From 0b40b322652f5f7f538381a4f299deb94f465c94 Mon Sep 17 00:00:00 2001 From: Nathan Bossart Date: Thu, 15 Dec 2022 14:11:43 -0800 Subject: [PATCH v9 2/3] handle race condition when restarting wal receivers --- src/backend/postmaster/postmaster.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index f459dab360..4107a85b51 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -1601,9 +1601,9 @@ checkControlFile(void) * * In normal conditions we wait at most one minute, to ensure that the other * background tasks handled by ServerLoop get done even when no requests are - * arriving. However, if there are background workers waiting to be started, - * we don't actually sleep so that they are quickly serviced. Other exception - * cases are as shown in the code. + * arriving. However, if there are background workers or a WAL receiver + * waiting to be started, we make sure they are quickly serviced. Other + * exception cases are as shown in the code. */ static void DetermineSleepTime(struct timeval *timeout) @@ -1611,11 +1611,12 @@ DetermineSleepTime(struct timeval *timeout) TimestampTz next_wakeup = 0; /* - * Normal case: either there are no background workers at all, or we're in - * a shutdown sequence (during which we ignore bgworkers altogether). + * Normal case: either there are no background workers and no WAL receiver + * at all, or we're in a shutdown sequence (during which we ignore + * bgworkers altogether). */ if (Shutdown > NoShutdown || - (!StartWorkerNeeded && !HaveCrashedWorker)) + (!StartWorkerNeeded && !HaveCrashedWorker && !WalReceiverRequested)) { if (AbortStartTime != 0) { @@ -1640,6 +1641,17 @@ DetermineSleepTime(struct timeval *timeout) return; } + /* + * We're probably waiting for SIGCHLD before starting the WAL receiver. We + * don't expect that to take long. + */ + if (WalReceiverRequested) + { + timeout->tv_sec = 0; + timeout->tv_usec = 100000; /* 100ms */ + return; + } + if (HaveCrashedWorker) { slist_mutable_iter siter; -- 2.25.1