public inbox for [email protected]help / color / mirror / Atom feed
[PATCH 1/2] bootstrap: convert Typ to a List* 3+ messages / 3 participants [nested] [flat]
* [PATCH 1/2] bootstrap: convert Typ to a List* @ 2020-11-20 02:48 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 3+ messages in thread From: Justin Pryzby @ 2020-11-20 02:48 UTC (permalink / raw) --- src/backend/bootstrap/bootstrap.c | 89 ++++++++++++++----------------- 1 file changed, 41 insertions(+), 48 deletions(-) diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..1b940d9d27 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -58,7 +58,7 @@ static void BootstrapModeMain(void); static void bootstrap_signals(void); static void ShutdownAuxiliaryProcess(int code, Datum arg); static Form_pg_attribute AllocateAttribute(void); -static void populate_typ_array(void); +static void populate_typ(void); static Oid gettype(char *type); static void cleanup(void); @@ -159,7 +159,7 @@ struct typmap FormData_pg_type am_typ; }; -static struct typmap **Typ = NULL; +static List *Typ = NIL; /* List of struct typmap* */ static struct typmap *Ap = NULL; static Datum values[MAXATTR]; /* current row's attribute values */ @@ -595,10 +595,10 @@ boot_openrel(char *relname) /* * pg_type must be filled before any OPEN command is executed, hence we - * can now populate the Typ array if we haven't yet. + * can now populate Typ if we haven't yet. */ - if (Typ == NULL) - populate_typ_array(); + if (Typ == NIL) + populate_typ(); if (boot_reldesc != NULL) closerel(NULL); @@ -688,7 +688,7 @@ DefineAttr(char *name, char *type, int attnum, int nullness) typeoid = gettype(type); - if (Typ != NULL) + if (Typ != NIL) { attrtypes[attnum]->atttypid = Ap->am_oid; attrtypes[attnum]->attlen = Ap->am_typ.typlen; @@ -866,47 +866,36 @@ cleanup(void) } /* ---------------- - * populate_typ_array + * populate_typ * - * Load the Typ array by reading pg_type. + * Load Typ by reading pg_type. * ---------------- */ static void -populate_typ_array(void) +populate_typ(void) { Relation rel; TableScanDesc scan; HeapTuple tup; - int nalloc; - int i; - - Assert(Typ == NULL); + MemoryContext old; - nalloc = 512; - Typ = (struct typmap **) - MemoryContextAlloc(TopMemoryContext, nalloc * sizeof(struct typmap *)); + Assert(Typ == NIL); rel = table_open(TypeRelationId, NoLock); scan = table_beginscan_catalog(rel, 0, NULL); - i = 0; + old = MemoryContextSwitchTo(TopMemoryContext); while ((tup = heap_getnext(scan, ForwardScanDirection)) != NULL) { Form_pg_type typForm = (Form_pg_type) GETSTRUCT(tup); + struct typmap *newtyp; - /* make sure there will be room for a trailing NULL pointer */ - if (i >= nalloc - 1) - { - nalloc *= 2; - Typ = (struct typmap **) - repalloc(Typ, nalloc * sizeof(struct typmap *)); - } - Typ[i] = (struct typmap *) - MemoryContextAlloc(TopMemoryContext, sizeof(struct typmap)); - Typ[i]->am_oid = typForm->oid; - memcpy(&(Typ[i]->am_typ), typForm, sizeof(Typ[i]->am_typ)); - i++; + newtyp = (struct typmap *) palloc(sizeof(struct typmap)); + Typ = lappend(Typ, newtyp); + + newtyp->am_oid = typForm->oid; + memcpy(&newtyp->am_typ, typForm, sizeof(newtyp->am_typ)); } - Typ[i] = NULL; /* Fill trailing NULL pointer */ + MemoryContextSwitchTo(old); table_endscan(scan); table_close(rel, NoLock); } @@ -916,25 +905,26 @@ populate_typ_array(void) * * NB: this is really ugly; it will return an integer index into TypInfo[], * and not an OID at all, until the first reference to a type not known in - * TypInfo[]. At that point it will read and cache pg_type in the Typ array, + * TypInfo[]. At that point it will read and cache pg_type in Typ, * and subsequently return a real OID (and set the global pointer Ap to * point at the found row in Typ). So caller must check whether Typ is - * still NULL to determine what the return value is! + * still NIL to determine what the return value is! * ---------------- */ static Oid gettype(char *type) { - if (Typ != NULL) + if (Typ != NIL) { - struct typmap **app; + ListCell *lc; - for (app = Typ; *app != NULL; app++) + foreach (lc, Typ) { - if (strncmp(NameStr((*app)->am_typ.typname), type, NAMEDATALEN) == 0) + struct typmap *app = lfirst(lc); + if (strncmp(NameStr(app->am_typ.typname), type, NAMEDATALEN) == 0) { - Ap = *app; - return (*app)->am_oid; + Ap = app; + return app->am_oid; } } } @@ -949,7 +939,7 @@ gettype(char *type) } /* Not in TypInfo, so we'd better be able to read pg_type now */ elog(DEBUG4, "external type: %s", type); - populate_typ_array(); + populate_typ(); return gettype(type); } elog(ERROR, "unrecognized type \"%s\"", type); @@ -977,17 +967,20 @@ boot_get_type_io_data(Oid typid, Oid *typinput, Oid *typoutput) { - if (Typ != NULL) + if (Typ != NIL) { /* We have the boot-time contents of pg_type, so use it */ - struct typmap **app; - struct typmap *ap; - - app = Typ; - while (*app && (*app)->am_oid != typid) - ++app; - ap = *app; - if (ap == NULL) + struct typmap *ap = NULL; + ListCell *lc; + + foreach (lc, Typ) + { + ap = lfirst(lc); + if (ap->am_oid == typid) + break; + } + + if (!ap || ap->am_oid != typid) elog(ERROR, "type OID %u not found in Typ list", typid); *typlen = ap->am_typ.typlen; -- 2.17.0 --yQbNiKLmgenwUfTN Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0002-Allow-composite-types-in-bootstrap.patchx" ^ permalink raw reply [nested|flat] 3+ messages in thread
* Re: 001_rep_changes.pl fails due to publisher stuck on shutdown @ 2024-05-29 15:56 vignesh C <[email protected]> 0 siblings, 1 reply; 3+ messages in thread From: vignesh C @ 2024-05-29 15:56 UTC (permalink / raw) To: Alexander Lakhin <[email protected]>; +Cc: pgsql-hackers On Wed, 29 May 2024 at 16:30, Alexander Lakhin <[email protected]> wrote: > > Hello hackers, > > As a recent buildfarm test failure [1] shows: > [14:33:02.374](0.333s) ok 23 - update works with dropped subscriber column > ### Stopping node "publisher" using mode fast > # Running: pg_ctl -D > /home/bf/bf-build/adder/HEAD/pgsql.build/testrun/subscription/001_rep_changes/data/t_001_rep_changes_publisher_data/pgdata > -m fast stop > waiting for server to shut down.. ... ... ... .. failed > pg_ctl: server does not shut down > # pg_ctl stop failed: 256 > # Postmaster PID for node "publisher" is 2222549 > [14:39:04.375](362.001s) Bail out! pg_ctl stop failed > > 001_rep_changes_publisher.log > 2024-05-16 14:33:02.907 UTC [2238704][client backend][4/22:0] LOG: statement: DELETE FROM tab_rep > 2024-05-16 14:33:02.925 UTC [2238704][client backend][:0] LOG: disconnection: session time: 0:00:00.078 user=bf > database=postgres host=[local] > 2024-05-16 14:33:02.939 UTC [2222549][postmaster][:0] LOG: received fast shutdown request > 2024-05-16 14:33:03.000 UTC [2222549][postmaster][:0] LOG: aborting any active transactions > 2024-05-16 14:33:03.049 UTC [2222549][postmaster][:0] LOG: background worker "logical replication launcher" (PID > 2223110) exited with exit code 1 > 2024-05-16 14:33:03.062 UTC [2222901][checkpointer][:0] LOG: shutting down > 2024-05-16 14:39:04.377 UTC [2222549][postmaster][:0] LOG: received immediate shutdown request > 2024-05-16 14:39:04.382 UTC [2222549][postmaster][:0] LOG: database system is shut down > > the publisher node may hang on stopping. > > I reproduced the failure (with aggressive autovacuum) locally and > discovered that it happens because: > 1) checkpointer calls WalSndInitStopping() (which sends > PROCSIG_WALSND_INIT_STOPPING to walsender), and then spins inside > WalSndWaitStopping() indefinitely, because: > 2) walsender receives the signal, sets got_STOPPING = true, but can't exit > WalSndLoop(): > 3) it never sets got_SIGUSR2 (to get into WalSndDone()) in > XLogSendLogical(): > 4) it never sets WalSndCaughtUp to true: > 5) logical_decoding_ctx->reader->EndRecPtr can't reach flushPtr in > XLogSendLogical(): > 6) EndRecPtr doesn't advance in XLogNextRecord(): > 7) XLogDecodeNextRecord() fails do decode a record that crosses a page > boundary: > 8) ReadPageInternal() (commented "Wait for the next page to become > available") constantly returns XLREAD_FAIL: > 9) state->routine.page_read()/logical_read_xlog_page() constantly returns > -1: > 10) flushptr = WalSndWaitForWal() stops advancing, because > got_STOPPING == true (see 2). > > That is, walsender doesn't let itself to catch up, if it gets the stop > signal when it's lagging behind and decoding a record requires reading > the next wal page. > > Please look at the reproducing test (based on 001_rep_changes.pl) attached. > If fails for me as below: > # 17 > Bailout called. Further testing stopped: pg_ctl stop failed > FAILED--Further testing stopped: pg_ctl stop failed > make: *** [Makefile:21: check] Ошибка 255 Thank you, Alexander, for sharing the script. I was able to reproduce the issue using the provided script. Furthermore, while investigating its origins, I discovered that this problem persists across all branches up to PG10 (the script needs slight adjustments to run it on older versions). It's worth noting that this issue isn't a result of recent version changes. Regards, Vignesh ^ permalink raw reply [nested|flat] 3+ messages in thread
* Re: 001_rep_changes.pl fails due to publisher stuck on shutdown @ 2024-05-30 04:48 Peter Smith <[email protected]> parent: vignesh C <[email protected]> 0 siblings, 0 replies; 3+ messages in thread From: Peter Smith @ 2024-05-30 04:48 UTC (permalink / raw) To: vignesh C <[email protected]>; +Cc: Alexander Lakhin <[email protected]>; pgsql-hackers On Thu, May 30, 2024 at 2:09 AM vignesh C <[email protected]> wrote: > > On Wed, 29 May 2024 at 16:30, Alexander Lakhin <[email protected]> wrote: > > > > Hello hackers, > > > > As a recent buildfarm test failure [1] shows: > > [14:33:02.374](0.333s) ok 23 - update works with dropped subscriber column > > ### Stopping node "publisher" using mode fast > > # Running: pg_ctl -D > > /home/bf/bf-build/adder/HEAD/pgsql.build/testrun/subscription/001_rep_changes/data/t_001_rep_changes_publisher_data/pgdata > > -m fast stop > > waiting for server to shut down.. ... ... ... .. failed > > pg_ctl: server does not shut down > > # pg_ctl stop failed: 256 > > # Postmaster PID for node "publisher" is 2222549 > > [14:39:04.375](362.001s) Bail out! pg_ctl stop failed > > > > 001_rep_changes_publisher.log > > 2024-05-16 14:33:02.907 UTC [2238704][client backend][4/22:0] LOG: statement: DELETE FROM tab_rep > > 2024-05-16 14:33:02.925 UTC [2238704][client backend][:0] LOG: disconnection: session time: 0:00:00.078 user=bf > > database=postgres host=[local] > > 2024-05-16 14:33:02.939 UTC [2222549][postmaster][:0] LOG: received fast shutdown request > > 2024-05-16 14:33:03.000 UTC [2222549][postmaster][:0] LOG: aborting any active transactions > > 2024-05-16 14:33:03.049 UTC [2222549][postmaster][:0] LOG: background worker "logical replication launcher" (PID > > 2223110) exited with exit code 1 > > 2024-05-16 14:33:03.062 UTC [2222901][checkpointer][:0] LOG: shutting down > > 2024-05-16 14:39:04.377 UTC [2222549][postmaster][:0] LOG: received immediate shutdown request > > 2024-05-16 14:39:04.382 UTC [2222549][postmaster][:0] LOG: database system is shut down > > > > the publisher node may hang on stopping. > > > > I reproduced the failure (with aggressive autovacuum) locally and > > discovered that it happens because: > > 1) checkpointer calls WalSndInitStopping() (which sends > > PROCSIG_WALSND_INIT_STOPPING to walsender), and then spins inside > > WalSndWaitStopping() indefinitely, because: > > 2) walsender receives the signal, sets got_STOPPING = true, but can't exit > > WalSndLoop(): > > 3) it never sets got_SIGUSR2 (to get into WalSndDone()) in > > XLogSendLogical(): > > 4) it never sets WalSndCaughtUp to true: > > 5) logical_decoding_ctx->reader->EndRecPtr can't reach flushPtr in > > XLogSendLogical(): > > 6) EndRecPtr doesn't advance in XLogNextRecord(): > > 7) XLogDecodeNextRecord() fails do decode a record that crosses a page > > boundary: > > 8) ReadPageInternal() (commented "Wait for the next page to become > > available") constantly returns XLREAD_FAIL: > > 9) state->routine.page_read()/logical_read_xlog_page() constantly returns > > -1: > > 10) flushptr = WalSndWaitForWal() stops advancing, because > > got_STOPPING == true (see 2). > > > > That is, walsender doesn't let itself to catch up, if it gets the stop > > signal when it's lagging behind and decoding a record requires reading > > the next wal page. > > > > Please look at the reproducing test (based on 001_rep_changes.pl) attached. > > If fails for me as below: > > # 17 > > Bailout called. Further testing stopped: pg_ctl stop failed > > FAILED--Further testing stopped: pg_ctl stop failed > > make: *** [Makefile:21: check] Ошибка 255 > > Thank you, Alexander, for sharing the script. I was able to reproduce > the issue using the provided script. Furthermore, while investigating > its origins, I discovered that this problem persists across all > branches up to PG10 (the script needs slight adjustments to run it on > older versions). It's worth noting that this issue isn't a result of > recent version changes. > Hi, FWIW using the provided scripting I was also able to reproduce the problem on HEAD but for me, it was more rare. -- the script passed ok 3 times all 100 iterations; it eventually failed on the 4th run on the 75th iteration. ====== Kind Regards, Peter Smith. Fujitsu Australia ^ permalink raw reply [nested|flat] 3+ messages in thread
end of thread, other threads:[~2024-05-30 04:48 UTC | newest] Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-11-20 02:48 [PATCH 1/2] bootstrap: convert Typ to a List* Justin Pryzby <[email protected]> 2024-05-29 15:56 Re: 001_rep_changes.pl fails due to publisher stuck on shutdown vignesh C <[email protected]> 2024-05-30 04:48 ` Re: 001_rep_changes.pl fails due to publisher stuck on shutdown Peter Smith <[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