From 46651ce6fe013220ed397add242004d764fc0153 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 4 May 2024 14:15:05 +0200 Subject: Adding upstream version 14.5. Signed-off-by: Daniel Baumann --- src/backend/postmaster/bgwriter.c | 351 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 351 insertions(+) create mode 100644 src/backend/postmaster/bgwriter.c (limited to 'src/backend/postmaster/bgwriter.c') diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c new file mode 100644 index 0000000..715d519 --- /dev/null +++ b/src/backend/postmaster/bgwriter.c @@ -0,0 +1,351 @@ +/*------------------------------------------------------------------------- + * + * bgwriter.c + * + * The background writer (bgwriter) is new as of Postgres 8.0. It attempts + * to keep regular backends from having to write out dirty shared buffers + * (which they would only do when needing to free a shared buffer to read in + * another page). In the best scenario all writes from shared buffers will + * be issued by the background writer process. However, regular backends are + * still empowered to issue writes if the bgwriter fails to maintain enough + * clean shared buffers. + * + * As of Postgres 9.2 the bgwriter no longer handles checkpoints. + * + * The bgwriter is started by the postmaster as soon as the startup subprocess + * finishes, or as soon as recovery begins if we are doing archive recovery. + * It remains alive until the postmaster commands it to terminate. + * Normal termination is by SIGTERM, which instructs the bgwriter to exit(0). + * Emergency termination is by SIGQUIT; like any backend, the bgwriter will + * simply abort and exit on SIGQUIT. + * + * If the bgwriter exits unexpectedly, the postmaster treats that the same + * as a backend crash: shared memory may be corrupted, so remaining backends + * should be killed by SIGQUIT and then a recovery cycle started. + * + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * + * + * IDENTIFICATION + * src/backend/postmaster/bgwriter.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "access/xlog.h" +#include "access/xlog_internal.h" +#include "libpq/pqsignal.h" +#include "miscadmin.h" +#include "pgstat.h" +#include "postmaster/bgwriter.h" +#include "postmaster/interrupt.h" +#include "storage/buf_internals.h" +#include "storage/bufmgr.h" +#include "storage/condition_variable.h" +#include "storage/fd.h" +#include "storage/ipc.h" +#include "storage/lwlock.h" +#include "storage/proc.h" +#include "storage/procsignal.h" +#include "storage/shmem.h" +#include "storage/smgr.h" +#include "storage/spin.h" +#include "storage/standby.h" +#include "utils/guc.h" +#include "utils/memutils.h" +#include "utils/resowner.h" +#include "utils/timestamp.h" + +/* + * GUC parameters + */ +int BgWriterDelay = 200; + +/* + * Multiplier to apply to BgWriterDelay when we decide to hibernate. + * (Perhaps this needs to be configurable?) + */ +#define HIBERNATE_FACTOR 50 + +/* + * Interval in which standby snapshots are logged into the WAL stream, in + * milliseconds. + */ +#define LOG_SNAPSHOT_INTERVAL_MS 15000 + +/* + * LSN and timestamp at which we last issued a LogStandbySnapshot(), to avoid + * doing so too often or repeatedly if there has been no other write activity + * in the system. + */ +static TimestampTz last_snapshot_ts; +static XLogRecPtr last_snapshot_lsn = InvalidXLogRecPtr; + + +/* + * Main entry point for bgwriter process + * + * This is invoked from AuxiliaryProcessMain, which has already created the + * basic execution environment, but not enabled signals yet. + */ +void +BackgroundWriterMain(void) +{ + sigjmp_buf local_sigjmp_buf; + MemoryContext bgwriter_context; + bool prev_hibernate; + WritebackContext wb_context; + + /* + * Properly accept or ignore signals that might be sent to us. + */ + pqsignal(SIGHUP, SignalHandlerForConfigReload); + pqsignal(SIGINT, SIG_IGN); + pqsignal(SIGTERM, SignalHandlerForShutdownRequest); + /* SIGQUIT handler was already set up by InitPostmasterChild */ + pqsignal(SIGALRM, SIG_IGN); + pqsignal(SIGPIPE, SIG_IGN); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); + pqsignal(SIGUSR2, SIG_IGN); + + /* + * Reset some signals that are accepted by postmaster but not here + */ + pqsignal(SIGCHLD, SIG_DFL); + + /* + * We just started, assume there has been either a shutdown or + * end-of-recovery snapshot. + */ + last_snapshot_ts = GetCurrentTimestamp(); + + /* + * Create a memory context that we will do all our work in. We do this so + * that we can reset the context during error recovery and thereby avoid + * possible memory leaks. Formerly this code just ran in + * TopMemoryContext, but resetting that would be a really bad idea. + */ + bgwriter_context = AllocSetContextCreate(TopMemoryContext, + "Background Writer", + ALLOCSET_DEFAULT_SIZES); + MemoryContextSwitchTo(bgwriter_context); + + WritebackContextInit(&wb_context, &bgwriter_flush_after); + + /* + * If an exception is encountered, processing resumes here. + * + * You might wonder why this isn't coded as an infinite loop around a + * PG_TRY construct. The reason is that this is the bottom of the + * exception stack, and so with PG_TRY there would be no exception handler + * in force at all during the CATCH part. By leaving the outermost setjmp + * always active, we have at least some chance of recovering from an error + * during error recovery. (If we get into an infinite loop thereby, it + * will soon be stopped by overflow of elog.c's internal state stack.) + * + * Note that we use sigsetjmp(..., 1), so that the prevailing signal mask + * (to wit, BlockSig) will be restored when longjmp'ing to here. Thus, + * signals other than SIGQUIT will be blocked until we complete error + * recovery. It might seem that this policy makes the HOLD_INTERRUPTS() + * call redundant, but it is not since InterruptPending might be set + * already. + */ + if (sigsetjmp(local_sigjmp_buf, 1) != 0) + { + /* Since not using PG_TRY, must reset error stack by hand */ + error_context_stack = NULL; + + /* Prevent interrupts while cleaning up */ + HOLD_INTERRUPTS(); + + /* Report the error to the server log */ + EmitErrorReport(); + + /* + * These operations are really just a minimal subset of + * AbortTransaction(). We don't have very many resources to worry + * about in bgwriter, but we do have LWLocks, buffers, and temp files. + */ + LWLockReleaseAll(); + ConditionVariableCancelSleep(); + AbortBufferIO(); + UnlockBuffers(); + ReleaseAuxProcessResources(false); + AtEOXact_Buffers(false); + AtEOXact_SMgr(); + AtEOXact_Files(false); + AtEOXact_HashTables(false); + + /* + * Now return to normal top-level context and clear ErrorContext for + * next time. + */ + MemoryContextSwitchTo(bgwriter_context); + FlushErrorState(); + + /* Flush any leaked data in the top-level context */ + MemoryContextResetAndDeleteChildren(bgwriter_context); + + /* re-initialize to avoid repeated errors causing problems */ + WritebackContextInit(&wb_context, &bgwriter_flush_after); + + /* Now we can allow interrupts again */ + RESUME_INTERRUPTS(); + + /* + * Sleep at least 1 second after any error. A write error is likely + * to be repeated, and we don't want to be filling the error logs as + * fast as we can. + */ + pg_usleep(1000000L); + + /* + * Close all open files after any error. This is helpful on Windows, + * where holding deleted files open causes various strange errors. + * It's not clear we need it elsewhere, but shouldn't hurt. + */ + smgrcloseall(); + + /* Report wait end here, when there is no further possibility of wait */ + pgstat_report_wait_end(); + } + + /* We can now handle ereport(ERROR) */ + PG_exception_stack = &local_sigjmp_buf; + + /* + * Unblock signals (they were blocked when the postmaster forked us) + */ + PG_SETMASK(&UnBlockSig); + + /* + * Reset hibernation state after any error. + */ + prev_hibernate = false; + + /* + * Loop forever + */ + for (;;) + { + bool can_hibernate; + int rc; + + /* Clear any already-pending wakeups */ + ResetLatch(MyLatch); + + HandleMainLoopInterrupts(); + + /* + * Do one cycle of dirty-buffer writing. + */ + can_hibernate = BgBufferSync(&wb_context); + + /* + * Send off activity statistics to the stats collector + */ + pgstat_send_bgwriter(); + + if (FirstCallSinceLastCheckpoint()) + { + /* + * After any checkpoint, close all smgr files. This is so we + * won't hang onto smgr references to deleted files indefinitely. + */ + smgrcloseall(); + } + + /* + * Log a new xl_running_xacts every now and then so replication can + * get into a consistent state faster (think of suboverflowed + * snapshots) and clean up resources (locks, KnownXids*) more + * frequently. The costs of this are relatively low, so doing it 4 + * times (LOG_SNAPSHOT_INTERVAL_MS) a minute seems fine. + * + * We assume the interval for writing xl_running_xacts is + * significantly bigger than BgWriterDelay, so we don't complicate the + * overall timeout handling but just assume we're going to get called + * often enough even if hibernation mode is active. It's not that + * important that LOG_SNAPSHOT_INTERVAL_MS is met strictly. To make + * sure we're not waking the disk up unnecessarily on an idle system + * we check whether there has been any WAL inserted since the last + * time we've logged a running xacts. + * + * We do this logging in the bgwriter as it is the only process that + * is run regularly and returns to its mainloop all the time. E.g. + * Checkpointer, when active, is barely ever in its mainloop and thus + * makes it hard to log regularly. + */ + if (XLogStandbyInfoActive() && !RecoveryInProgress()) + { + TimestampTz timeout = 0; + TimestampTz now = GetCurrentTimestamp(); + + timeout = TimestampTzPlusMilliseconds(last_snapshot_ts, + LOG_SNAPSHOT_INTERVAL_MS); + + /* + * Only log if enough time has passed and interesting records have + * been inserted since the last snapshot. Have to compare with <= + * instead of < because GetLastImportantRecPtr() points at the + * start of a record, whereas last_snapshot_lsn points just past + * the end of the record. + */ + if (now >= timeout && + last_snapshot_lsn <= GetLastImportantRecPtr()) + { + last_snapshot_lsn = LogStandbySnapshot(); + last_snapshot_ts = now; + } + } + + /* + * Sleep until we are signaled or BgWriterDelay has elapsed. + * + * Note: the feedback control loop in BgBufferSync() expects that we + * will call it every BgWriterDelay msec. While it's not critical for + * correctness that that be exact, the feedback loop might misbehave + * if we stray too far from that. Hence, avoid loading this process + * down with latch events that are likely to happen frequently during + * normal operation. + */ + rc = WaitLatch(MyLatch, + WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH, + BgWriterDelay /* ms */ , WAIT_EVENT_BGWRITER_MAIN); + + /* + * If no latch event and BgBufferSync says nothing's happening, extend + * the sleep in "hibernation" mode, where we sleep for much longer + * than bgwriter_delay says. Fewer wakeups save electricity. When a + * backend starts using buffers again, it will wake us up by setting + * our latch. Because the extra sleep will persist only as long as no + * buffer allocations happen, this should not distort the behavior of + * BgBufferSync's control loop too badly; essentially, it will think + * that the system-wide idle interval didn't exist. + * + * There is a race condition here, in that a backend might allocate a + * buffer between the time BgBufferSync saw the alloc count as zero + * and the time we call StrategyNotifyBgWriter. While it's not + * critical that we not hibernate anyway, we try to reduce the odds of + * that by only hibernating when BgBufferSync says nothing's happening + * for two consecutive cycles. Also, we mitigate any possible + * consequences of a missed wakeup by not hibernating forever. + */ + if (rc == WL_TIMEOUT && can_hibernate && prev_hibernate) + { + /* Ask for notification at next buffer allocation */ + StrategyNotifyBgWriter(MyProc->pgprocno); + /* Sleep ... */ + (void) WaitLatch(MyLatch, + WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH, + BgWriterDelay * HIBERNATE_FACTOR, + WAIT_EVENT_BGWRITER_HIBERNATE); + /* Reset the notification request in case we timed out */ + StrategyNotifyBgWriter(-1); + } + + prev_hibernate = can_hibernate; + } +} -- cgit v1.2.3