public inbox for [email protected]
help / color / mirror / Atom feed[PATCH v24 3/5] Make archiver process an auxiliary process
287+ messages / 8 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ 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; 287+ 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] 287+ messages in thread
* stats.sql might fail due to shared buffers also used by parallel tests
@ 2025-01-06 07:00 Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
0 siblings, 1 reply; 287+ messages in thread
From: Alexander Lakhin @ 2025-01-06 07:00 UTC (permalink / raw)
To: pgsql-hackers; +Cc: Andres Freund <[email protected]>; Melanie Plageman <[email protected]>
Hello hackers,
I'd like to share my investigation of one mysterious stats.sql failure
occurred in December: [1].
The difference of the failure is:
--- C:/prog/bf/root/HEAD/pgsql/src/test/regress/expected/stats.out 2024-09-18 19:31:14.665516500 +0000
+++ C:/prog/bf/root/HEAD/pgsql.build/testrun/recovery/027_stream_regress/data/results/stats.out 2024-12-17
09:57:08.944588500 +0000
@@ -1291,7 +1291,7 @@
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 ?column?
 ----------
- t
+ f
 (1 row)
027_stream_regress_primary.log contains:
2024-12-17 09:57:06.778 UTC [8568:109] pg_regress/stats LOG: statement: SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
     FROM pg_stat_io
     WHERE object = 'relation'
2024-12-17 09:57:06.779 UTC [8568:110] pg_regress/stats LOG: statement: CREATE TABLE test_io_shared(a int);
2024-12-17 09:57:06.780 UTC [8568:111] pg_regress/stats LOG: statement: INSERT INTO test_io_shared SELECT i FROM
generate_series(1,100)i;
...
2024-12-17 09:57:06.782 UTC [8568:115] pg_regress/stats LOG: statement: CHECKPOINT;
2024-12-17 09:57:06.794 UTC [3664:40] LOG:Â checkpoint starting: immediate force wait
2024-12-17 09:57:06.856 UTC [3664:41] LOG:Â checkpoint complete: wrote 0 buffers (0.0%), wrote 1 SLRU buffers; 0 WAL
file(s) added, 0 removed, 0 recycled; write=0.001 s, sync=0.001 s, total=0.062 s; sync files=0, longest=0.000 s,
average=0.000 s; distance=1875 kB, estimate=52682 kB; lsn=0/14A2F410, redo lsn=0/14A2F3B8
2024-12-17 09:57:06.857 UTC [8568:116] pg_regress/stats LOG: statement: CHECKPOINT;
2024-12-17 09:57:06.857 UTC [3664:42] LOG:Â checkpoint starting: immediate force wait
2024-12-17 09:57:06.859 UTC [3664:43] LOG:Â checkpoint complete: wrote 0 buffers (0.0%), wrote 0 SLRU buffers; 0 WAL
file(s) added, 0 removed, 0 recycled; write=0.001 s, sync=0.001 s, total=0.002 s; sync files=0, longest=0.000 s,
average=0.000 s; distance=0 kB, estimate=47414 kB; lsn=0/14A2F4E0, redo lsn=0/14A2F488
2024-12-17 09:57:06.859 UTC [8568:117] pg_regress/stats LOG: statement: SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
     FROM pg_stat_io
     WHERE object = 'relation'
2024-12-17 09:57:06.860 UTC [8568:118] pg_regress/stats LOG: statement: SELECT 77693 > 77693;
The corresponding test case (added by 10a082bf7, dated 2023-02-11) is:
SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 FROM pg_stat_io
 WHERE object = 'relation' \gset io_sum_shared_before_
...
CREATE TABLE test_io_shared(a int);
INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
...
CHECKPOINT;
CHECKPOINT;
...
SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 FROM pg_stat_get_backend_io(pg_backend_pid())
 WHERE object = 'relation' \gset my_io_sum_shared_after_
SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
So, as we can see from the log above, both checkpoints wrote 0 buffers,
moreover, no other process/backend wrote any buffers.
After series of experiments, I found that this situation is possible when
other backend steals shared buffers from checkpointer, without making new
buffers dirty, and then delays flushing it's statistics.
Please find attached a reproducer for this issue: I've added two sleeps
to stats.sql and reduced parallel_schedule, but I believe it's a legal
change, which doesn't affect the test case essentially.
With bufchurn.sql running concurrently. and TEMP_CONFIG containing
shared_buffers = 1MB (as in the 027_stream_regress test in question), I can
see exactly the same failure:
$ echo 'shared_buffers = 1MB' >/tmp/extra.config; TEMP_CONFIG=/tmp/extra.config make -s check
# +++ regress check in src/test/regress +++
# initializing database system by copying initdb template
# using temp instance on port 65312 with PID 129700
ok 1        - test_setup                               356 ms
ok 2        - create_index                            1002 ms
# parallel group (2 tests):Â stats bufchurn
not ok 3    + stats                                  21176 ms
...
diff -U3 .../src/test/regress/expected/stats.out .../src/test/regress/results/stats.out
--- .../src/test/regress/expected/stats.out 2025-01-06 08:03:07.720275980 +0200
+++ .../src/test/regress/results/stats.out  2025-01-06 08:15:34.602170721 +0200
@@ -1321,7 +1321,7 @@
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 ?column?
 ----------
- t
+ f
 (1 row)
...
[1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=drongo&dt=2024-12-17%2008%3A59%3A44
Best regards,
Alexander
Attachments:
[text/x-patch] stats-bufs-write-repro.patch (8.8K, ../../[email protected]/2-stats-bufs-write-repro.patch)
download | inline diff:
diff --git a/src/test/regress/expected/bufchurn.out b/src/test/regress/expected/bufchurn.out
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index a0317b7208..651898b9f4 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -834,6 +834,12 @@ SELECT num_requested AS rqst_ckpts_before FROM pg_stat_checkpointer \gset
SELECT wal_bytes AS wal_bytes_before FROM pg_stat_wal \gset
CREATE TEMP TABLE test_stats_temp AS SELECT 17;
DROP TABLE test_stats_temp;
+SELECT pg_sleep(10);
+ pg_sleep
+----------
+
+(1 row)
+
-- Checkpoint twice: The checkpointer reports stats after reporting completion
-- of the checkpoint. But after a second checkpoint we'll see at least the
-- results of the first.
@@ -1298,6 +1304,12 @@ SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
t
(1 row)
+SELECT pg_sleep(10);
+ pg_sleep
+----------
+
+(1 row)
+
-- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
-- and fsyncs in the global stats (usually not for the backend).
-- See comment above for rationale for two explicit CHECKPOINTs.
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index 1edd9e45eb..2142842a31 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -1,138 +1,4 @@
-# ----------
-# src/test/regress/parallel_schedule
-#
-# Most test scripts can be run after running just test_setup and possibly
-# create_index. Exceptions to this rule are documented below.
-#
-# By convention, we put no more than twenty tests in any one parallel group;
-# this limits the number of connections needed to run the tests.
-# ----------
-
-# required setup steps
test: test_setup
-
-# ----------
-# The first group of parallel tests
-# ----------
-test: boolean char name varchar text int2 int4 int8 oid float4 float8 bit numeric txid uuid enum money rangetypes pg_lsn regproc
-
-# ----------
-# The second group of parallel tests
-# multirangetypes depends on rangetypes
-# multirangetypes shouldn't run concurrently with type_sanity
-# ----------
-test: strings md5 numerology point lseg line box path polygon circle date time timetz timestamp timestamptz interval inet macaddr macaddr8 multirangetypes
-
-# ----------
-# Another group of parallel tests
-# geometry depends on point, lseg, line, box, path, polygon, circle
-# horology depends on date, time, timetz, timestamp, timestamptz, interval
-# ----------
-test: geometry horology tstypes regex type_sanity opr_sanity misc_sanity comments expressions unicode xid mvcc database stats_import
-
-# ----------
-# Load huge amounts of data
-# We should split the data files into single files and then
-# execute two copy tests in parallel, to check that copy itself
-# is concurrent safe.
-# ----------
-test: copy copyselect copydml copyencoding insert insert_conflict
-
-# ----------
-# More groups of parallel tests
-# Note: many of the tests in later groups depend on create_index
-# ----------
-test: create_function_c create_misc create_operator create_procedure create_table create_type create_schema
-test: create_index create_index_spgist create_view index_including index_including_gist
-
-# ----------
-# Another group of parallel tests
-# ----------
-test: create_aggregate create_function_sql create_cast constraints triggers select inherit typed_table vacuum drop_if_exists updatable_views roleattributes create_am hash_func errors infinite_recurse
-
-# ----------
-# sanity_check does a vacuum, affecting the sort order of SELECT *
-# results. So it should not run parallel to other tests.
-# ----------
-test: sanity_check
-
-# ----------
-# Another group of parallel tests
-# aggregates depends on create_aggregate
-# join depends on create_misc
-# ----------
-test: select_into select_distinct select_distinct_on select_implicit select_having subselect union case join aggregates transactions random portals arrays btree_index hash_index update delete namespace prepared_xacts
-
-# ----------
-# Another group of parallel tests
-# ----------
-test: brin gin gist spgist privileges init_privs security_label collate matview lock replica_identity rowsecurity object_address tablesample groupingsets drop_operator password identity generated_stored join_hash
-
-# ----------
-# Additional BRIN tests
-# ----------
-test: brin_bloom brin_multi
-
-# ----------
-# Another group of parallel tests
-# psql depends on create_am
-# amutils depends on geometry, create_index_spgist, hash_index, brin
-# ----------
-test: create_table_like alter_generic alter_operator misc async dbsize merge misc_functions sysviews tsrf tid tidscan tidrangescan collate.utf8 collate.icu.utf8 incremental_sort create_role without_overlaps
-
-# collate.linux.utf8 and collate.icu.utf8 tests cannot be run in parallel with each other
-test: rules psql psql_crosstab amutils stats_ext collate.linux.utf8 collate.windows.win1252
-
-# ----------
-# Run these alone so they don't run out of parallel workers
-# select_parallel depends on create_misc
-# ----------
-test: select_parallel
-test: write_parallel
-test: vacuum_parallel
-
-# no relation related tests can be put in this group
-test: publication subscription
-
-# ----------
-# Another group of parallel tests
-# select_views depends on create_view
-# ----------
-test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock indirect_toast equivclass
-
-# ----------
-# Another group of parallel tests (JSON related)
-# ----------
-test: json jsonb json_encoding jsonpath jsonpath_encoding jsonb_jsonpath sqljson sqljson_queryfuncs sqljson_jsontable
-
-# ----------
-# Another group of parallel tests
-# with depends on create_misc
-# NB: temp.sql does a reconnect which transiently uses 2 connections,
-# so keep this parallel group to at most 19 tests
-# ----------
-test: plancache limit plpgsql copy2 temp domain rangefuncs prepare conversion truncate alter_table sequence polymorphism rowtypes returning largeobject with xml
-
-# ----------
-# Another group of parallel tests
-#
-# The stats test resets stats, so nothing else needing stats access can be in
-# this group.
-# ----------
-test: partition_join partition_prune reloptions hash_part indexing partition_aggregate partition_info tuplesort explain compression memoize stats predicate
-
-# event_trigger depends on create_am and cannot run concurrently with
-# any test that runs DDL
-# oidjoins is read-only, though, and should run late for best coverage
-test: oidjoins event_trigger
-
-# event_trigger_login cannot run concurrently with any other tests because
-# on-login event handling could catch connection of a concurrent test.
-test: event_trigger_login
-
-# this test also uses event triggers, so likewise run it by itself
-test: fast_default
-
-# run tablespace test at the end because it drops the tablespace created during
-# setup that other tests may use.
-test: tablespace
+test: create_index
+test: stats bufchurn
+# test: ministats bufchurn
diff --git a/src/test/regress/sql/bufchurn.sql b/src/test/regress/sql/bufchurn.sql
new file mode 100644
index 0000000000..c29ac4acf9
--- /dev/null
+++ b/src/test/regress/sql/bufchurn.sql
@@ -0,0 +1,22 @@
+SELECT pg_sleep(2);
+CREATE TABLE t0(i int, t text);
+ALTER TABLE t0 ALTER t SET STORAGE PLAIN;
+INSERT INTO t0 SELECT g, g || repeat('x', 8000) FROM generate_series(1, 256) g;
+
+CREATE TABLE t1(i int, t text);
+ALTER TABLE tl ALTER t SET STORAGE PLAIN;
+INSERT INTO t1 SELECT g, g || repeat('x', 8000) FROM generate_series(1, 256) g;
+
+EXPLAIN ANALYZE SELECT SUM(i) FROM t0 GROUP BY t;
+EXPLAIN ANALYZE SELECT SUM(i) FROM t1 GROUP BY t;
+
+\c -
+SELECT 'SELECT pg_sleep(1);' FROM generate_series(1, 10)
+\gexec
+
+BEGIN;
+SELECT 'EXPLAIN ANALYZE SELECT SUM(i) FROM t0; EXPLAIN ANALYZE SELECT SUM(i) FROM t1;' FROM generate_series(1, 20)
+\gexec
+
+SELECT pg_sleep(10);
+ROLLBACK;
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 399c72bbcf..fcec1be377 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -426,6 +426,7 @@ SELECT wal_bytes AS wal_bytes_before FROM pg_stat_wal \gset
CREATE TEMP TABLE test_stats_temp AS SELECT 17;
DROP TABLE test_stats_temp;
+SELECT pg_sleep(10);
-- Checkpoint twice: The checkpointer reports stats after reporting completion
-- of the checkpoint. But after a second checkpoint we'll see at least the
-- results of the first.
@@ -632,6 +633,7 @@ SELECT sum(extends) AS my_io_sum_shared_after_extends
WHERE context = 'normal' AND object = 'relation' \gset
SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+SELECT pg_sleep(10);
-- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
-- and fsyncs in the global stats (usually not for the backend).
-- See comment above for rationale for two explicit CHECKPOINTs.
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-03 06:54 ` Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
0 siblings, 1 reply; 287+ messages in thread
From: Shlok Kyal @ 2025-07-03 06:54 UTC (permalink / raw)
To: Alexander Lakhin <[email protected]>; +Cc: pgsql-hackers; Andres Freund <[email protected]>; Melanie Plageman <[email protected]>
On Mon, 6 Jan 2025 at 12:30, Alexander Lakhin <[email protected]> wrote:
>
> Hello hackers,
>
> I'd like to share my investigation of one mysterious stats.sql failure
> occurred in December: [1].
> The difference of the failure is:
> --- C:/prog/bf/root/HEAD/pgsql/src/test/regress/expected/stats.out 2024-09-18 19:31:14.665516500 +0000
> +++ C:/prog/bf/root/HEAD/pgsql.build/testrun/recovery/027_stream_regress/data/results/stats.out 2024-12-17
> 09:57:08.944588500 +0000
> @@ -1291,7 +1291,7 @@
> SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
> ?column?
> ----------
> - t
> + f
> (1 row)
>
> 027_stream_regress_primary.log contains:
> 2024-12-17 09:57:06.778 UTC [8568:109] pg_regress/stats LOG: statement: SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
> FROM pg_stat_io
> WHERE object = 'relation'
> 2024-12-17 09:57:06.779 UTC [8568:110] pg_regress/stats LOG: statement: CREATE TABLE test_io_shared(a int);
> 2024-12-17 09:57:06.780 UTC [8568:111] pg_regress/stats LOG: statement: INSERT INTO test_io_shared SELECT i FROM
> generate_series(1,100)i;
> ...
> 2024-12-17 09:57:06.782 UTC [8568:115] pg_regress/stats LOG: statement: CHECKPOINT;
> 2024-12-17 09:57:06.794 UTC [3664:40] LOG: checkpoint starting: immediate force wait
> 2024-12-17 09:57:06.856 UTC [3664:41] LOG: checkpoint complete: wrote 0 buffers (0.0%), wrote 1 SLRU buffers; 0 WAL
> file(s) added, 0 removed, 0 recycled; write=0.001 s, sync=0.001 s, total=0.062 s; sync files=0, longest=0.000 s,
> average=0.000 s; distance=1875 kB, estimate=52682 kB; lsn=0/14A2F410, redo lsn=0/14A2F3B8
> 2024-12-17 09:57:06.857 UTC [8568:116] pg_regress/stats LOG: statement: CHECKPOINT;
> 2024-12-17 09:57:06.857 UTC [3664:42] LOG: checkpoint starting: immediate force wait
> 2024-12-17 09:57:06.859 UTC [3664:43] LOG: checkpoint complete: wrote 0 buffers (0.0%), wrote 0 SLRU buffers; 0 WAL
> file(s) added, 0 removed, 0 recycled; write=0.001 s, sync=0.001 s, total=0.002 s; sync files=0, longest=0.000 s,
> average=0.000 s; distance=0 kB, estimate=47414 kB; lsn=0/14A2F4E0, redo lsn=0/14A2F488
> 2024-12-17 09:57:06.859 UTC [8568:117] pg_regress/stats LOG: statement: SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
> FROM pg_stat_io
> WHERE object = 'relation'
> 2024-12-17 09:57:06.860 UTC [8568:118] pg_regress/stats LOG: statement: SELECT 77693 > 77693;
>
> The corresponding test case (added by 10a082bf7, dated 2023-02-11) is:
> SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
> FROM pg_stat_io
> WHERE object = 'relation' \gset io_sum_shared_before_
> ...
> CREATE TABLE test_io_shared(a int);
> INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
> ...
> CHECKPOINT;
> CHECKPOINT;
> ...
> SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
> FROM pg_stat_get_backend_io(pg_backend_pid())
> WHERE object = 'relation' \gset my_io_sum_shared_after_
> SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
>
> So, as we can see from the log above, both checkpoints wrote 0 buffers,
> moreover, no other process/backend wrote any buffers.
>
> After series of experiments, I found that this situation is possible when
> other backend steals shared buffers from checkpointer, without making new
> buffers dirty, and then delays flushing it's statistics.
>
> Please find attached a reproducer for this issue: I've added two sleeps
> to stats.sql and reduced parallel_schedule, but I believe it's a legal
> change, which doesn't affect the test case essentially.
>
> With bufchurn.sql running concurrently. and TEMP_CONFIG containing
> shared_buffers = 1MB (as in the 027_stream_regress test in question), I can
> see exactly the same failure:
> $ echo 'shared_buffers = 1MB' >/tmp/extra.config; TEMP_CONFIG=/tmp/extra.config make -s check
> # +++ regress check in src/test/regress +++
> # initializing database system by copying initdb template
> # using temp instance on port 65312 with PID 129700
> ok 1 - test_setup 356 ms
> ok 2 - create_index 1002 ms
> # parallel group (2 tests): stats bufchurn
> not ok 3 + stats 21176 ms
> ...
>
> diff -U3 .../src/test/regress/expected/stats.out .../src/test/regress/results/stats.out
> --- .../src/test/regress/expected/stats.out 2025-01-06 08:03:07.720275980 +0200
> +++ .../src/test/regress/results/stats.out 2025-01-06 08:15:34.602170721 +0200
> @@ -1321,7 +1321,7 @@
> SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
> ?column?
> ----------
> - t
> + f
> (1 row)
> ...
>
> [1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=drongo&dt=2024-12-17%2008%3A59%3A44
>
Hi Hackers,
I have also encountered a similar buildfarm failure [1].
| 1/1 + subscription 142 ms FAIL
1/1 postgresql:regress / regress/regress ERROR 284.85s exit status 1
diff --strip-trailing-cr -U3
c:/build-farm-local/buildroot/HEAD/pgsql/src/test/regress/expected/subscription.out
c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/regress/regress/results/subscription.out
--- c:/build-farm-local/buildroot/HEAD/pgsql/src/test/regress/expected/subscription.out
2025-06-28 20:13:02 +0900
+++ c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/regress/regress/results/subscription.out
2025-06-28 20:35:21 +0900
@@ -70,7 +70,7 @@
SELECT :'prev_stats_reset' < stats_reset FROM
pg_stat_subscription_stats WHERE subname = 'regress_testsub';
?column?
----------
- t
+ f
(1 row)
logs around this statement do not show unexpected thing:
2025-06-28 20:35:20.857 JST client backend[6092]
pg_regress/subscription STATEMENT: CREATE SUBSCRIPTION
regress_testsub CONNECTION 'testconn' PUBLICATION testpub;
2025-06-28 20:35:20.857 JST client backend[6092]
pg_regress/subscription ERROR: publication name "foo" used more than
once
2025-06-28 20:35:20.857 JST client backend[6092]
pg_regress/subscription STATEMENT: CREATE SUBSCRIPTION
regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION
foo, testpub, foo WITH (connect = false);
2025-06-28 20:35:20.858 JST client backend[6092]
pg_regress/subscription WARNING: subscription was created, but is not
connected
2025-06-28 20:35:20.858 JST client backend[6092]
pg_regress/subscription HINT: To initiate replication, you must
manually create the replication slot, enable the subscription, and
refresh the subscription.
2025-06-28 20:35:20.861 JST client backend[6092]
pg_regress/subscription ERROR: subscription "regress_testsub" already
exists
In subscription.sql, I looked at the test. The statement are like:
-- Reset the stats again and check if the new reset_stats is updated.
SELECT stats_reset as prev_stats_reset FROM pg_stat_subscription_stats
WHERE subname = 'regress_testsub' \gset
SELECT pg_stat_reset_subscription_stats(oid) FROM pg_subscription
WHERE subname = 'regress_testsub';
SELECT :'prev_stats_reset' < stats_reset FROM
pg_stat_subscription_stats WHERE subname = 'regress_testsub';
So according to me, I suspect the following causes
1) The time difference between 'prev_stats_reset' and current
'stats_reset' value is less than 1 microseconds.
'stats_reset' is of type 'timestamp with time zone' and the content of
it is like: '2025-06-30 21:01:07.925253+05:30'. So if the time
difference between 'prev_stats_reset' and current 'stats_reset' is
less than 1 microseconds. The query 'SELECT :'prev_stats_reset' <
stats_reset FROM pg_stat_subscription_stats WHERE subname =
'regress_testsub'' might return 'false' instead of 'true'.
But I was not able to reproduce such a scenario after multiple
testing. Even in high end machines, it takes at least a few
microseconds. Also there are multiple cases where we did similar
timestamp comparison in 'stats.sql' as well. And, I didn't find any
other failure related to such case. So, I feel this is not possible.
2) pg_stat_reset_subscription_stats(oid) function did not reset the stats.
We have a shared hash 'pgStatLocal.shared_hash'. If the entry
reference (for the subscription) is not found while executing
'pg_stat_reset_subscription_stats(oid)'. It may not be able to reset
the stats. Maybe somehow this shared hash is getting dropped..
Also, it could be failing due to the same reason as Alexander has
reproduced in another case [2].
[1]: https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=hamerkop&dt=2025-06-28%2011%3A02%3A30
[2]: https://www.postgresql.org/message-id/fe0391a8-dfa9-41c3-bf1c-7ea058e40f30%40gmail.com
Thanks and Regards,
Shlok Kyal
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
@ 2025-07-04 20:00 ` Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
0 siblings, 1 reply; 287+ messages in thread
From: Alexander Lakhin @ 2025-07-04 20:00 UTC (permalink / raw)
To: Shlok Kyal <[email protected]>; +Cc: pgsql-hackers; Andres Freund <[email protected]>; Melanie Plageman <[email protected]>
Hello Shlok,
03.07.2025 09:54, Shlok Kyal wrote:
> I have also encountered a similar buildfarm failure [1].
>
> | 1/1 + subscription 142 ms FAIL
> 1/1 postgresql:regress / regress/regress ERROR 284.85s exit status 1
>
> diff --strip-trailing-cr -U3
> c:/build-farm-local/buildroot/HEAD/pgsql/src/test/regress/expected/subscription.out
> c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/regress/regress/results/subscription.out
> --- c:/build-farm-local/buildroot/HEAD/pgsql/src/test/regress/expected/subscription.out
> 2025-06-28 20:13:02 +0900
> +++ c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/regress/regress/results/subscription.out
> 2025-06-28 20:35:21 +0900
> @@ -70,7 +70,7 @@
> SELECT :'prev_stats_reset' < stats_reset FROM
> pg_stat_subscription_stats WHERE subname = 'regress_testsub';
> ?column?
> ----------
> - t
> + f
> (1 row)
Thank you for your attention to this! Yes, I also noticed that failure,
but could not reproduce it yet.
> So according to me, I suspect the following causes
> 1) The time difference between 'prev_stats_reset' and current
> 'stats_reset' value is less than 1 microseconds.
> 'stats_reset' is of type 'timestamp with time zone' and the content of
> it is like: '2025-06-30 21:01:07.925253+05:30'. So if the time
> difference between 'prev_stats_reset' and current 'stats_reset' is
> less than 1 microseconds. The query 'SELECT :'prev_stats_reset' <
> stats_reset FROM pg_stat_subscription_stats WHERE subname =
> 'regress_testsub'' might return 'false' instead of 'true'.
> But I was not able to reproduce such a scenario after multiple
> testing. Even in high end machines, it takes at least a few
> microseconds. Also there are multiple cases where we did similar
> timestamp comparison in 'stats.sql' as well. And, I didn't find any
> other failure related to such case. So, I feel this is not possible.
Did you try that on Windows (hamerkop is a Windows animal)? IIUC,
GetCurrentTimestamp() -> gettimeofday() implemented on Windows via
GetSystemTimePreciseAsFileTime(), and it has 100ns resolution,
according to [1].
I tried it on a Windows VM and saw the following numbers:
SELECT :'prev_stats_reset' < stats_reset, :'prev_stats_reset', stats_reset FROM pg_stat_subscription_stats WHERE subname
= 'regress_testsub';
 ?column? |             ?column?              | stats_reset
----------+-------------------------------------+-------------------------------------
 t       | Fri Jul 04 11:46:10.224323 2025 PDT | Fri Jul 04 11:46:10.224975 2025 PDT
 (1 row)
that is, the difference is about 600 ns — if I could make the VM 6x faster
or run the test on a bare metal, maybe I'd get the test failed.
Although the overall duration of the subscription doesn't differ much:
My VM:
# parallel group (2 tests):Â subscription publication
ok 164      + publication                              806 ms
ok 165      + subscription                             210 ms
vs
hamerkop:
# parallel group (2 tests):Â subscription publication
ok 164      + publication                             2383 ms
not ok 165  + subscription                             142 ms
So probably the failure is caused by something else.
> 2) pg_stat_reset_subscription_stats(oid) function did not reset the stats.
> We have a shared hash 'pgStatLocal.shared_hash'. If the entry
> reference (for the subscription) is not found while executing
> 'pg_stat_reset_subscription_stats(oid)'. It may not be able to reset
> the stats. Maybe somehow this shared hash is getting dropped..
> Also, it could be failing due to the same reason as Alexander has
I don't think 2) is relevant here, because shared buffers shouldn't affect
subscription's statistics.
[1] https://stackoverflow.com/questions/4444090/measuring-time-with-a-resolution-of-microseconds-in-c
Best regards.
Alexander
^ permalink raw reply [nested|flat] 287+ messages in thread
* RE: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-15 07:33 ` Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
0 siblings, 1 reply; 287+ messages in thread
From: Hayato Kuroda (Fujitsu) @ 2025-07-15 07:33 UTC (permalink / raw)
To: 'Alexander Lakhin' <[email protected]>; Shlok Kyal <[email protected]>; +Cc: pgsql-hackers; Andres Freund <[email protected]>; Melanie Plageman <[email protected]>
Dear Alexander,
> > So according to me, I suspect the following causes
> > 1) The time difference between 'prev_stats_reset' and current
> > 'stats_reset' value is less than 1 microseconds.
> > 'stats_reset' is of type 'timestamp with time zone' and the content of
> > it is like: '2025-06-30 21:01:07.925253+05:30'. So if the time
> > difference between 'prev_stats_reset' and current 'stats_reset' is
> > less than 1 microseconds. The query 'SELECT :'prev_stats_reset' <
> > stats_reset FROM pg_stat_subscription_stats WHERE subname =
> > 'regress_testsub'' might return 'false' instead of 'true'.
> > But I was not able to reproduce such a scenario after multiple
> > testing. Even in high end machines, it takes at least a few
> > microseconds. Also there are multiple cases where we did similar
> > timestamp comparison in 'stats.sql' as well. And, I didn't find any
> > other failure related to such case. So, I feel this is not possible.
>
> Did you try that on Windows (hamerkop is a Windows animal)? IIUC,
> GetCurrentTimestamp() -> gettimeofday() implemented on Windows via
> GetSystemTimePreciseAsFileTime(), and it has 100ns resolution,
Hmm. I'm not familiar with the Windows environment, but I have the doubt for it.
GetSystemTimePreciseAsFileTime() returns FILETIME structure, which represents the
time UTC with 100-nanosecod intervals [1]. The stack overflow seemed to refer it.
However, the document for GetSystemTimePreciseAsFileTime() says that the
resolution is < 1 us [2]. Also, MS doc [3] does not say that
GetSystemTimePreciseAsFileTime() returns value monotonically.
Another API QueryPerformanceCounter() seems to have the monotony.
A bit old document [4] also raised the possibility:
```
Consecutive calls may return the same result. The call time is less than the
smallest increment of the system time. The granularity is in the sub-microsecond
regime. The function may be used for time measurements but some care has to be
taken: Time differences may be ZERO.
```
Also, what if the the system clock is modified during the test via NTP?
> > 2) pg_stat_reset_subscription_stats(oid) function did not reset the stats.
> > We have a shared hash 'pgStatLocal.shared_hash'. If the entry
> > reference (for the subscription) is not found while executing
> > 'pg_stat_reset_subscription_stats(oid)'. It may not be able to reset
> > the stats. Maybe somehow this shared hash is getting dropped..
> > Also, it could be failing due to the same reason as Alexander has
>
> I don't think 2) is relevant here, because shared buffers shouldn't affect
> subscription's statistics.
To confirm; we do not consider the possibility that pgstat_get_entry_ref() returns
NULL right?
[1]: https://learn.microsoft.com/en-us/windows/win32/api/minwinbase/ns-minwinbase-filetime
[2]: https://learn.microsoft.com/en-us/windows/win32/api/sysinfoapi/nf-sysinfoapi-getsystemtimepreciseasf...
[3]: https://learn.microsoft.com/en-us/windows/win32/sysinfo/acquiring-high-resolution-time-stamps
[4]: http://www.windowstimestamp.com/description#:~:text=2.1.4.2.%C2%A0%C2%A0Desktop%20Applications%3A%20...)
Best regards,
Hayato Kuroda
FUJITSU LIMITED
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
@ 2025-07-20 08:00 ` Alexander Lakhin <[email protected]>
2025-07-23 00:55 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Yugo Nagata <[email protected]>
2025-07-23 04:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 05:48 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests TAKATSUKA Haruka <[email protected]>
0 siblings, 3 replies; 287+ messages in thread
From: Alexander Lakhin @ 2025-07-20 08:00 UTC (permalink / raw)
To: Hayato Kuroda (Fujitsu) <[email protected]>; Yugo Nagata <[email protected]>; +Cc: pgsql-hackers; Shlok Kyal <[email protected]>
Hello Kuroda-san,
Thank you for your attention to this!
15.07.2025 10:33, Hayato Kuroda (Fujitsu) wrote:
> GetSystemTimePreciseAsFileTime() returns FILETIME structure, which represents the
> time UTC with 100-nanosecod intervals [1]. The stack overflow seemed to refer it.
> However, the document for GetSystemTimePreciseAsFileTime() says that the
> resolution is < 1 us [2]. Also, MS doc [3] does not say that
> GetSystemTimePreciseAsFileTime() returns value monotonically.
> Another API QueryPerformanceCounter() seems to have the monotony.
>
> A bit old document [4] also raised the possibility:
>
> ```
> Consecutive calls may return the same result. The call time is less than the
> smallest increment of the system time. The granularity is in the sub-microsecond
> regime. The function may be used for time measurements but some care has to be
> taken: Time differences may be ZERO.
> ```
>
> Also, what if the the system clock is modified during the test via NTP?
Yeah, I made a simple test for GetSystemTimePreciseAsFileTime() and
confirmed that in my VM it provides sub-microsecond precision. Regarding
NTP, I think the second failure of this ilk [1] makes this cause close to
impossible. (Can't wait for the third one to gather more information.)
>>> 2) pg_stat_reset_subscription_stats(oid) function did not reset the stats.
>>> We have a shared hash 'pgStatLocal.shared_hash'. If the entry
>>> reference (for the subscription) is not found while executing
>>> 'pg_stat_reset_subscription_stats(oid)'. It may not be able to reset
>>> the stats. Maybe somehow this shared hash is getting dropped..
>>> Also, it could be failing due to the same reason as Alexander has
>> I don't think 2) is relevant here, because shared buffers shouldn't affect
>> subscription's statistics.
> To confirm; we do not consider the possibility that pgstat_get_entry_ref() returns
> NULL right?
I've held a simple experiment with a modification like this:
@@ -1078,6 +1078,7 @@ pgstat_reset_entry(PgStat_Kind kind, Oid dboid, uint64 objid, TimestampTz ts)
    Assert(!pgstat_get_kind_info(kind)->fixed_amount);
    entry_ref = pgstat_get_entry_ref(kind, dboid, objid, false, NULL);
+if (rand() % 3 == 0) entry_ref = NULL;
    if (!entry_ref || entry_ref->shared_entry->dropped)
and got several failures like:
--- .../postgresql/src/test/regress/expected/subscription.out 2025-04-25 10:27:32.851554400 -0700
+++ .../postgresql/build/testrun/regress/regress/results/subscription.out 2025-07-20 00:05:05.667903300 -0700
@@ -56,7 +56,7 @@
 SELECT subname, stats_reset IS NULL stats_reset_is_null FROM pg_stat_subscription_stats WHERE subname = 'regress_testsub';
     subname    | stats_reset_is_null
 -----------------+---------------------
- regress_testsub | f
+ regress_testsub | t
 (1 row)
 -- Reset the stats again and check if the new reset_stats is updated.
@@ -68,11 +68,9 @@
 (1 row)
 SELECT :'prev_stats_reset' < stats_reset FROM pg_stat_subscription_stats WHERE subname = 'regress_testsub';
- ?column?
-----------
- t
-(1 row)
-
+ERROR:Â syntax error at or near ":"
+LINE 1: SELECT :'prev_stats_reset' < stats_reset FROM pg_stat_subscr...
+
--- .../postgresql/src/test/regress/expected/stats.out   2025-04-25 10:27:36.930322500 -0700
+++ .../postgresql/build/testrun/regress/regress/results/stats.out 2025-07-20 00:05:19.579864900 -0700
@@ -1720,7 +1720,7 @@
 SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 ?column?
 ----------
- t
+ f
 (1 row)
...
Thus, if there is some issue with pgstat_get_entry_ref(), then it should
be specific to subscriptions and come out in that place only (given the
information we have now).
So I still suspect some Windows/concrete animal's peculiarity.
Nagata-san, could you please share the configuration of hamerkop? If it's
running inside VM, what virtualization software is used?
[1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=hamerkop&dt=2025-07-09%2011%3A02%3A23
Best regards.
Alexander
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-23 00:55 ` Yugo Nagata <[email protected]>
2 siblings, 0 replies; 287+ messages in thread
From: Yugo Nagata @ 2025-07-23 00:55 UTC (permalink / raw)
To: Alexander Lakhin <[email protected]>; +Cc: Hayato Kuroda (Fujitsu) <[email protected]>; pgsql-hackers; Shlok Kyal <[email protected]>; [email protected]
Hello Alexander,
> Nagata-san, could you please share the configuration of hamerkop? If it's
> running inside VM, what virtualization software is used?
>
> [1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=hamerkop&dt=2025-07-09%2011%3A02%3A23
I am not the person in charge of it, so I added the responsible email address to the CC list.
Takatsuka-san, could you please take care of this?
Regards,
Yugo Nagata
--
Yugo Nagata <[email protected]>
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-23 04:00 ` Alexander Lakhin <[email protected]>
2025-07-23 06:15 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2 siblings, 1 reply; 287+ messages in thread
From: Alexander Lakhin @ 2025-07-23 04:00 UTC (permalink / raw)
To: Hayato Kuroda (Fujitsu) <[email protected]>; +Cc: pgsql-hackers; Shlok Kyal <[email protected]>; Yugo Nagata <[email protected]>
Hello Kuroda-san,
20.07.2025 11:00, Alexander Lakhin wrote:
>
> Yeah, I made a simple test for GetSystemTimePreciseAsFileTime() and
> confirmed that in my VM it provides sub-microsecond precision. Regarding
> NTP, I think the second failure of this ilk [1] makes this cause close to
> impossible. (Can't wait for the third one to gather more information.)
And here it is [1]:
diff --strip-trailing-cr -U3 c:/build-farm-local/buildroot/HEAD/pgsql/src/test/isolation/expected/stats.out
c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/isolation/isolation/results/stats.out
--- c:/build-farm-local/buildroot/HEAD/pgsql/src/test/isolation/expected/stats.out 2025-07-22 20:08:30 +0900
+++ c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/isolation/isolation/results/stats.out 2025-07-22 20:30:47 +0900
@@ -3729,7 +3729,7 @@
 name |pg_stat_get_function_calls|total_above_zero|self_above_zero
 --------------+--------------------------+----------------+---------------
-test_stat_func|Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 1|t |t
+test_stat_func|Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 1|f |f
 (1 row)
Not related to subscriptions this time, but still related to pg_stat and
time measurement.
There was the same looking failure on caiman, which is running on
continuously updated Fedora: [2].
I could not reproduce that one either, but suspected the OS kernel:
It had 6.14.0-0.rc3.20250219git6537cfb395f3.31.fc43.x86_64 at the moment
of the failure and updated to 6.14.0-0.rc4.36.fc43.x86_64 on 2025-02-27.
There was no failures of this kind since then.
So I think we could observe such anomalies if, say, the OS kernel can't
read system clock in time (stalls for a millisecond when accessing it)...
[1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=hamerkop&dt=2025-07-22%2011%3A02%3A15
[2] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=caiman&dt=2025-02-23%2006%3A54%3A54
Best regards,
Alexander
^ permalink raw reply [nested|flat] 287+ messages in thread
* RE: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 04:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-23 06:15 ` Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-26 09:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
0 siblings, 1 reply; 287+ messages in thread
From: Hayato Kuroda (Fujitsu) @ 2025-07-23 06:15 UTC (permalink / raw)
To: 'Alexander Lakhin' <[email protected]>; +Cc: pgsql-hackers; Shlok Kyal <[email protected]>; Yugo Nagata <[email protected]>
Dear Alexander,
> And here it is [1]:
> diff --strip-trailing-cr -U3
> c:/build-farm-local/buildroot/HEAD/pgsql/src/test/isolation/expected/stats.ou
> t
> c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/isolation/isolation/res
> ults/stats.out
> ---
> c:/build-farm-local/buildroot/HEAD/pgsql/src/test/isolation/expected/stats.ou
> t 2025-07-22 20:08:30 +0900
> +++
> c:/build-farm-local/buildroot/HEAD/pgsql.build/testrun/isolation/isolation/res
> ults/stats.out 2025-07-22 20:30:47 +0900
> @@ -3729,7 +3729,7 @@
>
> name |pg_stat_get_function_calls|total_above_zero|self_above_zero
> --------------+--------------------------+----------------+---------------
> -test_stat_func| 1|t |t
> +test_stat_func| 1|f |f
> (1 row)
>
> Not related to subscriptions this time, but still related to pg_stat and
> time measurement.
It looks like for me that we measured the execution time of the function in
millisecond but it was "zero", right?
> So I think we could observe such anomalies if, say, the OS kernel can't
> read system clock in time (stalls for a millisecond when accessing it)...
I also feel like that. But if so, how should we fix tests? We must remove all
stuff which assumes the time is monotonic?
Best regards,
Hayato Kuroda
FUJITSU LIMITED
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 04:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 06:15 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
@ 2025-07-26 09:00 ` Alexander Lakhin <[email protected]>
0 siblings, 0 replies; 287+ messages in thread
From: Alexander Lakhin @ 2025-07-26 09:00 UTC (permalink / raw)
To: Hayato Kuroda (Fujitsu) <[email protected]>; TAKATSUKA Haruka <[email protected]>; +Cc: pgsql-hackers; Shlok Kyal <[email protected]>; Yugo Nagata <[email protected]>
Hello Kuroda-san and Takatsuka-san,
24.07.2025 03:49, TAKATSUKA Haruka wrote:
> {snip}
>> Maybe you could try tools.syncTime = "0" by any chance?
> It has been already tools.syncTime = "0" so far.
> I confirmed the following GUI setting.
> ...
23.07.2025 09:15, Hayato Kuroda (Fujitsu) wrote:
> It looks like for me that we measured the execution time of the function in
> millisecond but it was "zero", right?
Yes, my understanding is the same.
>> So I think we could observe such anomalies if, say, the OS kernel can't
>> read system clock in time (stalls for a millisecond when accessing it)...
> I also feel like that. But if so, how should we fix tests? We must remove all
> stuff which assumes the time is monotonic?
From what Takatsuka-san shared on hamerkop's configuration, I still
suspect there could be some platform specifics there. I've found another
interesting reading on the subject, which describes effects of CPU
pressure and mentions other low-level parameters, e. g.
monitor_control.virtual_rdtsc: [1].
Probably there could be some experiments performed there to measure the
maximum timer resolution (e. g. with a simple program attached).
I also observed a failure of pg_stat_statements on ARMv7 device in the past:
--- .../contrib/pg_stat_statements/expected/entry_timestamp.out 2024-04-11 07:20:32.563588101 +0300
+++Â .../contrib/pg_stat_statements/results/entry_timestamp.out 2024-04-15 11:16:00.217396694 +0300
@@ -45,7 +45,7 @@
 WHERE query LIKE '%STMTTS%';
 total | minmax_plan_zero | minmax_exec_zero | minmax_stats_since_after_ref | stats_since_after_ref
 -------+------------------+------------------+------------------------------+-----------------------
-Â Â Â Â 2 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0
+Â Â Â Â 2 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 1 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0 |Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 0
 (1 row)
with clocksource =Â 32k_counter, which gave me the maximum resolution
0.030517 sec.
So if to choose fixing tests, then it's not clear to me, what lowest timer
resolution to consider acceptable.
[1] https://www.vmware.com/docs/vmware_timekeeping
Best regards,
Alexander
Attachments:
[text/x-csrc] test-gst.c (951B, ../../[email protected]/3-test-gst.c)
download | inline:
#include <windows.h>
#define FILETIME_UNITS_PER_SEC 10000000L
#define FILETIME_UNITS_PER_USEC 10
void main(int argc, char *argv[]) {
FILETIME ft1, ft2;
ULARGE_INTEGER uli1, uli2;
int r = 0;
int n = (argc > 1) ? atol(argv[1]) : 0;
GetSystemTimePreciseAsFileTime(&ft1);
for (long int i = 0; i < n; i++) r += i;
GetSystemTimePreciseAsFileTime(&ft2);
uli1.LowPart = ft1.dwLowDateTime; uli1.HighPart = ft1.dwHighDateTime;
long usec1 = (long) (((uli1.QuadPart) % FILETIME_UNITS_PER_SEC)
/ FILETIME_UNITS_PER_USEC);
uli2.LowPart = ft2.dwLowDateTime; uli2.HighPart = ft2.dwHighDateTime;
long usec2 = (long) (((uli2.QuadPart) % FILETIME_UNITS_PER_SEC)
/ FILETIME_UNITS_PER_USEC);
printf("usec1: %llu, usec2: %llu, usec2 - usec1: %d, uli2 - uli1: %ld, r: %d\n", usec1, usec2, usec2 - usec1, (long)(uli2.QuadPart - uli1.QuadPart), r);
}
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-23 05:48 ` TAKATSUKA Haruka <[email protected]>
2025-07-23 20:00 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2 siblings, 1 reply; 287+ messages in thread
From: TAKATSUKA Haruka @ 2025-07-23 05:48 UTC (permalink / raw)
To: Alexander Lakhin <[email protected]>; +Cc: Hayato Kuroda (Fujitsu) <[email protected]>; pgsql-hackers; Shlok Kyal <[email protected]>; [email protected]
Hello Alexander,
On Wed, 23 Jul 2025 00:55:37 +0000
Yugo Nagata - Buildfarm <[email protected]> wrote:
> > Nagata-san, could you please share the configuration of hamerkop? If it's
> > running inside VM, what virtualization software is used?
It's vmware ESXi 7.0.3 (21930508).
This Windows enable auto-synchronize with 'time.windows.com'.
VMware Tools 12.1.5 build 20735119 is installed in the VM.
Thanks,
Haruka Takatsuka
> > [1] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=hamerkop&dt=2025-07-09%2011%3A02%3A23
>
> I am not the person in charge of it, so I added the responsible email address to the CC list.
> Takatsuka-san, could you please take care of this?
>
> Regards,
> Yugo Nagata
>
> --
> Yugo Nagata <[email protected]>
> Cache content lost
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 05:48 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests TAKATSUKA Haruka <[email protected]>
@ 2025-07-23 20:00 ` Alexander Lakhin <[email protected]>
2025-07-24 00:49 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests TAKATSUKA Haruka <[email protected]>
0 siblings, 1 reply; 287+ messages in thread
From: Alexander Lakhin @ 2025-07-23 20:00 UTC (permalink / raw)
To: TAKATSUKA Haruka <[email protected]>; +Cc: Hayato Kuroda (Fujitsu) <[email protected]>; pgsql-hackers; Shlok Kyal <[email protected]>; [email protected]
Hello Takatsuka-san,
23.07.2025 08:48, TAKATSUKA Haruka wrote:
> Hello Alexander,
>
> On Wed, 23 Jul 2025 00:55:37 +0000
> Yugo Nagata - Buildfarm<[email protected]> wrote:
>
>>> Nagata-san, could you please share the configuration of hamerkop? If it's
>>> running inside VM, what virtualization software is used?
> It's vmware ESXi 7.0.3 (21930508).
> This Windows enable auto-synchronize with 'time.windows.com'.
> VMware Tools 12.1.5 build 20735119 is installed in the VM.
Thank you for your prompt response!
I used VirtualBox, not VMWare, when trying to reproduce the issue, maybe
that's the reason why I failed. It looks like VMWare has it's own
specifics related to timekeeping: [1].
Maybe you could try tools.syncTime = "0" by any chance?
There is also an interesting note in VMware Tools 11 docs [2]:
If the clock on the guest operating system is ahead of the clock on the
host, VMware Tools causes the clock on the guest to run more slowly until
the clocks are synchronized.
But still it's hard to say without experimentation whether this can cause
the observed effect.
[1] https://knowledge.broadcom.com/external/article?legacyId=1318
[2]
https://techdocs.broadcom.com/us/en/vmware-cis/vsphere/tools/11-1-0/vmware-tools-administration-11-1...
Best regards,
Alexander
^ permalink raw reply [nested|flat] 287+ messages in thread
* Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 05:48 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests TAKATSUKA Haruka <[email protected]>
2025-07-23 20:00 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
@ 2025-07-24 00:49 ` TAKATSUKA Haruka <[email protected]>
0 siblings, 0 replies; 287+ messages in thread
From: TAKATSUKA Haruka @ 2025-07-24 00:49 UTC (permalink / raw)
To: Alexander Lakhin <[email protected]>; +Cc: Hayato Kuroda (Fujitsu) <[email protected]>; pgsql-hackers; Shlok Kyal <[email protected]>; [email protected]
On Wed, 23 Jul 2025 23:00:00 +0300
Alexander Lakhin <[email protected]> wrote:
{snip}
> >>> Nagata-san, could you please share the configuration of hamerkop? If it's
> >>> running inside VM, what virtualization software is used?
> > It's vmware ESXi 7.0.3 (21930508).
> > This Windows enable auto-synchronize with 'time.windows.com'.
> > VMware Tools 12.1.5 build 20735119 is installed in the VM.
>
> Thank you for your prompt response!
>
> I used VirtualBox, not VMWare, when trying to reproduce the issue, maybe
> that's the reason why I failed. It looks like VMWare has it's own
> specifics related to timekeeping: [1].
>
> Maybe you could try tools.syncTime = "0" by any chance?
It has been already tools.syncTime = "0" so far.
I confirmed the following GUI setting.
VM Options
VMware Tools
Time "Synchronize guest time with host": unchecked
Thanks,
Haruka Takatsuka
^ permalink raw reply [nested|flat] 287+ messages in thread
end of thread, other threads:[~2025-07-26 09:00 UTC | newest]
Thread overview: 287+ 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 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 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 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 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 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 v25 4/8] 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 v36 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 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 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 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 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 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 v52 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 v33 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]>
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 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 v50 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 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 v38 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 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 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 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 v34 4/7] 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 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 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 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 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 v42 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 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 v48 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 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 v52 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 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 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 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 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 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 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 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 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 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 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 v41 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 v40 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 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 v37 3/6] 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 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 v43 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 v39 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 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 v46 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 v47 3/7] 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 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 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 v51 3/7] 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 v51 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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]>
2025-01-06 07:00 stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-03 06:54 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Shlok Kyal <[email protected]>
2025-07-04 20:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-15 07:33 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-20 08:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 00:55 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Yugo Nagata <[email protected]>
2025-07-23 04:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 06:15 ` RE: stats.sql might fail due to shared buffers also used by parallel tests Hayato Kuroda (Fujitsu) <[email protected]>
2025-07-26 09:00 ` Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-23 05:48 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests TAKATSUKA Haruka <[email protected]>
2025-07-23 20:00 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests Alexander Lakhin <[email protected]>
2025-07-24 00:49 ` Re: [Buildfarm:84] Re: stats.sql might fail due to shared buffers also used by parallel tests TAKATSUKA Haruka <[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