From fa837ad637c8c50d499ac51b84e7a3eb4ed2b1c2 Mon Sep 17 00:00:00 2001 From: Alvaro Herrera Date: Mon, 24 Aug 2009 17:23:28 +0000 Subject: [PATCH] Avoid calling kill() in a postmaster signal handler. This causes problems when the system load is high, per report from Zdenek Kotala in <1250860954.1239.114.camel@localhost>; instead of calling kill directly, have the signal handler set a flag which is checked in ServerLoop. This way, the handler can return before being called again by a subsequent signal sent from the autovacuum launcher. Also, increase the sleep in the launcher in this failure path to 1 second. Backpatch to 8.3, which is when the signalling between autovacuum launcher/postmaster was introduced. Also, add a couple of ReleasePostmasterChildSlot calls in error paths; this part backpatched to 8.4 which is when the child slot stuff was introduced. --- src/backend/postmaster/autovacuum.c | 4 ++-- src/backend/postmaster/postmaster.c | 20 +++++++++++++++++--- 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c index eea76fb6a2d..8c4b3dcc9f3 100644 --- a/src/backend/postmaster/autovacuum.c +++ b/src/backend/postmaster/autovacuum.c @@ -55,7 +55,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/postmaster/autovacuum.c,v 1.71.2.9 2009/06/09 19:36:42 alvherre Exp $ + * $PostgreSQL: pgsql/src/backend/postmaster/autovacuum.c,v 1.71.2.10 2009/08/24 17:23:28 alvherre Exp $ * *------------------------------------------------------------------------- */ @@ -646,7 +646,7 @@ AutoVacLauncherMain(int argc, char *argv[]) * of a worker will continue to fail in the same way. */ AutoVacuumShmem->av_signal[AutoVacForkFailed] = false; - pg_usleep(100000L); /* 100ms */ + pg_usleep(1000000L); /* 1s */ SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_WORKER); continue; } diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 8c6fb05a257..ebac2299fed 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -37,7 +37,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.551.2.3 2009/08/11 11:51:20 mha Exp $ + * $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.551.2.4 2009/08/24 17:23:28 alvherre Exp $ * * NOTES * @@ -269,6 +269,8 @@ bool redirection_done = false; /* stderr redirected for syslogger? */ /* received START_AUTOVAC_LAUNCHER signal */ static volatile sig_atomic_t start_autovac_launcher = false; +/* the launcher needs to be signalled to communicate some condition */ +static volatile bool avlauncher_needs_signal = false; /* * State for assigning random salts and cancel keys. @@ -1321,6 +1323,14 @@ ServerLoop(void) if (PgStatPID == 0 && pmState == PM_RUN) PgStatPID = pgstat_start(); + /* If we need to signal the autovacuum launcher, do so now */ + if (avlauncher_needs_signal) + { + avlauncher_needs_signal = false; + if (AutoVacPID != 0) + kill(AutoVacPID, SIGUSR1); + } + /* * Touch the socket and lock file every 58 minutes, to ensure that * they are not removed by overzealous /tmp-cleaning tasks. We assume @@ -4155,12 +4165,16 @@ StartAutovacuumWorker(void) /* * Report the failure to the launcher, if it's running. (If it's not, we * might not even be connected to shared memory, so don't try to call - * AutoVacWorkerFailed.) + * AutoVacWorkerFailed.) Note that we also need to signal it so that it + * responds to the condition, but we don't do that here, instead waiting + * for ServerLoop to do it. This way we avoid a ping-pong signalling in + * quick succession between the autovac launcher and postmaster in case + * things get ugly. */ if (AutoVacPID != 0) { AutoVacWorkerFailed(); - kill(AutoVacPID, SIGUSR1); + avlauncher_needs_signal = true; } } -- 2.47.2