/* * Log details of the current snapshot to WAL. This allows the snapshot state * to be reconstructed on the standby. * * We can move directly to STANDBY_SNAPSHOT_READY at startup if we * start from a shutdown checkpoint because we know nothing was running * at that time and our recovery snapshot is known empty. In the more * typical case of an online checkpoint we need to jump through a few * hoops to get a correct recovery snapshot and this requires a two or * sometimes a three stage process. * * The initial snapshot must contain all running xids and all current * AccessExclusiveLocks at a point in time on the standby. Assembling * that information while the server is running requires many and * various LWLocks, so we choose to derive that information piece by * piece and then re-assemble that info on the standby. When that * information is fully assembled we move to STANDBY_SNAPSHOT_READY. * * Since locking on the primary when we derive the information is not * strict, we note that there is a time window between the derivation and * writing to WAL of the derived information. That allows race conditions * that we must resolve, since xids and locks may enter or leave the * snapshot during that window. This creates the issue that an xid or * lock may start *after* the snapshot has been derived yet *before* the * snapshot is logged in the running xacts WAL record. We resolve this by * starting to accumulate changes at a point just prior to when we derive * the snapshot on the primary, then ignore duplicates when we later apply * the snapshot from the running xacts record. This is implemented during * CreateCheckpoint() where we use the logical checkpoint location as * our starting point and then write the running xacts record immediately * before writing the main checkpoint WAL record. Since we always start * up from a checkpoint and are immediately at our starting point, we * unconditionally move to STANDBY_INITIALIZED. After this point we * must do 4 things: * * move shared nextXid forwards as we see new xids * * extend the clog and subtrans with each new xid * * keep track of uncommitted known assigned xids * * keep track of uncommitted AccessExclusiveLocks * * When we see a commit/abort we must remove known assigned xids and locks * from the completing transaction. Attempted removals that cannot locate * an entry are expected and must not cause an error when we are in state * STANDBY_INITIALIZED. This is implemented in StandbyReleaseLocks() and * KnownAssignedXidsRemove(). * * Later, when we apply the running xact data we must be careful to ignore * transactions already committed, since those commits raced ahead when * making WAL entries. */ void LogStandbySnapshot(TransactionId *oldestActiveXid, TransactionId *nextXid) { RunningTransactions running; xl_standby_lock *locks; int nlocks; Assert(XLogStandbyInfoActive()); /* * Get details of any AccessExclusiveLocks being held at the moment. * * XXX GetRunningTransactionLocks() currently holds a lock on all * partitions though it is possible to further optimise the locking. By * reference counting locks and storing the value on the ProcArray entry * for each backend we can easily tell if any locks need recording without * trying to acquire the partition locks and scanning the lock table. */ locks = GetRunningTransactionLocks(&nlocks); if (nlocks > 0) LogAccessExclusiveLocks(nlocks, locks); /* * Log details of all in-progress transactions. This should be the last * record we write, because standby will open up when it sees this. */ running = GetRunningTransactionData(); LogCurrentRunningXacts(running); /* GetRunningTransactionData() acquired XidGenLock, we must release it */ LWLockRelease(XidGenLock); *oldestActiveXid = running->oldestRunningXid; *nextXid = running->nextXid; }
/* * _bt_page_recyclable() -- Is an existing page recyclable? * * This exists to make sure _bt_getbuf and btvacuumscan have the same * policy about whether a page is safe to re-use. */ bool _bt_page_recyclable(Page page) { BTPageOpaque opaque; TransactionId cutoff; /* * It's possible to find an all-zeroes page in an index --- for example, a * backend might successfully extend the relation one page and then crash * before it is able to make a WAL entry for adding the page. If we find a * zeroed page then reclaim it. */ if (PageIsNew(page)) return true; /* * Otherwise, recycle if deleted and too old to have any processes * interested in it. If we are generating records for Hot Standby * defer page recycling until RecentGlobalXmin to respect user * controls specified by vacuum_defer_cleanup_age or hot_standby_feedback. */ if (XLogStandbyInfoActive()) cutoff = RecentGlobalXmin; else cutoff = RecentXmin; opaque = (BTPageOpaque) PageGetSpecialPointer(page); if (P_ISDELETED(opaque) && TransactionIdPrecedesOrEquals(opaque->btpo.xact, cutoff)) return true; return false; }
/* * Log details of the current snapshot to WAL. This allows the snapshot state * to be reconstructed on the standby. */ void LogStandbySnapshot(TransactionId *oldestActiveXid, TransactionId *nextXid) { RunningTransactions running; xl_standby_lock *locks; int nlocks; Assert(XLogStandbyInfoActive()); /* * Get details of any AccessExclusiveLocks being held at the moment. */ locks = GetRunningTransactionLocks(&nlocks); if (nlocks > 0) LogAccessExclusiveLocks(nlocks, locks); /* * Log details of all in-progress transactions. This should be the last * record we write, because standby will open up when it sees this. */ running = GetRunningTransactionData(); LogCurrentRunningXacts(running); *oldestActiveXid = running->oldestRunningXid; *nextXid = running->nextXid; }
/* * btvacuumscan --- scan the index for VACUUMing purposes * * This combines the functions of looking for leaf tuples that are deletable * according to the vacuum callback, looking for empty pages that can be * deleted, and looking for old deleted pages that can be recycled. Both * btbulkdelete and btvacuumcleanup invoke this (the latter only if no * btbulkdelete call occurred). * * The caller is responsible for initially allocating/zeroing a stats struct * and for obtaining a vacuum cycle ID if necessary. */ static void btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state, BTCycleId cycleid) { Relation rel = info->index; BTVacState vstate; BlockNumber num_pages; BlockNumber blkno; bool needLock; /* * Reset counts that will be incremented during the scan; needed in case * of multiple scans during a single VACUUM command */ stats->estimated_count = false; stats->num_index_tuples = 0; stats->pages_deleted = 0; /* Set up info to pass down to btvacuumpage */ vstate.info = info; vstate.stats = stats; vstate.callback = callback; vstate.callback_state = callback_state; vstate.cycleid = cycleid; vstate.lastBlockVacuumed = BTREE_METAPAGE; /* Initialise at first block */ vstate.lastBlockLocked = BTREE_METAPAGE; vstate.totFreePages = 0; /* Create a temporary memory context to run _bt_pagedel in */ vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext, "_bt_pagedel", ALLOCSET_DEFAULT_SIZES); /* * The outer loop iterates over all index pages except the metapage, in * physical order (we hope the kernel will cooperate in providing * read-ahead for speed). It is critical that we visit all leaf pages, * including ones added after we start the scan, else we might fail to * delete some deletable tuples. Hence, we must repeatedly check the * relation length. We must acquire the relation-extension lock while * doing so to avoid a race condition: if someone else is extending the * relation, there is a window where bufmgr/smgr have created a new * all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If * we manage to scan such a page here, we'll improperly assume it can be * recycled. Taking the lock synchronizes things enough to prevent a * problem: either num_pages won't include the new page, or _bt_getbuf * already has write lock on the buffer and it will be fully initialized * before we can examine it. (See also vacuumlazy.c, which has the same * issue.) Also, we need not worry if a page is added immediately after * we look; the page splitting code already has write-lock on the left * page before it adds a right page, so we must already have processed any * tuples due to be moved into such a page. * * We can skip locking for new or temp relations, however, since no one * else could be accessing them. */ needLock = !RELATION_IS_LOCAL(rel); blkno = BTREE_METAPAGE + 1; for (;;) { /* Get the current relation length */ if (needLock) LockRelationForExtension(rel, ExclusiveLock); num_pages = RelationGetNumberOfBlocks(rel); if (needLock) UnlockRelationForExtension(rel, ExclusiveLock); /* Quit if we've scanned the whole relation */ if (blkno >= num_pages) break; /* Iterate over pages, then loop back to recheck length */ for (; blkno < num_pages; blkno++) { btvacuumpage(&vstate, blkno, blkno); } } /* * Check to see if we need to issue one final WAL record for this index, * which may be needed for correctness on a hot standby node when non-MVCC * index scans could take place. * * If the WAL is replayed in hot standby, the replay process needs to get * cleanup locks on all index leaf pages, just as we've been doing here. * However, we won't issue any WAL records about pages that have no items * to be deleted. For pages between pages we've vacuumed, the replay code * will take locks under the direction of the lastBlockVacuumed fields in * the XLOG_BTREE_VACUUM WAL records. To cover pages after the last one * we vacuum, we need to issue a dummy XLOG_BTREE_VACUUM WAL record * against the last leaf page in the index, if that one wasn't vacuumed. */ if (XLogStandbyInfoActive() && vstate.lastBlockVacuumed < vstate.lastBlockLocked) { Buffer buf; /* * The page should be valid, but we can't use _bt_getbuf() because we * want to use a nondefault buffer access strategy. Since we aren't * going to delete any items, getting cleanup lock again is probably * overkill, but for consistency do that anyway. */ buf = ReadBufferExtended(rel, MAIN_FORKNUM, vstate.lastBlockLocked, RBM_NORMAL, info->strategy); LockBufferForCleanup(buf); _bt_checkpage(rel, buf); _bt_delitems_vacuum(rel, buf, NULL, 0, vstate.lastBlockVacuumed); _bt_relbuf(rel, buf); } MemoryContextDelete(vstate.pagedelcontext); /* update statistics */ stats->num_pages = num_pages; stats->pages_free = vstate.totFreePages; }
/* * btvacuumscan --- scan the index for VACUUMing purposes * * This combines the functions of looking for leaf tuples that are deletable * according to the vacuum callback, looking for empty pages that can be * deleted, and looking for old deleted pages that can be recycled. Both * btbulkdelete and btvacuumcleanup invoke this (the latter only if no * btbulkdelete call occurred). * * The caller is responsible for initially allocating/zeroing a stats struct * and for obtaining a vacuum cycle ID if necessary. */ static void btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state, BTCycleId cycleid) { Relation rel = info->index; BTVacState vstate; BlockNumber num_pages; BlockNumber blkno; bool needLock; /* * Reset counts that will be incremented during the scan; needed in case * of multiple scans during a single VACUUM command */ stats->estimated_count = false; stats->num_index_tuples = 0; stats->pages_deleted = 0; /* Set up info to pass down to btvacuumpage */ vstate.info = info; vstate.stats = stats; vstate.callback = callback; vstate.callback_state = callback_state; vstate.cycleid = cycleid; vstate.lastBlockVacuumed = BTREE_METAPAGE; /* Initialise at first block */ vstate.lastUsedPage = BTREE_METAPAGE; vstate.totFreePages = 0; /* Create a temporary memory context to run _bt_pagedel in */ vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext, "_bt_pagedel", ALLOCSET_DEFAULT_MINSIZE, ALLOCSET_DEFAULT_INITSIZE, ALLOCSET_DEFAULT_MAXSIZE); /* * The outer loop iterates over all index pages except the metapage, in * physical order (we hope the kernel will cooperate in providing * read-ahead for speed). It is critical that we visit all leaf pages, * including ones added after we start the scan, else we might fail to * delete some deletable tuples. Hence, we must repeatedly check the * relation length. We must acquire the relation-extension lock while * doing so to avoid a race condition: if someone else is extending the * relation, there is a window where bufmgr/smgr have created a new * all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If * we manage to scan such a page here, we'll improperly assume it can be * recycled. Taking the lock synchronizes things enough to prevent a * problem: either num_pages won't include the new page, or _bt_getbuf * already has write lock on the buffer and it will be fully initialized * before we can examine it. (See also vacuumlazy.c, which has the same * issue.) Also, we need not worry if a page is added immediately after * we look; the page splitting code already has write-lock on the left * page before it adds a right page, so we must already have processed any * tuples due to be moved into such a page. * * We can skip locking for new or temp relations, however, since no one * else could be accessing them. */ needLock = !RELATION_IS_LOCAL(rel); blkno = BTREE_METAPAGE + 1; for (;;) { /* Get the current relation length */ if (needLock) LockRelationForExtension(rel, ExclusiveLock); num_pages = RelationGetNumberOfBlocks(rel); if (needLock) UnlockRelationForExtension(rel, ExclusiveLock); /* Quit if we've scanned the whole relation */ if (blkno >= num_pages) break; /* Iterate over pages, then loop back to recheck length */ for (; blkno < num_pages; blkno++) { btvacuumpage(&vstate, blkno, blkno); } } /* * InHotStandby we need to scan right up to the end of the index for * correct locking, so we may need to write a WAL record for the final * block in the index if it was not vacuumed. It's possible that VACUUMing * has actually removed zeroed pages at the end of the index so we need to * take care to issue the record for last actual block and not for the * last block that was scanned. Ignore empty indexes. */ if (XLogStandbyInfoActive() && num_pages > 1 && vstate.lastBlockVacuumed < (num_pages - 1)) { Buffer buf; /* * We can't use _bt_getbuf() here because it always applies * _bt_checkpage(), which will barf on an all-zero page. We want to * recycle all-zero pages, not fail. Also, we want to use a * nondefault buffer access strategy. */ buf = ReadBufferExtended(rel, MAIN_FORKNUM, num_pages - 1, RBM_NORMAL, info->strategy); LockBufferForCleanup(buf); _bt_delitems_vacuum(rel, buf, NULL, 0, vstate.lastBlockVacuumed); _bt_relbuf(rel, buf); } MemoryContextDelete(vstate.pagedelcontext); /* update statistics */ stats->num_pages = num_pages; stats->pages_free = vstate.totFreePages; }
/* * _bt_getbuf() -- Get a buffer by block number for read or write. * * blkno == P_NEW means to get an unallocated index page. The page * will be initialized before returning it. * * When this routine returns, the appropriate lock is set on the * requested buffer and its reference count has been incremented * (ie, the buffer is "locked and pinned"). Also, we apply * _bt_checkpage to sanity-check the page (except in P_NEW case). */ Buffer _bt_getbuf(Relation rel, BlockNumber blkno, int access) { Buffer buf; if (blkno != P_NEW) { /* Read an existing block of the relation */ buf = ReadBuffer(rel, blkno); LockBuffer(buf, access); _bt_checkpage(rel, buf); } else { bool needLock; Page page; Assert(access == BT_WRITE); /* * First see if the FSM knows of any free pages. * * We can't trust the FSM's report unreservedly; we have to check that * the page is still free. (For example, an already-free page could * have been re-used between the time the last VACUUM scanned it and * the time the VACUUM made its FSM updates.) * * In fact, it's worse than that: we can't even assume that it's safe * to take a lock on the reported page. If somebody else has a lock * on it, or even worse our own caller does, we could deadlock. (The * own-caller scenario is actually not improbable. Consider an index * on a serial or timestamp column. Nearly all splits will be at the * rightmost page, so it's entirely likely that _bt_split will call us * while holding a lock on the page most recently acquired from FSM. A * VACUUM running concurrently with the previous split could well have * placed that page back in FSM.) * * To get around that, we ask for only a conditional lock on the * reported page. If we fail, then someone else is using the page, * and we may reasonably assume it's not free. (If we happen to be * wrong, the worst consequence is the page will be lost to use till * the next VACUUM, which is no big problem.) */ for (;;) { blkno = GetFreeIndexPage(rel); if (blkno == InvalidBlockNumber) break; buf = ReadBuffer(rel, blkno); if (ConditionalLockBuffer(buf)) { page = BufferGetPage(buf); if (_bt_page_recyclable(page)) { /* * If we are generating WAL for Hot Standby then create a * WAL record that will allow us to conflict with queries * running on standby. */ if (XLogStandbyInfoActive()) { TransactionId latestRemovedXid; BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page); /* * opaque->btpo.xact is the threshold value not the * value to measure conflicts against. We must retreat * by one from it to get the correct conflict xid. */ latestRemovedXid = opaque->btpo.xact; TransactionIdRetreat(latestRemovedXid); _bt_log_reuse_page(rel, blkno, latestRemovedXid); } /* Okay to use page. Re-initialize and return it */ _bt_pageinit(page, BufferGetPageSize(buf)); return buf; } elog(DEBUG2, "FSM returned nonrecyclable page"); _bt_relbuf(rel, buf); } else { elog(DEBUG2, "FSM returned nonlockable page"); /* couldn't get lock, so just drop pin */ ReleaseBuffer(buf); } } /* * Extend the relation by one page. * * We have to use a lock to ensure no one else is extending the rel at * the same time, else we will both try to initialize the same new * page. We can skip locking for new or temp relations, however, * since no one else could be accessing them. */ needLock = !RELATION_IS_LOCAL(rel); if (needLock) LockRelationForExtension(rel, ExclusiveLock); buf = ReadBuffer(rel, P_NEW); /* Acquire buffer lock on new page */ LockBuffer(buf, BT_WRITE); /* * Release the file-extension lock; it's now OK for someone else to * extend the relation some more. Note that we cannot release this * lock before we have buffer lock on the new page, or we risk a race * condition against btvacuumscan --- see comments therein. */ if (needLock) UnlockRelationForExtension(rel, ExclusiveLock); /* Initialize the new page before returning it */ page = BufferGetPage(buf); Assert(PageIsNew(page)); _bt_pageinit(page, BufferGetPageSize(buf)); } /* ref count and lock type are correct */ return buf; }
/* * 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; /* * Properly accept or ignore signals the postmaster might send us. * * bgwriter doesn't participate in ProcSignal signalling, but a SIGUSR1 * handler is still needed for latch wakeups. */ pqsignal(SIGHUP, BgSigHupHandler); /* set flag to read config file */ pqsignal(SIGINT, SIG_IGN); pqsignal(SIGTERM, ReqShutdownHandler); /* shutdown */ pqsignal(SIGQUIT, bg_quickdie); /* hard crash time */ pqsignal(SIGALRM, SIG_IGN); pqsignal(SIGPIPE, SIG_IGN); pqsignal(SIGUSR1, bgwriter_sigusr1_handler); pqsignal(SIGUSR2, SIG_IGN); /* * Reset some signals that are accepted by postmaster but not here */ pqsignal(SIGCHLD, SIG_DFL); pqsignal(SIGTTIN, SIG_DFL); pqsignal(SIGTTOU, SIG_DFL); pqsignal(SIGCONT, SIG_DFL); pqsignal(SIGWINCH, SIG_DFL); /* We allow SIGQUIT (quickdie) at all times */ sigdelset(&BlockSig, SIGQUIT); /* * Create a resource owner to keep track of our resources (currently only * buffer pins). */ CurrentResourceOwner = ResourceOwnerCreate(NULL, "Background Writer"); /* * 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_MINSIZE, ALLOCSET_DEFAULT_INITSIZE, ALLOCSET_DEFAULT_MAXSIZE); MemoryContextSwitchTo(bgwriter_context); /* * If an exception is encountered, processing resumes here. * * See notes in postgres.c about the design of this coding. */ 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(); AbortBufferIO(); UnlockBuffers(); /* buffer pins are released here: */ ResourceOwnerRelease(CurrentResourceOwner, RESOURCE_RELEASE_BEFORE_LOCKS, false, true); /* we needn't bother with the other ResourceOwnerRelease phases */ AtEOXact_Buffers(false); AtEOXact_SMgr(); AtEOXact_Files(); 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); /* 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); if (got_SIGHUP) { got_SIGHUP = false; ProcessConfigFile(PGC_SIGHUP); } if (shutdown_requested) { /* * From here on, elog(ERROR) should end with exit(1), not send * control back to the sigsetjmp block above */ ExitOnAnyError = true; /* Normal exit from the bgwriter is here */ proc_exit(0); /* done */ } /* * Do one cycle of dirty-buffer writing. */ can_hibernate = BgBufferSync(); /* * 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_snap_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 its 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 some xlog record has * been inserted. */ if (now >= timeout && last_snapshot_lsn != GetXLogInsertRecPtr()) { 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_POSTMASTER_DEATH, BgWriterDelay /* ms */ ); /* * 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 ... */ rc = WaitLatch(MyLatch, WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, BgWriterDelay * HIBERNATE_FACTOR); /* Reset the notification request in case we timed out */ StrategyNotifyBgWriter(-1); } /* * Emergency bailout if postmaster has died. This is to avoid the * necessity for manual cleanup of all postmaster children. */ if (rc & WL_POSTMASTER_DEATH) exit(1); prev_hibernate = can_hibernate; } }