report_allocated_bytes_increase(firstBlockSize, PG_ALLOC_ASET); return (MemoryContext) set; } @@ -539,6 +541,7 @@ AllocSetReset(MemoryContext context) AllocSet set = (AllocSet) context; AllocBlock block; Size keepersize PG_USED_FOR_ASSERTS_ONLY; + uint64 deallocation = 0; Assert(AllocSetIsValid(set)); @@ -581,6 +584,7 @@ AllocSetReset(MemoryContext context) { /* Normal case, release the block */ context->mem_allocated -= block->endptr - ((char *) block); + deallocation += block->endptr - ((char *) block); #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->freeptr - ((char *) block)); @@ -591,6 +595,7 @@ AllocSetReset(MemoryContext context) } Assert(context->mem_allocated == keepersize); + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_ASET); /* Reset block size allocation sequence, too */ set->nextBlockSize = set->initBlockSize; @@ -609,6 +614,7 @@ AllocSetDelete(MemoryContext context) AllocSet set = (AllocSet) context; AllocBlock block = set->blocks; Size keepersize PG_USED_FOR_ASSERTS_ONLY; + uint64 deallocation = 0; Assert(AllocSetIsValid(set)); @@ -647,11 +653,13 @@ AllocSetDelete(MemoryContext context) freelist->first_free = (AllocSetContext *) oldset->header.nextchild; freelist->num_free--; + deallocation += oldset->header.mem_allocated; /* All that remains is to free the header/initial block */ free(oldset); } Assert(freelist->num_free == 0); + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_ASET); } /* Now add the just-deleted context to the freelist. */ @@ -668,7 +676,10 @@ AllocSetDelete(MemoryContext context) AllocBlock next = block->next; if (!IsKeeperBlock(set, block)) + { context->mem_allocated -= block->endptr - ((char *) block); + deallocation += block->endptr - ((char *) block); + } #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->freeptr - ((char *) block)); @@ -681,6 +692,7 @@ AllocSetDelete(MemoryContext context) } Assert(context->mem_allocated == keepersize); + pgstat_report_allocated_bytes_decrease(deallocation + context->mem_allocated, PG_ALLOC_ASET); /* Finally, free the context header, including the keeper block */ free(set); @@ -717,6 +729,7 @@ AllocSetAllocLarge(MemoryContext context, Size size, int flags) return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); block->aset = set; block->freeptr = block->endptr = ((char *) block) + blksize; @@ -923,6 +936,7 @@ AllocSetAllocFromNewBlock(MemoryContext context, Size size, int flags, return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); block->aset = set; block->freeptr = ((char *) block) + ALLOC_BLOCKHDRSZ; @@ -1100,6 +1114,7 @@ AllocSetFree(void *pointer) block->next->prev = block->prev; set->header.mem_allocated -= block->endptr - ((char *) block); + pgstat_report_allocated_bytes_decrease(block->endptr - ((char *) block), PG_ALLOC_ASET); #ifdef CLOBBER_FREED_MEMORY wipe_mem(block, block->freeptr - ((char *) block)); @@ -1233,7 +1248,9 @@ AllocSetRealloc(void *pointer, Size size, int flags) /* updated separately, not to underflow when (oldblksize > blksize) */ set->header.mem_allocated -= oldblksize; + pgstat_report_allocated_bytes_decrease(oldblksize, PG_ALLOC_ASET); set->header.mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_ASET); block->freeptr = block->endptr = ((char *) block) + blksize; diff --git a/src/backend/utils/mmgr/generation.c b/src/backend/utils/mmgr/generation.c index 5d81af1f94..dbea4f248e 100644 --- a/src/backend/utils/mmgr/generation.c +++ b/src/backend/utils/mmgr/generation.c @@ -37,6 +37,7 @@ #include "lib/ilist.h" #include "port/pg_bitutils.h" +#include "utils/backend_status.h" #include "utils/memdebug.h" #include "utils/memutils.h" #include "utils/memutils_internal.h" @@ -266,6 +267,7 @@ GenerationContextCreate(MemoryContext parent, name); ((MemoryContext) set)->mem_allocated = firstBlockSize; + pgstat_report_allocated_bytes_increase(firstBlockSize, PG_ALLOC_GENERATION); return (MemoryContext) set; } @@ -284,6 +286,7 @@ GenerationReset(MemoryContext context) { GenerationContext *set = (GenerationContext *) context; dlist_mutable_iter miter; + uint64 deallocation = 0; Assert(GenerationIsValid(set)); @@ -306,9 +309,14 @@ GenerationReset(MemoryContext context) if (IsKeeperBlock(set, block)) GenerationBlockMarkEmpty(block); else + { + deallocation += block->blksize; GenerationBlockFree(set, block); + } } + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_GENERATION); + /* set it so new allocations to make use of the keeper block */ set->block = KeeperBlock(set); @@ -329,6 +337,9 @@ GenerationDelete(MemoryContext context) { /* Reset to release all releasable GenerationBlocks */ GenerationReset(context); + + pgstat_report_allocated_bytes_decrease(context->mem_allocated, PG_ALLOC_GENERATION); + /* And free the context header and keeper block */ free(context); } @@ -366,6 +377,7 @@ GenerationAllocLarge(MemoryContext context, Size size, int flags) return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_GENERATION); /* block with a single (used) chunk */ block->context = set; @@ -488,6 +500,7 @@ GenerationAllocFromNewBlock(MemoryContext context, Size size, int flags, return MemoryContextAllocationFailure(context, size, flags); context->mem_allocated += blksize; + pgstat_report_allocated_bytes_increase(blksize, PG_ALLOC_GENERATION); /* initialize the new block */ GenerationBlockInit(set, block, blksize); diff --git a/src/backend/utils/mmgr/slab.c b/src/backend/utils/mmgr/slab.c index 3e15d59683..850760f485 100644 --- a/src/backend/utils/mmgr/slab.c +++ b/src/backend/utils/mmgr/slab.c @@ -69,6 +69,7 @@ #include "postgres.h" #include "lib/ilist.h" +#include "utils/backend_status.h" #include "utils/memdebug.h" #include "utils/memutils.h" #include "utils/memutils_internal.h" @@ -417,6 +418,13 @@ SlabContextCreate(MemoryContext parent, parent, name); + /* + * If SlabContextCreate is updated to add context header size to + * context->mem_allocated, then update here and SlabDelete appropriately + */ + pgstat_report_allocated_bytes_increase(Slab_CONTEXT_HDRSZ(slab->chunksPerBlock), + PG_ALLOC_SLAB); + return (MemoryContext) slab; } @@ -433,6 +441,7 @@ SlabReset(MemoryContext context) SlabContext *slab = (SlabContext *) context; dlist_mutable_iter miter; int i; + uint64 deallocation = 0; Assert(SlabIsValid(slab)); @@ -453,6 +462,7 @@ SlabReset(MemoryContext context) #endif free(block); context->mem_allocated -= slab->blockSize; + deallocation += slab->blockSize; } /* walk over blocklist and free the blocks */ @@ -469,9 +479,11 @@ SlabReset(MemoryContext context) #endif free(block); context->mem_allocated -= slab->blockSize; + deallocation += slab->blockSize; } } + pgstat_report_allocated_bytes_decrease(deallocation, PG_ALLOC_SLAB); slab->curBlocklistIndex = 0; Assert(context->mem_allocated == 0); @@ -486,6 +498,14 @@ SlabDelete(MemoryContext context) { /* Reset to release all the SlabBlocks */ SlabReset(context); + + /* + * Until context header allocation is included in context->mem_allocated, + * cast to slab and decrement the header allocation + */ + pgstat_report_allocated_bytes_decrease(Slab_CONTEXT_HDRSZ(((SlabContext *) context)->chunksPerBlock), + PG_ALLOC_SLAB); + /* And free the context header */ free(context); } @@ -569,6 +589,7 @@ SlabAllocFromNewBlock(MemoryContext context, Size size, int flags) block->slab = slab; context->mem_allocated += slab->blockSize; + pgstat_report_allocated_bytes_increase(slab->blockSize, PG_ALLOC_SLAB); /* use the first chunk in the new block */ chunk = SlabBlockGetChunk(slab, block, 0); @@ -797,6 +818,7 @@ SlabFree(void *pointer) #endif free(block); slab->header.mem_allocated -= slab->blockSize; + pgstat_report_allocated_bytes_decrease(slab->blockSize, PG_ALLOC_SLAB); } /* diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 4af5c2e847..56ab1f9470 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -5435,6 +5435,23 @@ proname => 'pg_stat_get_backend_idset', prorows => '100', proretset => 't', provolatile => 's', proparallel => 'r', prorettype => 'int4', proargtypes => '', prosrc => 'pg_stat_get_backend_idset' }, +{ oid => '9890', + descr => 'statistics: memory allocation information for backends', + proname => 'pg_stat_get_memory_allocation', prorows => '100', proisstrict => 'f', + proretset => 't', provolatile => 's', proparallel => 'r', + prorettype => 'record', proargtypes => 'int4', + proallargtypes => '{int4,oid,int4,int8,int8,int8,int8,int8}', + proargmodes => '{i,o,o,o,o,o,o,o}', + proargnames => '{pid,datid,pid,allocated_bytes,aset_allocated_bytes,dsm_allocated_bytes,generation_allocated_bytes,slab_allocated_bytes}', + prosrc => 'pg_stat_get_memory_allocation' }, +{ oid => '9891', + descr => 'statistics: global memory allocation information', + proname => 'pg_stat_get_global_memory_allocation', proisstrict => 'f', + provolatile => 's', proparallel => 'r', prorettype => 'record', + proargtypes => '', proallargtypes => '{oid,int8}', + proargmodes => '{o,o}', + proargnames => '{datid,global_dsm_allocated_bytes}', + prosrc =>'pg_stat_get_global_memory_allocation' }, { oid => '2022', descr => 'statistics: information about currently active backends', proname => 'pg_stat_get_activity', prorows => '100', proisstrict => 'f', diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1095aefddf..a350f455cd 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -422,6 +422,8 @@ typedef struct PROC_HDR int spins_per_delay; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ int startupBufferPinWaitBufId; + /* Global dsm allocations */ + pg_atomic_uint64 global_dsm_allocation; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; diff --git a/src/include/utils/backend_status.h b/src/include/utils/backend_status.h index 7b7f6f59d0..cbf801884d 100644 --- a/src/include/utils/backend_status.h +++ b/src/include/utils/backend_status.h @@ -10,6 +10,7 @@ #ifndef BACKEND_STATUS_H #define BACKEND_STATUS_H +#include "common/int.h" #include "datatype/timestamp.h" #include "libpq/pqcomm.h" #include "miscadmin.h" /* for BackendType */ @@ -32,6 +33,14 @@ typedef enum BackendState STATE_DISABLED, } BackendState; +/* Enum helper for reporting memory allocator type */ +enum pg_allocator_type +{ + PG_ALLOC_ASET = 1, + PG_ALLOC_DSM, + PG_ALLOC_GENERATION, + PG_ALLOC_SLAB +}; /* ---------- * Shared-memory data structures @@ -170,6 +179,15 @@ typedef struct PgBackendStatus /* query identifier, optionally computed using post_parse_analyze_hook */ uint64 st_query_id; + + /* Current memory allocated to this backend */ + uint64 allocated_bytes; + + /* Current memory allocated to this backend by type */ + uint64 aset_allocated_bytes; + uint64 dsm_allocated_bytes; + uint64 generation_allocated_bytes; + uint64 slab_allocated_bytes; } PgBackendStatus; @@ -292,6 +310,11 @@ extern PGDLLIMPORT int pgstat_track_activity_query_size; * ---------- */ extern PGDLLIMPORT PgBackendStatus *MyBEEntry; +extern PGDLLIMPORT uint64 *my_allocated_bytes; +extern PGDLLIMPORT uint64 *my_aset_allocated_bytes; +extern PGDLLIMPORT uint64 *my_dsm_allocated_bytes; +extern PGDLLIMPORT uint64 *my_generation_allocated_bytes; +extern PGDLLIMPORT uint64 *my_slab_allocated_bytes; /* ---------- @@ -323,7 +346,12 @@ extern const char *pgstat_get_backend_current_activity(int pid, bool checkUser); extern const char *pgstat_get_crashed_backend_activity(int pid, char *buffer, int buflen); extern uint64 pgstat_get_my_query_id(void); - +extern void pgstat_set_allocated_bytes_storage(uint64 *allocated_bytes, + uint64 *aset_allocated_bytes, + uint64 *dsm_allocated_bytes, + uint64 *generation_allocated_bytes, + uint64 *slab_allocated_bytes); +extern void pgstat_reset_allocated_bytes_storage(void); /* ---------- * Support functions for the SQL-callable functions to @@ -336,5 +364,119 @@ extern LocalPgBackendStatus *pgstat_get_local_beentry_by_proc_number(ProcNumber extern LocalPgBackendStatus *pgstat_get_local_beentry_by_index(int idx); extern char *pgstat_clip_activity(const char *raw_activity); +/* ---------- + * pgstat_report_allocated_bytes_decrease() - + * Called to report decrease in memory allocated for this backend. + * + * my_{*_}allocated_bytes initially points to local memory, making it safe to + * call this before pgstats has been initialized. + * ---------- + */ +static inline void +pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, + int pg_allocator_type) +{ + uint64 temp; + + /* Avoid allocated_bytes unsigned integer overflow on decrease */ + if (pg_sub_u64_overflow(*my_allocated_bytes, proc_allocated_bytes, &temp)) + { + /* On overflow, set allocated bytes and allocator type bytes to zero */ + *my_allocated_bytes = 0; + *my_aset_allocated_bytes = 0; + *my_dsm_allocated_bytes = 0; + *my_generation_allocated_bytes = 0; + *my_slab_allocated_bytes = 0; + } + else + { + /* decrease allocation */ + *my_allocated_bytes -= proc_allocated_bytes; + + /* Decrease allocator type allocated bytes. */ + switch (pg_allocator_type) + { + case PG_ALLOC_ASET: + *my_aset_allocated_bytes -= proc_allocated_bytes; + break; + case PG_ALLOC_DSM: + + /* + * Some dsm allocations live beyond process exit. These are + * accounted for in a global counter in + * pgstat_reset_allocated_bytes_storage at process exit. + */ + *my_dsm_allocated_bytes -= proc_allocated_bytes; + break; + case PG_ALLOC_GENERATION: + *my_generation_allocated_bytes -= proc_allocated_bytes; + break; + case PG_ALLOC_SLAB: + *my_slab_allocated_bytes -= proc_allocated_bytes; + break; + } + } + + return; +} + +/* ---------- + * pgstat_report_allocated_bytes_increase() - + * Called to report increase in memory allocated for this backend. + * + * my_allocated_bytes initially points to local memory, making it safe to call + * this before pgstats has been initialized. + * ---------- + */ +static inline void +pgstat_report_allocated_bytes_increase(int64 proc_allocated_bytes, + int pg_allocator_type) +{ + *my_allocated_bytes += proc_allocated_bytes; + + /* Increase allocator type allocated bytes */ + switch (pg_allocator_type) + { + case PG_ALLOC_ASET: + *my_aset_allocated_bytes += proc_allocated_bytes; + break; + case PG_ALLOC_DSM: + + /* + * Some dsm allocations live beyond process exit. These are + * accounted for in a global counter in + * pgstat_reset_allocated_bytes_storage at process exit. + */ + *my_dsm_allocated_bytes += proc_allocated_bytes; + break; + case PG_ALLOC_GENERATION: + *my_generation_allocated_bytes += proc_allocated_bytes; + break; + case PG_ALLOC_SLAB: + *my_slab_allocated_bytes += proc_allocated_bytes; + break; + } + + return; +} + +/* --------- + * pgstat_init_allocated_bytes() - + * + * Called to initialize allocated bytes variables after fork and to + * avoid double counting allocations. + * --------- + */ +static inline void +pgstat_init_allocated_bytes(void) +{ + *my_allocated_bytes = 0; + *my_aset_allocated_bytes = 0; + *my_dsm_allocated_bytes = 0; + *my_generation_allocated_bytes = 0; + *my_slab_allocated_bytes = 0; + + return; +} #endif /* BACKEND_STATUS_H */ diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 0cd2c64fca..2f62f5e4ea 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1877,6 +1877,24 @@ pg_stat_database_conflicts| SELECT oid AS datid, pg_stat_get_db_conflict_startup_deadlock(oid) AS confl_deadlock, pg_stat_get_db_conflict_logicalslot(oid) AS confl_active_logicalslot FROM pg_database d; +pg_stat_global_memory_allocation| WITH sums AS ( + SELECT sum(pg_stat_memory_allocation.aset_allocated_bytes) AS total_aset_allocated_bytes, + sum(pg_stat_memory_allocation.dsm_allocated_bytes) AS total_dsm_allocated_bytes, + sum(pg_stat_memory_allocation.generation_allocated_bytes) AS total_generation_allocated_bytes, + sum(pg_stat_memory_allocation.slab_allocated_bytes) AS total_slab_allocated_bytes + FROM pg_stat_memory_allocation + ) + SELECT s.datid, + current_setting('shared_memory_size'::text, true) AS shared_memory_size, + (current_setting('shared_memory_size_in_huge_pages'::text, true))::integer AS shared_memory_size_in_huge_pages, + s.global_dsm_allocated_bytes, + sums.total_aset_allocated_bytes, + sums.total_dsm_allocated_bytes, + sums.total_generation_allocated_bytes, + sums.total_slab_allocated_bytes + FROM sums, + (pg_stat_get_global_memory_allocation() s(datid, global_dsm_allocated_bytes) + LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_gssapi| SELECT pid, gss_auth AS gss_authenticated, gss_princ AS principal, @@ -1903,6 +1921,15 @@ pg_stat_io| SELECT backend_type, fsync_time, stats_reset FROM pg_stat_get_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset); +pg_stat_memory_allocation| SELECT s.datid, + s.pid, + s.allocated_bytes, + s.aset_allocated_bytes, + s.dsm_allocated_bytes, + s.generation_allocated_bytes, + s.slab_allocated_bytes + FROM (pg_stat_get_memory_allocation(NULL::integer) s(datid, pid, allocated_bytes, aset_allocated_bytes, dsm_allocated_bytes, generation_allocated_bytes, slab_allocated_bytes) + LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_progress_analyze| SELECT s.pid, s.datid, d.datname, diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out index 6e08898b18..902d827998 100644 --- a/src/test/regress/expected/stats.out +++ b/src/test/regress/expected/stats.out @@ -1646,4 +1646,40 @@ SELECT COUNT(*) FROM brin_hot_3 WHERE a = 2; DROP TABLE brin_hot_3; SET enable_seqscan = on; +-- ensure that allocated_bytes exist for backends +SELECT + allocated_bytes > 0 AS result +FROM + pg_stat_activity ps + JOIN pg_stat_memory_allocation pa ON (pa.pid = ps.pid) +WHERE + backend_type IN ('checkpointer', 'background writer', 'walwriter', 'autovacuum launcher'); + result +-------- + t + t + t + t +(4 rows) + +-- ensure that pg_stat_global_memory_allocation view exists +SELECT + datid > 0, pg_size_bytes(shared_memory_size) >= 0, shared_memory_size_in_huge_pages >= -1, global_dsm_allocated_bytes >= 0 +FROM + pg_stat_global_memory_allocation; + ?column? | ?column? | ?column? | ?column? +----------+----------+----------+---------- + t | t | t | t +(1 row) + +-- ensure that pg_stat_memory_allocation view exists +SELECT + pid > 0, allocated_bytes >= 0, aset_allocated_bytes >= 0, dsm_allocated_bytes >= 0, generation_allocated_bytes >= 0, slab_allocated_bytes >= 0 +FROM + pg_stat_memory_allocation limit 1; + ?column? | ?column? | ?column? | ?column? | ?column? | ?column? +----------+----------+----------+----------+----------+---------- + t | t | t | t | t | t +(1 row) + -- End of Stats Test diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql index d8ac0d06f4..40746c9258 100644 --- a/src/test/regress/sql/stats.sql +++ b/src/test/regress/sql/stats.sql @@ -849,4 +849,24 @@ DROP TABLE brin_hot_3; SET enable_seqscan = on; +-- ensure that allocated_bytes exist for backends +SELECT + allocated_bytes > 0 AS result +FROM + pg_stat_activity ps + JOIN pg_stat_memory_allocation pa ON (pa.pid = ps.pid) +WHERE + backend_type IN ('checkpointer', 'background writer', 'walwriter', 'autovacuum launcher'); + +-- ensure that pg_stat_global_memory_allocation view exists +SELECT + datid > 0, pg_size_bytes(shared_memory_size) >= 0, shared_memory_size_in_huge_pages >= -1, global_dsm_allocated_bytes >= 0 +FROM + pg_stat_global_memory_allocation; + +-- ensure that pg_stat_memory_allocation view exists +SELECT + pid > 0, allocated_bytes >= 0, aset_allocated_bytes >= 0, dsm_allocated_bytes >= 0, generation_allocated_bytes >= 0, slab_allocated_bytes >= 0 +FROM + pg_stat_memory_allocation limit 1; -- End of Stats Test -- 2.43.2 [text/x-patch] v20240314-0002-Add-the-ability-to-limit-the-amount-of-memory-that-c.patch (37.7K, ../../[email protected]/3-v20240314-0002-Add-the-ability-to-limit-the-amount-of-memory-that-c.patch) download | inline diff: From 72656bfa6819990be79bf925e5e888168aeb71a4 Mon Sep 17 00:00:00 2001 From: Tomas Vondra <[email protected]> Date: Tue, 26 Dec 2023 17:55:23 +0100 Subject: [PATCH 2/2] Add the ability to limit the amount of memory that can be allocated to backends. This builds on the work that adds backend memory allocated tracking. Add GUC variable max_total_backend_memory. Specifies a limit to the amount of memory (in MB) that may be allocated to backends in total (i.e. this is not a per user or per backend limit). If unset, or set to 0 it is disabled. It is intended as a resource to help avoid the OOM killer on LINUX and manage resources in general. A backend request that would exhaust max_total_backend_memory memory will be denied with an out of memory error causing that backend's current query/transaction to fail. Further requests will not be allocated until dropping below the limit. Keep this in mind when setting this value. Due to the dynamic nature of memory allocations, this limit is not exact. This limit does not affect auxiliary backend processes. Backend memory allocations are displayed in the pg_stat_memory_allocation and pg_stat_global_memory_allocation views. --- doc/src/sgml/config.sgml | 30 +++ doc/src/sgml/monitoring.sgml | 38 +++- src/backend/catalog/system_views.sql | 2 + src/backend/port/sysv_shmem.c | 9 + src/backend/postmaster/postmaster.c | 5 + src/backend/storage/ipc/dsm_impl.c | 18 ++ src/backend/storage/lmgr/proc.c | 45 +++++ src/backend/utils/activity/backend_status.c | 175 ++++++++++++++++++ src/backend/utils/adt/pgstatfuncs.c | 16 +- src/backend/utils/hash/dynahash.c | 3 +- src/backend/utils/init/miscinit.c | 8 + src/backend/utils/misc/guc_tables.c | 11 ++ src/backend/utils/misc/postgresql.conf.sample | 3 + src/backend/utils/mmgr/aset.c | 33 ++++ src/backend/utils/mmgr/generation.c | 16 ++ src/backend/utils/mmgr/slab.c | 15 +- src/include/catalog/pg_proc.dat | 6 +- src/include/storage/proc.h | 7 + src/include/utils/backend_status.h | 103 ++++++++++- src/test/regress/expected/rules.out | 4 +- 20 files changed, 526 insertions(+), 21 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 65a6e6c408..4f26284ee1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -2306,6 +2306,36 @@ include_dir 'conf.d' </listitem> </varlistentry> + <varlistentry id="guc-max-total-backend-memory" xreflabel="max_total_backend_memory"> + <term><varname>max_total_backend_memory</varname> (<type>integer</type>) + <indexterm> + <primary><varname>max_total_backend_memory</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies a limit to the amount of memory (MB) that may be allocated to + backends in total (i.e. this is not a per user or per backend limit). + If unset, or set to 0 it is disabled. At databse startup + max_total_backend_memory is reduced by shared_memory_size_mb + (includes shared buffers and other memory required for initialization). + Each backend process is intialized with a 1MB local allowance which + also reduces total_bkend_mem_bytes_available. Keep this in mind when + setting this value. A backend request that would exhaust the limit will + be denied with an out of memory error causing that backend's current + query/transaction to fail. Further requests will not be allocated until + dropping below the limit. This limit does not affect auxiliary backend + processes + <xref linkend="glossary-auxiliary-proc"/> or the postmaster process. + Backend memory allocations (<varname>allocated_bytes</varname>) are + displayed in the + <link linkend="monitoring-pg-stat-memory-allocation-view"><structname>pg_stat_memory_allocation</structname></link> + view. Due to the dynamic nature of memory allocations, this limit is + not exact. + </para> + </listitem> + </varlistentry> + </variablelist> </sect2> diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 41d788be45..3c3689c03b 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -4659,10 +4659,7 @@ description | Waiting for a newly initialized WAL file to reach durable storage </para> <para> Memory currently allocated to this backend in bytes. This is the balance - of bytes allocated and freed by this backend. Dynamic shared memory - allocations are included only in the value displayed for the backend that - created them, they are not included in the value for backends that are - attached to them to avoid double counting. + of bytes allocated and freed by this backend. </para></entry> </row> @@ -4779,6 +4776,39 @@ description | Waiting for a newly initialized WAL file to reach durable storage </para></entry> </row> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>max_total_backend_memory_bytes</structfield> <type>bigint</type> + </para> + <para> + Reports the user defined backend maximum allowed shared memory in bytes. + 0 if disabled or not set. See + <xref linkend="guc-max-total-backend-memory"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>total_bkend_mem_bytes_available</structfield> <type>bigint</type> + </para> + <para> + Tracks max_total_backend_memory (in bytes) available for allocation. At + database startup, total_bkend_mem_bytes_available is reduced by the + byte equivalent of shared_memory_size_mb. Each backend process is + intialized with a 1MB local allowance which also reduces + total_bkend_mem_bytes_available. A process's allocation requests reduce + it's local allowance. If a process's allocation request exceeds it's + remaining allowance, an attempt is made to refill the local allowance + from total_bkend_mem_bytes_available. If the refill request fails, then + the requesting process will fail with an out of memory error resulting + in the cancellation of that process's active query/transaction. The + default refill allocation quantity is 1MB. If a request is greater than + 1MB, an attempt will be made to allocate the full amount. If + max_total_backend_memory is disabled, this will be -1. + <xref linkend="guc-max-total-backend-memory"/>. + </para></entry> + </row> + <row> <entry role="catalog_table_entry"><para role="column_definition"> <structfield>global_dsm_allocated_bytes</structfield> <type>bigint</type> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 61ff4a59b6..c646b28f16 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1402,6 +1402,8 @@ SELECT S.datid AS datid, current_setting('shared_memory_size', true) as shared_memory_size, (current_setting('shared_memory_size_in_huge_pages', true))::integer as shared_memory_size_in_huge_pages, + pg_size_bytes(current_setting('max_total_backend_memory', true)) as max_total_backend_memory_bytes, + S.total_bkend_mem_bytes_available, S.global_dsm_allocated_bytes, sums.total_aset_allocated_bytes, sums.total_dsm_allocated_bytes, diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 1a6d8fa0fb..c0788732df 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -34,6 +34,7 @@ #include "storage/fd.h" #include "storage/ipc.h" #include "storage/pg_shmem.h" +#include "utils/backend_status.h" #include "utils/guc.h" #include "utils/guc_hooks.h" #include "utils/pidfile.h" @@ -918,6 +919,14 @@ PGSharedMemoryReAttach(void) dsm_set_control_handle(hdr->dsm_control); UsedShmemSegAddr = hdr; /* probably redundant */ + + /* + * Init allocated bytes to avoid double counting parent allocation for + * fork/exec processes. Forked processes perform this action in + * InitPostmasterChild. For EXEC_BACKEND processes we have to wait for + * shared memory to be reattached. + */ + pgstat_init_allocated_bytes(); } /* diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 49fc6f979e..abb10ed7c8 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -556,6 +556,7 @@ typedef struct #endif char my_exec_path[MAXPGPATH]; char pkglib_path[MAXPGPATH]; + int max_total_bkend_mem; } BackendParameters; static void read_backend_variables(char *id, ClientSocket **client_sock, BackgroundWorker **worker); @@ -6152,6 +6153,8 @@ save_backend_variables(BackendParameters *param, ClientSocket *client_sock, Back strlcpy(param->pkglib_path, pkglib_path, MAXPGPATH); + param->max_total_bkend_mem = max_total_bkend_mem; + return true; } @@ -6391,6 +6394,8 @@ restore_backend_variables(BackendParameters *param, ClientSocket **client_sock, strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH); + max_total_bkend_mem = param->max_total_bkend_mem; + /* * We need to restore fd.c's counts of externally-opened FDs; to avoid * confusion, be sure to do this after restoring max_safe_fds. (Note: diff --git a/src/backend/storage/ipc/dsm_impl.c b/src/backend/storage/ipc/dsm_impl.c index af67e55bdf..b6dee75423 100644 --- a/src/backend/storage/ipc/dsm_impl.c +++ b/src/backend/storage/ipc/dsm_impl.c @@ -254,6 +254,16 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, return true; } + /* Do not exceed maximum allowed memory allocation */ + if (op == DSM_OP_CREATE && exceeds_max_total_bkend_mem(request_size)) + { + ereport(elevel, + (errcode_for_dynamic_shared_memory(), + errmsg("out of memory for segment \"%s\" - exceeds max_total_backend_memory: %m", + name))); + return false; + } + /* * Create new segment or open an existing one for attach. * @@ -523,6 +533,10 @@ dsm_impl_sysv(dsm_op op, dsm_handle handle, Size request_size, int flags = IPCProtection; size_t segsize; + /* Do not exceed maximum allowed memory allocation */ + if (op == DSM_OP_CREATE && exceeds_max_total_bkend_mem(request_size)) + return false; + /* * Allocate the memory BEFORE acquiring the resource, so that we don't * leak the resource if memory allocation fails. @@ -717,6 +731,10 @@ dsm_impl_windows(dsm_op op, dsm_handle handle, Size request_size, return true; } + /* Do not exceed maximum allowed memory allocation */ + if (op == DSM_OP_CREATE && exceeds_max_total_bkend_mem(request_size)) + return false; + /* Create new segment or open an existing one for attach. */ if (op == DSM_OP_CREATE) { diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 1959b5f4e6..6dbe4373f8 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -50,6 +50,7 @@ #include "storage/procsignal.h" #include "storage/spin.h" #include "storage/standby.h" +#include "utils/guc.h" #include "utils/timeout.h" #include "utils/timestamp.h" @@ -182,6 +183,50 @@ InitProcGlobal(void) pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PROC_NUMBER); pg_atomic_init_u64(&ProcGlobal->global_dsm_allocation, 0); + /* Setup backend memory limiting if configured */ + if (max_total_bkend_mem > 0) + { + /* + * Convert max_total_bkend_mem to bytes, account for + * shared_memory_size, and initialize total_bkend_mem_bytes. + */ + int result = 0; + + /* Get integer value of shared_memory_size */ + if (parse_int(GetConfigOption("shared_memory_size", true, false), &result, 0, NULL)) + { + /* + * Error on startup if backend memory limit is less than shared + * memory size. Warn on startup if backend memory available is + * less than arbitrarily picked value of 100MB. + */ + + if (max_total_bkend_mem - result <= 0) + { + ereport(ERROR, + errmsg("configured max_total_backend_memory %dMB is <= shared_memory_size %dMB", + max_total_bkend_mem, result), + errhint("Disable or increase the configuration parameter \"max_total_backend_memory\".")); + } + else if (max_total_bkend_mem - result <= 100) + { + ereport(WARNING, + errmsg("max_total_backend_memory %dMB - shared_memory_size %dMB is <= 100MB", + max_total_bkend_mem, result), + errhint("Consider increasing the configuration parameter \"max_total_backend_memory\".")); + } + + /* + * Account for shared memory size and initialize + * total_bkend_mem_bytes. + */ + pg_atomic_init_u64(&ProcGlobal->total_bkend_mem_bytes, + (uint64) max_total_bkend_mem * 1024 * 1024 - (uint64) result * 1024 * 1024); + } + else + ereport(ERROR, errmsg("max_total_backend_memory initialization is unable to parse shared_memory_size")); + } + /* * Create and initialize all the PGPROC structures we'll need. There are * five separate consumers: (1) normal backends, (2) autovacuum workers diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c index 25b545441b..c125dc3abb 100644 --- a/src/backend/utils/activity/backend_status.c +++ b/src/backend/utils/activity/backend_status.c @@ -44,6 +44,12 @@ bool pgstat_track_activities = false; int pgstat_track_activity_query_size = 1024; +/* + * Max backend memory allocation allowed (MB). 0 = disabled. + * Centralized bucket ProcGlobal->max_total_bkend_mem is initialized + * as a byte representation of this value in InitProcGlobal(). + */ +int max_total_bkend_mem = 0; /* exposed so that backend_progress.c can access it */ PgBackendStatus *MyBEEntry = NULL; @@ -67,6 +73,31 @@ uint64 *my_generation_allocated_bytes = &local_my_generation_allocated_bytes; uint64 local_my_slab_allocated_bytes = 0; uint64 *my_slab_allocated_bytes = &local_my_slab_allocated_bytes; +/* + * Define initial allocation allowance for a backend. + * + * NOTE: initial_allocation_allowance && allocation_allowance_refill_qty + * may be candidates for future GUC variables. Arbitrary 1MB selected initially. + */ +uint64 initial_allocation_allowance = 1024 * 1024; +uint64 allocation_allowance_refill_qty = 1024 * 1024; + +/* + * Local counter to manage shared memory allocations. At backend startup, set to + * initial_allocation_allowance via pgstat_init_allocated_bytes(). Decrease as + * memory is malloc'd. When exhausted, atomically refill if available from + * ProcGlobal->max_total_bkend_mem via exceeds_max_total_bkend_mem(). + */ +uint64 allocation_allowance = 0; + +/* + * Local counter of free'd shared memory. Return to global + * max_total_bkend_mem when return threshold is met. Arbitrary 1MB bytes + * selected initially. + */ +uint64 allocation_return = 0; +uint64 allocation_return_threshold = 1024 * 1024; + static PgBackendStatus *BackendStatusArray = NULL; static char *BackendAppnameBuffer = NULL; static char *BackendClientHostnameBuffer = NULL; @@ -1272,6 +1303,8 @@ pgstat_set_allocated_bytes_storage(uint64 *allocated_bytes, my_slab_allocated_bytes = slab_allocated_bytes; *slab_allocated_bytes = local_my_slab_allocated_bytes; + + return; } /* @@ -1295,6 +1328,23 @@ pgstat_reset_allocated_bytes_storage(void) *my_dsm_allocated_bytes); } + /* + * When limiting maximum backend memory, return this backend's memory + * allocations to global. + */ + if (max_total_bkend_mem) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + pg_atomic_add_fetch_u64(&procglobal->total_bkend_mem_bytes, + *my_allocated_bytes + allocation_allowance + + allocation_return); + + /* Reset memory allocation variables */ + allocation_allowance = 0; + allocation_return = 0; + } + /* Reset memory allocation variables */ *my_allocated_bytes = local_my_allocated_bytes = 0; *my_aset_allocated_bytes = local_my_aset_allocated_bytes = 0; @@ -1308,4 +1358,129 @@ pgstat_reset_allocated_bytes_storage(void) my_dsm_allocated_bytes = &local_my_dsm_allocated_bytes; my_generation_allocated_bytes = &local_my_generation_allocated_bytes; my_slab_allocated_bytes = &local_my_slab_allocated_bytes; + + return; +} + +/* + * Determine if allocation request will exceed max backend memory allowed. + * Do not apply to auxiliary processes. + * Refill allocation request bucket when needed/possible. + */ +bool +exceeds_max_total_bkend_mem(uint64 allocation_request) +{ + bool result = false; + + /* + * When limiting maximum backend memory, attempt to refill allocation + * request bucket if needed. + */ + if (max_total_bkend_mem && allocation_request > allocation_allowance && + ProcGlobal != NULL) + { + volatile PROC_HDR *procglobal = ProcGlobal; + uint64 available_max_total_bkend_mem = 0; + bool sts = false; + + /* + * If allocation request is larger than memory refill quantity then + * attempt to increase allocation allowance with requested amount, + * otherwise fall through. If this refill fails we do not have enough + * memory to meet the request. + */ + if (allocation_request >= allocation_allowance_refill_qty) + { + while ((available_max_total_bkend_mem = pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)) >= allocation_request) + { + if ((result = pg_atomic_compare_exchange_u64(&procglobal->total_bkend_mem_bytes, + &available_max_total_bkend_mem, + available_max_total_bkend_mem - allocation_request))) + { + allocation_allowance = allocation_allowance + allocation_request; + break; + } + } + + /* + * Exclude auxiliary and Postmaster processes from the check. + * Return false. While we want to exclude them from the check, we + * do not want to exclude them from the above allocation handling. + */ + switch (MyBackendType) + { + case B_STARTUP: + case B_ARCHIVER: + case B_BG_WRITER: + case B_CHECKPOINTER: + case B_WAL_WRITER: + case B_WAL_RECEIVER: + case B_WAL_SUMMARIZER: + return false; + default: + break; + } + + if (MyProcPid == PostmasterPid) + return false; + + /* + * If the atomic exchange fails (result == false), we do not have + * enough reserve memory to meet the request. Negate result to + * return the proper value. + */ + + return !result; + } + + /* + * Attempt to increase allocation allowance by memory refill quantity. + * If available memory is/becomes less than memory refill quantity, + * fall through to attempt to allocate remaining available memory. + */ + while ((available_max_total_bkend_mem = pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)) >= allocation_allowance_refill_qty) + { + if ((sts = pg_atomic_compare_exchange_u64(&procglobal->total_bkend_mem_bytes, + &available_max_total_bkend_mem, + available_max_total_bkend_mem - allocation_allowance_refill_qty))) + { + allocation_allowance = allocation_allowance + allocation_allowance_refill_qty; + break; + } + } + + /* Do not attempt to increase allocation if available memory is below + * allocation_allowance_refill_qty . + */ + + /* + * If refill is not successful, we return true, memory limit exceeded + */ + if (!sts) + result = true; + } + + /* + * Exclude auxiliary and postmaster processes from the check. Return false. + * While we want to exclude them from the check, we do not want to exclude + * them from the above allocation handling. + */ + switch (MyBackendType) + { + case B_STARTUP: + case B_ARCHIVER: + case B_BG_WRITER: + case B_CHECKPOINTER: + case B_WAL_WRITER: + case B_WAL_RECEIVER: + case B_WAL_SUMMARIZER: + result = false; + default: + break; + } + + if (MyProcPid == PostmasterPid) + result = false; + + return result; } diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 9c82ec48cb..15d2800d5b 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2093,7 +2093,7 @@ pg_stat_get_memory_allocation(PG_FUNCTION_ARGS) Datum pg_stat_get_global_memory_allocation(PG_FUNCTION_ARGS) { -#define PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS 2 +#define PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS 3 TupleDesc tupdesc; Datum values[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; bool nulls[PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS] = {0}; @@ -2103,15 +2103,23 @@ pg_stat_get_global_memory_allocation(PG_FUNCTION_ARGS) tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_GLOBAL_MEMORY_ALLOCATION_COLS); TupleDescInitEntry(tupdesc, (AttrNumber) 1, "datid", OIDOID, -1, 0); - TupleDescInitEntry(tupdesc, (AttrNumber) 2, "global_dsm_allocated_bytes", + TupleDescInitEntry(tupdesc, (AttrNumber) 2, "total_bkend_mem_bytes_available", + INT8OID, -1, 0); + TupleDescInitEntry(tupdesc, (AttrNumber) 3, "global_dsm_allocated_bytes", INT8OID, -1, 0); BlessTupleDesc(tupdesc); /* datid */ values[0] = ObjectIdGetDatum(MyDatabaseId); - /* get global_dsm_allocated_bytes */ - values[1] = Int64GetDatum(pg_atomic_read_u64(&procglobal->global_dsm_allocation)); + /* Get total_bkend_mem_bytes - return -1 if disabled */ + if (max_total_bkend_mem == 0) + values[1] = Int64GetDatum(-1); + else + values[1] = Int64GetDatum(pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)); + + /* Get global_dsm_allocated_bytes */ + values[2] = Int64GetDatum(pg_atomic_read_u64(&procglobal->global_dsm_allocation)); /* Returns the record as Datum */ PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls))); diff --git a/src/backend/utils/hash/dynahash.c b/src/backend/utils/hash/dynahash.c index a4152080b5..9450032a89 100644 --- a/src/backend/utils/hash/dynahash.c +++ b/src/backend/utils/hash/dynahash.c @@ -104,7 +104,6 @@ #include "utils/dynahash.h" #include "utils/memutils.h" - /* * Constants * @@ -359,7 +358,6 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) Assert(flags & HASH_ELEM); Assert(info->keysize > 0); Assert(info->entrysize >= info->keysize); - /* * For shared hash tables, we have a local hash header (HTAB struct) that * we allocate in TopMemoryContext; all else is in shared memory. @@ -377,6 +375,7 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags) } else { + /* Set up to allocate the hash header */ /* Create the hash table's private memory context */ if (flags & HASH_CONTEXT) CurrentDynaHashCxt = info->hcxt; diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c index 9b47450813..d72ec3a0db 100644 --- a/src/backend/utils/init/miscinit.c +++ b/src/backend/utils/init/miscinit.c @@ -171,8 +171,16 @@ InitPostmasterChild(void) errmsg_internal("could not set postmaster death monitoring pipe to FD_CLOEXEC mode: %m"))); #endif + /* + * Init pgstat allocated bytes counters here for forked backends. + * Fork/exec backends have not yet reattached to shared memory at this + * point. They will init pgstat allocated bytes counters in + * PGSharedMemoryReAttach. + */ +#ifndef EXEC_BACKEND /* Init allocated bytes to avoid double counting parent allocation */ pgstat_init_allocated_bytes(); +#endif } /* diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index 57d9de4dd9..65f0b69319 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -3626,6 +3626,17 @@ struct config_int ConfigureNamesInt[] = NULL, NULL, NULL }, + { + {"max_total_backend_memory", PGC_SU_BACKEND, RESOURCES_MEM, + gettext_noop("Restrict total backend memory allocations to this max."), + gettext_noop("0 turns this feature off."), + GUC_UNIT_MB + }, + &max_total_bkend_mem, + 0, 0, INT_MAX, + NULL, NULL, NULL + }, + /* End-of-list marker */ { {NULL, 0, 0, NULL, NULL}, NULL, 0, 0, 0, NULL, NULL, NULL diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2244ee52f7..50e2bb2bcf 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -169,6 +169,9 @@ #vacuum_buffer_usage_limit = 256kB # size of vacuum and analyze buffer access strategy ring; # 0 to disable vacuum buffer access strategy; # range 128kB to 16GB +#max_total_backend_memory = 0MB # Restrict total backend memory allocations + # to this max (in MB). 0 turns this feature + # off. # - Disk - diff --git a/src/backend/utils/mmgr/aset.c b/src/backend/utils/mmgr/aset.c index cd074add17..f0ee6a9390 100644 --- a/src/backend/utils/mmgr/aset.c +++ b/src/backend/utils/mmgr/aset.c @@ -438,6 +438,18 @@ AllocSetContextCreateInternal(MemoryContext parent, else firstBlockSize = Max(firstBlockSize, initBlockSize); + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(firstBlockSize)) + { + if (TopMemoryContext) + MemoryContextStats(TopMemoryContext); + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory - exceeds max_total_backend_memory"), + errdetail("Failed while creating memory context \"%s\".", + name))); + } + /* * Allocate the initial block. Unlike other aset.c blocks, it starts with * the context header and its block header follows that. @@ -724,6 +736,11 @@ AllocSetAllocLarge(MemoryContext context, Size size, int flags) #endif blksize = chunk_size + ALLOC_BLOCKHDRSZ + ALLOC_CHUNKHDRSZ; + + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (AllocBlock) malloc(blksize); if (block == NULL) return MemoryContextAllocationFailure(context, size, flags); @@ -917,6 +934,10 @@ AllocSetAllocFromNewBlock(MemoryContext context, Size size, int flags, while (blksize < required_size) blksize <<= 1; + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + /* Try to allocate it */ block = (AllocBlock) malloc(blksize); @@ -1238,6 +1259,18 @@ AllocSetRealloc(void *pointer, Size size, int flags) blksize = chksize + ALLOC_BLOCKHDRSZ + ALLOC_CHUNKHDRSZ; oldblksize = block->endptr - ((char *) block); + /* + * Do not exceed maximum allowed memory allocation. NOTE: checking for + * the full size here rather than just the amount of increased + * allocation to prevent a potential underflow of *my_allocation + * allowance in cases where blksize - oldblksize does not trigger a + * refill but blksize is greater than *my_allocation_allowance. + * Underflow would occur with the call below to + * pgstat_report_allocated_bytes_increase() + */ + if (blksize > oldblksize && exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (AllocBlock) realloc(block, blksize); if (block == NULL) { diff --git a/src/backend/utils/mmgr/generation.c b/src/backend/utils/mmgr/generation.c index dbea4f248e..3a6e3abeb8 100644 --- a/src/backend/utils/mmgr/generation.c +++ b/src/backend/utils/mmgr/generation.c @@ -203,6 +203,16 @@ GenerationContextCreate(MemoryContext parent, else allocSize = Max(allocSize, initBlockSize); + if (exceeds_max_total_bkend_mem(allocSize)) + { + MemoryContextStats(TopMemoryContext); + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory - exceeds max_total_backend_memory"), + errdetail("Failed while creating memory context \"%s\".", + name))); + } + /* * Allocate the initial block. Unlike other generation.c blocks, it * starts with the context header and its block header follows that. @@ -372,6 +382,9 @@ GenerationAllocLarge(MemoryContext context, Size size, int flags) required_size = chunk_size + Generation_CHUNKHDRSZ; blksize = required_size + Generation_BLOCKHDRSZ; + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (GenerationBlock *) malloc(blksize); if (block == NULL) return MemoryContextAllocationFailure(context, size, flags); @@ -494,6 +507,9 @@ GenerationAllocFromNewBlock(MemoryContext context, Size size, int flags, if (blksize < required_size) blksize = pg_nextpower2_size_t(required_size); + if (exceeds_max_total_bkend_mem(blksize)) + return NULL; + block = (GenerationBlock *) malloc(blksize); if (block == NULL) diff --git a/src/backend/utils/mmgr/slab.c b/src/backend/utils/mmgr/slab.c index 850760f485..36b3f14279 100644 --- a/src/backend/utils/mmgr/slab.c +++ b/src/backend/utils/mmgr/slab.c @@ -360,7 +360,16 @@ SlabContextCreate(MemoryContext parent, elog(ERROR, "block size %zu for slab is too small for %zu-byte chunks", blockSize, chunkSize); - + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(Slab_CONTEXT_HDRSZ(chunksPerBlock))) + { + MemoryContextStats(TopMemoryContext); + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory - exceeds max_total_backend_memory"), + errdetail("Failed while creating memory context \"%s\".", + name))); + } slab = (SlabContext *) malloc(Slab_CONTEXT_HDRSZ(chunksPerBlock)); if (slab == NULL) @@ -582,6 +591,10 @@ SlabAllocFromNewBlock(MemoryContext context, Size size, int flags) } else { + /* Do not exceed maximum allowed memory allocation */ + if (exceeds_max_total_bkend_mem(slab->blockSize)) + return MemoryContextAllocationFailure(context, size, flags); + block = (SlabBlock *) malloc(slab->blockSize); if (unlikely(block == NULL)) diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 56ab1f9470..79869d1c41 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -5448,9 +5448,9 @@ descr => 'statistics: global memory allocation information', proname => 'pg_stat_get_global_memory_allocation', proisstrict => 'f', provolatile => 's', proparallel => 'r', prorettype => 'record', - proargtypes => '', proallargtypes => '{oid,int8}', - proargmodes => '{o,o}', - proargnames => '{datid,global_dsm_allocated_bytes}', + proargtypes => '', proallargtypes => '{oid,int8,int8}', + proargmodes => '{o,o,o}', + proargnames => '{datid,total_bkend_mem_bytes_available,global_dsm_allocated_bytes}', prosrc =>'pg_stat_get_global_memory_allocation' }, { oid => '2022', descr => 'statistics: information about currently active backends', diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index a350f455cd..fa7c94c6c9 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -424,6 +424,13 @@ typedef struct PROC_HDR int startupBufferPinWaitBufId; /* Global dsm allocations */ pg_atomic_uint64 global_dsm_allocation; + + /* + * Max backend memory allocation tracker. Used/Initialized when + * max_total_bkend_mem > 0 as max_total_bkend_mem (MB) converted to bytes. + * Decreases/increases with free/malloc of backend memory. + */ + pg_atomic_uint64 total_bkend_mem_bytes; } PROC_HDR; extern PGDLLIMPORT PROC_HDR *ProcGlobal; diff --git a/src/include/utils/backend_status.h b/src/include/utils/backend_status.h index cbf801884d..a833941272 100644 --- a/src/include/utils/backend_status.h +++ b/src/include/utils/backend_status.h @@ -14,7 +14,7 @@ #include "datatype/timestamp.h" #include "libpq/pqcomm.h" #include "miscadmin.h" /* for BackendType */ -#include "storage/procnumber.h" +#include "storage/proc.h" #include "utils/backend_progress.h" @@ -303,6 +303,7 @@ typedef struct LocalPgBackendStatus */ extern PGDLLIMPORT bool pgstat_track_activities; extern PGDLLIMPORT int pgstat_track_activity_query_size; +extern PGDLLIMPORT int max_total_bkend_mem; /* ---------- @@ -315,6 +316,10 @@ extern PGDLLIMPORT uint64 *my_aset_allocated_bytes; extern PGDLLIMPORT uint64 *my_dsm_allocated_bytes; extern PGDLLIMPORT uint64 *my_generation_allocated_bytes; extern PGDLLIMPORT uint64 *my_slab_allocated_bytes; +extern PGDLLIMPORT uint64 allocation_allowance; +extern PGDLLIMPORT uint64 initial_allocation_allowance; +extern PGDLLIMPORT uint64 allocation_return; +extern PGDLLIMPORT uint64 allocation_return_threshold; /* ---------- @@ -363,6 +368,7 @@ extern PgBackendStatus *pgstat_get_beentry_by_proc_number(ProcNumber procNumber) extern LocalPgBackendStatus *pgstat_get_local_beentry_by_proc_number(ProcNumber procNumber); extern LocalPgBackendStatus *pgstat_get_local_beentry_by_index(int idx); extern char *pgstat_clip_activity(const char *raw_activity); +extern bool exceeds_max_total_bkend_mem(uint64 allocation_request); /* ---------- * pgstat_report_allocated_bytes_decrease() - @@ -378,7 +384,7 @@ pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, { uint64 temp; - /* Avoid allocated_bytes unsigned integer overflow on decrease */ + /* Sanity check: my allocated bytes should never drop below zero */ if (pg_sub_u64_overflow(*my_allocated_bytes, proc_allocated_bytes, &temp)) { /* On overflow, set allocated bytes and allocator type bytes to zero */ @@ -387,13 +393,35 @@ pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, *my_dsm_allocated_bytes = 0; *my_generation_allocated_bytes = 0; *my_slab_allocated_bytes = 0; + + /* Add freed memory to allocation return counter. */ + allocation_return += proc_allocated_bytes; + + /* + * Return freed memory to the global counter if return threshold is + * met. + */ + if (max_total_bkend_mem && allocation_return >= allocation_return_threshold) + { + if (ProcGlobal) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + /* Add to global tracker */ + pg_atomic_add_fetch_u64(&procglobal->total_bkend_mem_bytes, + allocation_return); + + /* Restart the count */ + allocation_return = 0; + } + } } else { - /* decrease allocation */ - *my_allocated_bytes -= proc_allocated_bytes; + /* Add freed memory to allocation return counter */ + allocation_return += proc_allocated_bytes; - /* Decrease allocator type allocated bytes. */ + /* Decrease allocator type allocated bytes */ switch (pg_allocator_type) { case PG_ALLOC_ASET: @@ -415,6 +443,30 @@ pgstat_report_allocated_bytes_decrease(int64 proc_allocated_bytes, *my_slab_allocated_bytes -= proc_allocated_bytes; break; } + + /* decrease allocation */ + *my_allocated_bytes = *my_aset_allocated_bytes + + *my_dsm_allocated_bytes + *my_generation_allocated_bytes + + *my_slab_allocated_bytes; + + /* + * Return freed memory to the global counter if return threshold is + * met. + */ + if (max_total_bkend_mem && allocation_return >= allocation_return_threshold) + { + if (ProcGlobal) + { + volatile PROC_HDR *procglobal = ProcGlobal; + + /* Add to global tracker */ + pg_atomic_add_fetch_u64(&procglobal->total_bkend_mem_bytes, + allocation_return); + + /* Restart the count */ + allocation_return = 0; + } + } } return; @@ -432,7 +484,13 @@ static inline void pgstat_report_allocated_bytes_increase(int64 proc_allocated_bytes, int pg_allocator_type) { - *my_allocated_bytes += proc_allocated_bytes; + uint64 temp; + + /* Sanity check: my allocated bytes should never drop below zero */ + if (pg_sub_u64_overflow(allocation_allowance, proc_allocated_bytes, &temp)) + allocation_allowance = 0; + else + allocation_allowance -= proc_allocated_bytes; /* Increase allocator type allocated bytes */ switch (pg_allocator_type) @@ -457,6 +515,9 @@ pgstat_report_allocated_bytes_increase(int64 proc_allocated_bytes, break; } + *my_allocated_bytes = *my_aset_allocated_bytes + *my_dsm_allocated_bytes + + *my_generation_allocated_bytes + *my_slab_allocated_bytes; + return; } @@ -476,6 +537,36 @@ pgstat_init_allocated_bytes(void) *my_generation_allocated_bytes = 0; *my_slab_allocated_bytes = 0; + /* If we're limiting backend memory */ + if (max_total_bkend_mem) + { + volatile PROC_HDR *procglobal = ProcGlobal; + uint64 available_max_total_bkend_mem = 0; + + allocation_return = 0; + allocation_allowance = 0; + + /* Account for the initial allocation allowance */ + while ((available_max_total_bkend_mem = pg_atomic_read_u64(&procglobal->total_bkend_mem_bytes)) >= initial_allocation_allowance) + { + /* + * On success populate allocation_allowance. Failure here will + * result in the backend's first invocation of + * exceeds_max_total_bkend_mem allocating requested, default, or + * available memory or result in an out of memory error. + */ + if (pg_atomic_compare_exchange_u64(&procglobal->total_bkend_mem_bytes, + &available_max_total_bkend_mem, + available_max_total_bkend_mem - + initial_allocation_allowance)) + { + allocation_allowance = initial_allocation_allowance; + + break; + } + } + } + return; } diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 2f62f5e4ea..01dee8ddea 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1887,13 +1887,15 @@ pg_stat_global_memory_allocation| WITH sums AS ( SELECT s.datid, current_setting('shared_memory_size'::text, true) AS shared_memory_size, (current_setting('shared_memory_size_in_huge_pages'::text, true))::integer AS shared_memory_size_in_huge_pages, + pg_size_bytes(current_setting('max_total_backend_memory'::text, true)) AS max_total_backend_memory_bytes, + s.total_bkend_mem_bytes_available, s.global_dsm_allocated_bytes, sums.total_aset_allocated_bytes, sums.total_dsm_allocated_bytes, sums.total_generation_allocated_bytes, sums.total_slab_allocated_bytes FROM sums, - (pg_stat_get_global_memory_allocation() s(datid, global_dsm_allocated_bytes) + (pg_stat_get_global_memory_allocation() s(datid, total_bkend_mem_bytes_available, global_dsm_allocated_bytes) LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_gssapi| SELECT pid, gss_auth AS gss_authenticated, -- 2.43.2 ^ permalink raw reply [nested|flat] 281+ messages in thread
* Re: Add the ability to limit the amount of memory that can be allocated to backends. @ 2024-03-15 07:00 Alexander Lakhin <[email protected]> parent: Anton A. Melnikov <[email protected]> 0 siblings, 0 replies; 281+ messages in thread From: Alexander Lakhin @ 2024-03-15 07:00 UTC (permalink / raw) To: Anton A. Melnikov <[email protected]>; Aleksander Alekseev <[email protected]>; [email protected] <[email protected]>; +Cc: Tomas Vondra <[email protected]>; Andres Freund <[email protected]>; Andrei Lepikhov <[email protected]>; Stephen Frost <[email protected]>; [email protected]; Arne Roland <[email protected]>; vignesh C <[email protected]>; Justin Pryzby <[email protected]>; Ibrar Ahmed <[email protected]>; stephen.frost <[email protected]> Hello Anton, 14.03.2024 23:36, Anton A. Melnikov wrote: > On 13.03.2024 10:41, Anton A. Melnikov wrote: > >> Here is a version updated for the current master. >> > > During patch updating i mistakenly added double counting of deallocatated blocks. > That's why the tests in the patch tester failed. > Fixed it and squashed fix 0002 with 0001. > Here is fixed version. Please try the following with the patches applied: echo "shared_buffers = '1MB' max_total_backend_memory = '10MB'" > /tmp/extra.config CPPFLAGS="-Og" ./configure --enable-tap-tests --enable-debug --enable-cassert ... TEMP_CONFIG=/tmp/extra.config make check It fails for me as follows: ... # postmaster did not respond within 60 seconds, examine ".../src/test/regress/log/postmaster.log" for the reason ... src/test/regress/log/postmaster.log contains: ... TRAP: failed Assert("ret != NULL"), File: "mcxt.c", Line: 1327, PID: 4109270 TRAP: failed Assert("ret != NULL"), File: "mcxt.c", Line: 1327, PID: 4109271 postgres: autovacuum launcher (ExceptionalCondition+0x69)[0x55ce441fcc6e] postgres: autovacuum launcher (palloc0+0x0)[0x55ce4422eb67] postgres: logical replication launcher (ExceptionalCondition+0x69)[0x55ce441fcc6e] postgres: autovacuum launcher (InitDeadLockChecking+0xa6)[0x55ce4408a6f0] postgres: logical replication launcher (palloc0+0x0)[0x55ce4422eb67] postgres: logical replication launcher (InitDeadLockChecking+0x45)[0x55ce4408a68f] postgres: autovacuum launcher (InitProcess+0x600)[0x55ce4409c6f2] postgres: logical replication launcher (InitProcess+0x600)[0x55ce4409c6f2] postgres: autovacuum launcher (+0x44b4e2)[0x55ce43ff24e2] ... grep TRAP src/test/regress/log/postmaster.log | wc -l 445 Best regards, Alexander ^ permalink raw reply [nested|flat] 281+ messages in thread
end of thread, other threads:[~2024-03-15 07:00 UTC | newest] Thread overview: 281+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2018-11-07 07:53 [PATCH 3/5] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2018-11-07 07:53 [PATCH v24 3/5] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v35 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v32 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v33 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v33 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v34 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v29 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v30 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v31 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v39 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v41 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v42 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v37 3/6] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v43 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v44 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v25 4/8] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v38 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v40 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v36 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]> 2024-01-23 11:47 Re: Add the ability to limit the amount of memory that can be allocated to backends. Anton A. Melnikov <[email protected]> 2024-01-28 19:11 ` Re: Add the ability to limit the amount of memory that can be allocated to backends. Tomas Vondra <[email protected]> 2024-03-12 13:30 ` Re: Add the ability to limit the amount of memory that can be allocated to backends. Aleksander Alekseev <[email protected]> 2024-03-13 07:41 ` Re: Add the ability to limit the amount of memory that can be allocated to backends. Anton A. Melnikov <[email protected]> 2024-03-14 20:36 ` Re: Add the ability to limit the amount of memory that can be allocated to backends. Anton A. Melnikov <[email protected]> 2024-03-15 07:00 ` Re: Add the ability to limit the amount of memory that can be allocated to backends. Alexander Lakhin <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox