diff options
Diffstat (limited to 'src/backend')
59 files changed, 980 insertions, 778 deletions
diff --git a/src/backend/access/rmgrdesc/replorigindesc.c b/src/backend/access/rmgrdesc/replorigindesc.c index 5dd74233996..35e3af2903e 100644 --- a/src/backend/access/rmgrdesc/replorigindesc.c +++ b/src/backend/access/rmgrdesc/replorigindesc.c @@ -29,7 +29,7 @@ replorigin_desc(StringInfo buf, XLogReaderState *record) xlrec = (xl_replorigin_set *) rec; - appendStringInfo(buf, "set %u; lsn %X/%X; force: %d", + appendStringInfo(buf, "set %u; lsn %X/%08X; force: %d", xlrec->node_id, LSN_FORMAT_ARGS(xlrec->remote_lsn), xlrec->force); diff --git a/src/backend/access/rmgrdesc/xactdesc.c b/src/backend/access/rmgrdesc/xactdesc.c index 305598e2865..f0f696855b9 100644 --- a/src/backend/access/rmgrdesc/xactdesc.c +++ b/src/backend/access/rmgrdesc/xactdesc.c @@ -359,7 +359,7 @@ xact_desc_commit(StringInfo buf, uint8 info, xl_xact_commit *xlrec, RepOriginId if (parsed.xinfo & XACT_XINFO_HAS_ORIGIN) { - appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s", + appendStringInfo(buf, "; origin: node %u, lsn %X/%08X, at %s", origin_id, LSN_FORMAT_ARGS(parsed.origin_lsn), timestamptz_to_str(parsed.origin_timestamp)); @@ -384,7 +384,7 @@ xact_desc_abort(StringInfo buf, uint8 info, xl_xact_abort *xlrec, RepOriginId or if (parsed.xinfo & XACT_XINFO_HAS_ORIGIN) { - appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s", + appendStringInfo(buf, "; origin: node %u, lsn %X/%08X, at %s", origin_id, LSN_FORMAT_ARGS(parsed.origin_lsn), timestamptz_to_str(parsed.origin_timestamp)); @@ -418,7 +418,7 @@ xact_desc_prepare(StringInfo buf, uint8 info, xl_xact_prepare *xlrec, RepOriginI * way as PrepareRedoAdd(). */ if (origin_id != InvalidRepOriginId) - appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s", + appendStringInfo(buf, "; origin: node %u, lsn %X/%08X, at %s", origin_id, LSN_FORMAT_ARGS(parsed.origin_lsn), timestamptz_to_str(parsed.origin_timestamp)); diff --git a/src/backend/access/rmgrdesc/xlogdesc.c b/src/backend/access/rmgrdesc/xlogdesc.c index 58040f28656..cd6c2a2f650 100644 --- a/src/backend/access/rmgrdesc/xlogdesc.c +++ b/src/backend/access/rmgrdesc/xlogdesc.c @@ -65,7 +65,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record) { CheckPoint *checkpoint = (CheckPoint *) rec; - appendStringInfo(buf, "redo %X/%X; " + appendStringInfo(buf, "redo %X/%08X; " "tli %u; prev tli %u; fpw %s; wal_level %s; xid %u:%u; oid %u; multi %u; offset %u; " "oldest xid %u in DB %u; oldest multi %u in DB %u; " "oldest/newest commit timestamp xid: %u/%u; " @@ -111,7 +111,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record) XLogRecPtr startpoint; memcpy(&startpoint, rec, sizeof(XLogRecPtr)); - appendStringInfo(buf, "%X/%X", LSN_FORMAT_ARGS(startpoint)); + appendStringInfo(buf, "%X/%08X", LSN_FORMAT_ARGS(startpoint)); } else if (info == XLOG_PARAMETER_CHANGE) { @@ -156,7 +156,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record) xl_overwrite_contrecord xlrec; memcpy(&xlrec, rec, sizeof(xl_overwrite_contrecord)); - appendStringInfo(buf, "lsn %X/%X; time %s", + appendStringInfo(buf, "lsn %X/%08X; time %s", LSN_FORMAT_ARGS(xlrec.overwritten_lsn), timestamptz_to_str(xlrec.overwrite_time)); } diff --git a/src/backend/access/transam/clog.c b/src/backend/access/transam/clog.c index 48f10bec91e..e80fbe109cf 100644 --- a/src/backend/access/transam/clog.c +++ b/src/backend/access/transam/clog.c @@ -110,9 +110,7 @@ static SlruCtlData XactCtlData; #define XactCtl (&XactCtlData) -static int ZeroCLOGPage(int64 pageno, bool writeXlog); static bool CLOGPagePrecedes(int64 page1, int64 page2); -static void WriteZeroPageXlogRec(int64 pageno); static void WriteTruncateXlogRec(int64 pageno, TransactionId oldestXact, Oid oldestXactDb); static void TransactionIdSetPageStatus(TransactionId xid, int nsubxids, @@ -832,41 +830,8 @@ check_transaction_buffers(int *newval, void **extra, GucSource source) void BootStrapCLOG(void) { - int slotno; - LWLock *lock = SimpleLruGetBankLock(XactCtl, 0); - - LWLockAcquire(lock, LW_EXCLUSIVE); - - /* Create and zero the first page of the commit log */ - slotno = ZeroCLOGPage(0, false); - - /* Make sure it's written out */ - SimpleLruWritePage(XactCtl, slotno); - Assert(!XactCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); -} - -/* - * Initialize (or reinitialize) a page of CLOG to zeroes. - * If writeXlog is true, also emit an XLOG record saying we did this. - * - * The page is not actually written, just set up in shared memory. - * The slot number of the new page is returned. - * - * Control lock must be held at entry, and will be held at exit. - */ -static int -ZeroCLOGPage(int64 pageno, bool writeXlog) -{ - int slotno; - - slotno = SimpleLruZeroPage(XactCtl, pageno); - - if (writeXlog) - WriteZeroPageXlogRec(pageno); - - return slotno; + /* Zero the initial page and flush it to disk */ + SimpleLruZeroAndWritePage(XactCtl, 0); } /* @@ -974,8 +939,9 @@ ExtendCLOG(TransactionId newestXact) LWLockAcquire(lock, LW_EXCLUSIVE); - /* Zero the page and make an XLOG entry about it */ - ZeroCLOGPage(pageno, true); + /* Zero the page and make a WAL entry about it */ + SimpleLruZeroPage(XactCtl, pageno); + XLogSimpleInsertInt64(RM_CLOG_ID, CLOG_ZEROPAGE, pageno); LWLockRelease(lock); } @@ -1068,17 +1034,6 @@ CLOGPagePrecedes(int64 page1, int64 page2) /* - * Write a ZEROPAGE xlog record - */ -static void -WriteZeroPageXlogRec(int64 pageno) -{ - XLogBeginInsert(); - XLogRegisterData(&pageno, sizeof(pageno)); - (void) XLogInsert(RM_CLOG_ID, CLOG_ZEROPAGE); -} - -/* * Write a TRUNCATE xlog record * * We must flush the xlog record to disk before returning --- see notes @@ -1114,19 +1069,9 @@ clog_redo(XLogReaderState *record) if (info == CLOG_ZEROPAGE) { int64 pageno; - int slotno; - LWLock *lock; memcpy(&pageno, XLogRecGetData(record), sizeof(pageno)); - - lock = SimpleLruGetBankLock(XactCtl, pageno); - LWLockAcquire(lock, LW_EXCLUSIVE); - - slotno = ZeroCLOGPage(pageno, false); - SimpleLruWritePage(XactCtl, slotno); - Assert(!XactCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); + SimpleLruZeroAndWritePage(XactCtl, pageno); } else if (info == CLOG_TRUNCATE) { diff --git a/src/backend/access/transam/commit_ts.c b/src/backend/access/transam/commit_ts.c index 225ff7ca9f2..370b38e048b 100644 --- a/src/backend/access/transam/commit_ts.c +++ b/src/backend/access/transam/commit_ts.c @@ -114,11 +114,9 @@ static void SetXidCommitTsInPage(TransactionId xid, int nsubxids, static void TransactionIdSetCommitTs(TransactionId xid, TimestampTz ts, RepOriginId nodeid, int slotno); static void error_commit_ts_disabled(void); -static int ZeroCommitTsPage(int64 pageno, bool writeXlog); static bool CommitTsPagePrecedes(int64 page1, int64 page2); static void ActivateCommitTs(void); static void DeactivateCommitTs(void); -static void WriteZeroPageXlogRec(int64 pageno); static void WriteTruncateXlogRec(int64 pageno, TransactionId oldestXid); /* @@ -603,28 +601,6 @@ BootStrapCommitTs(void) } /* - * Initialize (or reinitialize) a page of CommitTs to zeroes. - * If writeXlog is true, also emit an XLOG record saying we did this. - * - * The page is not actually written, just set up in shared memory. - * The slot number of the new page is returned. - * - * Control lock must be held at entry, and will be held at exit. - */ -static int -ZeroCommitTsPage(int64 pageno, bool writeXlog) -{ - int slotno; - - slotno = SimpleLruZeroPage(CommitTsCtl, pageno); - - if (writeXlog) - WriteZeroPageXlogRec(pageno); - - return slotno; -} - -/* * This must be called ONCE during postmaster or standalone-backend startup, * after StartupXLOG has initialized TransamVariables->nextXid. */ @@ -754,16 +730,7 @@ ActivateCommitTs(void) /* Create the current segment file, if necessary */ if (!SimpleLruDoesPhysicalPageExist(CommitTsCtl, pageno)) - { - LWLock *lock = SimpleLruGetBankLock(CommitTsCtl, pageno); - int slotno; - - LWLockAcquire(lock, LW_EXCLUSIVE); - slotno = ZeroCommitTsPage(pageno, false); - SimpleLruWritePage(CommitTsCtl, slotno); - Assert(!CommitTsCtl->shared->page_dirty[slotno]); - LWLockRelease(lock); - } + SimpleLruZeroAndWritePage(CommitTsCtl, pageno); /* Change the activation status in shared memory. */ LWLockAcquire(CommitTsLock, LW_EXCLUSIVE); @@ -874,8 +841,12 @@ ExtendCommitTs(TransactionId newestXact) LWLockAcquire(lock, LW_EXCLUSIVE); - /* Zero the page and make an XLOG entry about it */ - ZeroCommitTsPage(pageno, !InRecovery); + /* Zero the page ... */ + SimpleLruZeroPage(CommitTsCtl, pageno); + + /* and make a WAL entry about that, unless we're in REDO */ + if (!InRecovery) + XLogSimpleInsertInt64(RM_COMMIT_TS_ID, COMMIT_TS_ZEROPAGE, pageno); LWLockRelease(lock); } @@ -990,17 +961,6 @@ CommitTsPagePrecedes(int64 page1, int64 page2) /* - * Write a ZEROPAGE xlog record - */ -static void -WriteZeroPageXlogRec(int64 pageno) -{ - XLogBeginInsert(); - XLogRegisterData(&pageno, sizeof(pageno)); - (void) XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_ZEROPAGE); -} - -/* * Write a TRUNCATE xlog record */ static void @@ -1030,19 +990,9 @@ commit_ts_redo(XLogReaderState *record) if (info == COMMIT_TS_ZEROPAGE) { int64 pageno; - int slotno; - LWLock *lock; memcpy(&pageno, XLogRecGetData(record), sizeof(pageno)); - - lock = SimpleLruGetBankLock(CommitTsCtl, pageno); - LWLockAcquire(lock, LW_EXCLUSIVE); - - slotno = ZeroCommitTsPage(pageno, false); - SimpleLruWritePage(CommitTsCtl, slotno); - Assert(!CommitTsCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); + SimpleLruZeroAndWritePage(CommitTsCtl, pageno); } else if (info == COMMIT_TS_TRUNCATE) { diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c index 7a7afe3edc6..3cb09c3d598 100644 --- a/src/backend/access/transam/multixact.c +++ b/src/backend/access/transam/multixact.c @@ -401,8 +401,6 @@ static void mXactCachePut(MultiXactId multi, int nmembers, static char *mxstatus_to_string(MultiXactStatus status); /* management of SLRU infrastructure */ -static int ZeroMultiXactOffsetPage(int64 pageno, bool writeXlog); -static int ZeroMultiXactMemberPage(int64 pageno, bool writeXlog); static bool MultiXactOffsetPagePrecedes(int64 page1, int64 page2); static bool MultiXactMemberPagePrecedes(int64 page1, int64 page2); static bool MultiXactOffsetPrecedes(MultiXactOffset offset1, @@ -413,7 +411,6 @@ static bool MultiXactOffsetWouldWrap(MultiXactOffset boundary, MultiXactOffset start, uint32 distance); static bool SetOffsetVacuumLimit(bool is_startup); static bool find_multixact_start(MultiXactId multi, MultiXactOffset *result); -static void WriteMZeroPageXlogRec(int64 pageno, uint8 info); static void WriteMTruncateXlogRec(Oid oldestMultiDB, MultiXactId startTruncOff, MultiXactId endTruncOff, @@ -2033,70 +2030,9 @@ check_multixact_member_buffers(int *newval, void **extra, GucSource source) void BootStrapMultiXact(void) { - int slotno; - LWLock *lock; - - lock = SimpleLruGetBankLock(MultiXactOffsetCtl, 0); - LWLockAcquire(lock, LW_EXCLUSIVE); - - /* Create and zero the first page of the offsets log */ - slotno = ZeroMultiXactOffsetPage(0, false); - - /* Make sure it's written out */ - SimpleLruWritePage(MultiXactOffsetCtl, slotno); - Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); - - lock = SimpleLruGetBankLock(MultiXactMemberCtl, 0); - LWLockAcquire(lock, LW_EXCLUSIVE); - - /* Create and zero the first page of the members log */ - slotno = ZeroMultiXactMemberPage(0, false); - - /* Make sure it's written out */ - SimpleLruWritePage(MultiXactMemberCtl, slotno); - Assert(!MultiXactMemberCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); -} - -/* - * Initialize (or reinitialize) a page of MultiXactOffset to zeroes. - * If writeXlog is true, also emit an XLOG record saying we did this. - * - * The page is not actually written, just set up in shared memory. - * The slot number of the new page is returned. - * - * Control lock must be held at entry, and will be held at exit. - */ -static int -ZeroMultiXactOffsetPage(int64 pageno, bool writeXlog) -{ - int slotno; - - slotno = SimpleLruZeroPage(MultiXactOffsetCtl, pageno); - - if (writeXlog) - WriteMZeroPageXlogRec(pageno, XLOG_MULTIXACT_ZERO_OFF_PAGE); - - return slotno; -} - -/* - * Ditto, for MultiXactMember - */ -static int -ZeroMultiXactMemberPage(int64 pageno, bool writeXlog) -{ - int slotno; - - slotno = SimpleLruZeroPage(MultiXactMemberCtl, pageno); - - if (writeXlog) - WriteMZeroPageXlogRec(pageno, XLOG_MULTIXACT_ZERO_MEM_PAGE); - - return slotno; + /* Zero the initial pages and flush them to disk */ + SimpleLruZeroAndWritePage(MultiXactOffsetCtl, 0); + SimpleLruZeroAndWritePage(MultiXactMemberCtl, 0); } /* @@ -2134,7 +2070,7 @@ MaybeExtendOffsetSlru(void) * with creating a new segment file even if the page we're writing is * not the first in it, so this is enough. */ - slotno = ZeroMultiXactOffsetPage(pageno, false); + slotno = SimpleLruZeroPage(MultiXactOffsetCtl, pageno); SimpleLruWritePage(MultiXactOffsetCtl, slotno); } @@ -2568,8 +2504,10 @@ ExtendMultiXactOffset(MultiXactId multi) LWLockAcquire(lock, LW_EXCLUSIVE); - /* Zero the page and make an XLOG entry about it */ - ZeroMultiXactOffsetPage(pageno, true); + /* Zero the page and make a WAL entry about it */ + SimpleLruZeroPage(MultiXactOffsetCtl, pageno); + XLogSimpleInsertInt64(RM_MULTIXACT_ID, XLOG_MULTIXACT_ZERO_OFF_PAGE, + pageno); LWLockRelease(lock); } @@ -2611,8 +2549,10 @@ ExtendMultiXactMember(MultiXactOffset offset, int nmembers) LWLockAcquire(lock, LW_EXCLUSIVE); - /* Zero the page and make an XLOG entry about it */ - ZeroMultiXactMemberPage(pageno, true); + /* Zero the page and make a WAL entry about it */ + SimpleLruZeroPage(MultiXactMemberCtl, pageno); + XLogSimpleInsertInt64(RM_MULTIXACT_ID, + XLOG_MULTIXACT_ZERO_MEM_PAGE, pageno); LWLockRelease(lock); } @@ -3348,18 +3288,6 @@ MultiXactOffsetPrecedes(MultiXactOffset offset1, MultiXactOffset offset2) } /* - * Write an xlog record reflecting the zeroing of either a MEMBERs or - * OFFSETs page (info shows which) - */ -static void -WriteMZeroPageXlogRec(int64 pageno, uint8 info) -{ - XLogBeginInsert(); - XLogRegisterData(&pageno, sizeof(pageno)); - (void) XLogInsert(RM_MULTIXACT_ID, info); -} - -/* * Write a TRUNCATE xlog record * * We must flush the xlog record to disk before returning --- see notes in @@ -3401,36 +3329,16 @@ multixact_redo(XLogReaderState *record) if (info == XLOG_MULTIXACT_ZERO_OFF_PAGE) { int64 pageno; - int slotno; - LWLock *lock; memcpy(&pageno, XLogRecGetData(record), sizeof(pageno)); - - lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno); - LWLockAcquire(lock, LW_EXCLUSIVE); - - slotno = ZeroMultiXactOffsetPage(pageno, false); - SimpleLruWritePage(MultiXactOffsetCtl, slotno); - Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); + SimpleLruZeroAndWritePage(MultiXactOffsetCtl, pageno); } else if (info == XLOG_MULTIXACT_ZERO_MEM_PAGE) { int64 pageno; - int slotno; - LWLock *lock; memcpy(&pageno, XLogRecGetData(record), sizeof(pageno)); - - lock = SimpleLruGetBankLock(MultiXactMemberCtl, pageno); - LWLockAcquire(lock, LW_EXCLUSIVE); - - slotno = ZeroMultiXactMemberPage(pageno, false); - SimpleLruWritePage(MultiXactMemberCtl, slotno); - Assert(!MultiXactMemberCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); + SimpleLruZeroAndWritePage(MultiXactMemberCtl, pageno); } else if (info == XLOG_MULTIXACT_CREATE_ID) { diff --git a/src/backend/access/transam/slru.c b/src/backend/access/transam/slru.c index fe56286d9a9..10ec259f382 100644 --- a/src/backend/access/transam/slru.c +++ b/src/backend/access/transam/slru.c @@ -434,6 +434,31 @@ SimpleLruZeroLSNs(SlruCtl ctl, int slotno) } /* + * This is a convenience wrapper for the common case of zeroing a page and + * immediately flushing it to disk. + * + * Control lock is acquired and released here. + */ +void +SimpleLruZeroAndWritePage(SlruCtl ctl, int64 pageno) +{ + int slotno; + LWLock *lock; + + lock = SimpleLruGetBankLock(ctl, pageno); + LWLockAcquire(lock, LW_EXCLUSIVE); + + /* Create and zero the page */ + slotno = SimpleLruZeroPage(ctl, pageno); + + /* Make sure it's written out */ + SimpleLruWritePage(ctl, slotno); + Assert(!ctl->shared->page_dirty[slotno]); + + LWLockRelease(lock); +} + +/* * Wait for any active I/O on a page slot to finish. (This does not * guarantee that new I/O hasn't been started before we return, though. * In fact the slot might not even contain the same page anymore.) diff --git a/src/backend/access/transam/subtrans.c b/src/backend/access/transam/subtrans.c index 15153618fad..09aace9e09f 100644 --- a/src/backend/access/transam/subtrans.c +++ b/src/backend/access/transam/subtrans.c @@ -74,7 +74,6 @@ static SlruCtlData SubTransCtlData; #define SubTransCtl (&SubTransCtlData) -static int ZeroSUBTRANSPage(int64 pageno); static bool SubTransPagePrecedes(int64 page1, int64 page2); @@ -269,33 +268,8 @@ check_subtrans_buffers(int *newval, void **extra, GucSource source) void BootStrapSUBTRANS(void) { - int slotno; - LWLock *lock = SimpleLruGetBankLock(SubTransCtl, 0); - - LWLockAcquire(lock, LW_EXCLUSIVE); - - /* Create and zero the first page of the subtrans log */ - slotno = ZeroSUBTRANSPage(0); - - /* Make sure it's written out */ - SimpleLruWritePage(SubTransCtl, slotno); - Assert(!SubTransCtl->shared->page_dirty[slotno]); - - LWLockRelease(lock); -} - -/* - * Initialize (or reinitialize) a page of SUBTRANS to zeroes. - * - * The page is not actually written, just set up in shared memory. - * The slot number of the new page is returned. - * - * Control lock must be held at entry, and will be held at exit. - */ -static int -ZeroSUBTRANSPage(int64 pageno) -{ - return SimpleLruZeroPage(SubTransCtl, pageno); + /* Zero the initial page and flush it to disk */ + SimpleLruZeroAndWritePage(SubTransCtl, 0); } /* @@ -335,7 +309,7 @@ StartupSUBTRANS(TransactionId oldestActiveXID) prevlock = lock; } - (void) ZeroSUBTRANSPage(startPage); + (void) SimpleLruZeroPage(SubTransCtl, startPage); if (startPage == endPage) break; @@ -395,7 +369,7 @@ ExtendSUBTRANS(TransactionId newestXact) LWLockAcquire(lock, LW_EXCLUSIVE); /* Zero the page */ - ZeroSUBTRANSPage(pageno); + SimpleLruZeroPage(SubTransCtl, pageno); LWLockRelease(lock); } diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index a27f27cc037..186eb91f609 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -154,7 +154,7 @@ readTimeLineHistory(TimeLineID targetTLI) if (*ptr == '\0' || *ptr == '#') continue; - nfields = sscanf(fline, "%u\t%X/%X", &tli, &switchpoint_hi, &switchpoint_lo); + nfields = sscanf(fline, "%u\t%X/%08X", &tli, &switchpoint_hi, &switchpoint_lo); if (nfields < 1) { @@ -399,7 +399,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, * parent file failed to end with one. */ snprintf(buffer, sizeof(buffer), - "%s%u\t%X/%X\t%s\n", + "%s%u\t%X/%08X\t%s\n", (srcfd < 0) ? "" : "\n", parentTLI, LSN_FORMAT_ARGS(switchpoint), diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index 8975dc6d3c8..85cbe397cb2 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -1429,12 +1429,12 @@ XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len) if (errormsg) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not read two-phase state from WAL at %X/%X: %s", + errmsg("could not read two-phase state from WAL at %X/%08X: %s", LSN_FORMAT_ARGS(lsn), errormsg))); else ereport(ERROR, (errcode_for_file_access(), - errmsg("could not read two-phase state from WAL at %X/%X", + errmsg("could not read two-phase state from WAL at %X/%08X", LSN_FORMAT_ARGS(lsn)))); } @@ -1442,7 +1442,7 @@ XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len) (XLogRecGetInfo(xlogreader) & XLOG_XACT_OPMASK) != XLOG_XACT_PREPARE) ereport(ERROR, (errcode_for_file_access(), - errmsg("expected two-phase state data is not present in WAL at %X/%X", + errmsg("expected two-phase state data is not present in WAL at %X/%08X", LSN_FORMAT_ARGS(lsn)))); if (len != NULL) @@ -2533,7 +2533,7 @@ PrepareRedoAdd(FullTransactionId fxid, char *buf, ereport(reachedConsistency ? ERROR : WARNING, (errmsg("could not recover two-phase state file for transaction %u", hdr->xid), - errdetail("Two-phase state file has been found in WAL record %X/%X, but this transaction has already been restored from disk.", + errdetail("Two-phase state file has been found in WAL record %X/%08X, but this transaction has already been restored from disk.", LSN_FORMAT_ARGS(start_lsn)))); return; } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 47ffc0a2307..88fb9b45b2a 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -1028,7 +1028,7 @@ XLogInsertRecord(XLogRecData *rdata, oldCxt = MemoryContextSwitchTo(walDebugCxt); initStringInfo(&buf); - appendStringInfo(&buf, "INSERT @ %X/%X: ", LSN_FORMAT_ARGS(EndPos)); + appendStringInfo(&buf, "INSERT @ %X/%08X: ", LSN_FORMAT_ARGS(EndPos)); /* * We have to piece together the WAL record data from the XLogRecData @@ -1549,8 +1549,8 @@ WaitXLogInsertionsToFinish(XLogRecPtr upto) if (upto > reservedUpto) { ereport(LOG, - (errmsg("request to flush past end of generated WAL; request %X/%X, current position %X/%X", - LSN_FORMAT_ARGS(upto), LSN_FORMAT_ARGS(reservedUpto)))); + errmsg("request to flush past end of generated WAL; request %X/%08X, current position %X/%08X", + LSN_FORMAT_ARGS(upto), LSN_FORMAT_ARGS(reservedUpto))); upto = reservedUpto; } @@ -1716,7 +1716,7 @@ GetXLogBuffer(XLogRecPtr ptr, TimeLineID tli) endptr = pg_atomic_read_u64(&XLogCtl->xlblocks[idx]); if (expectedEndPtr != endptr) - elog(PANIC, "could not find WAL buffer for %X/%X", + elog(PANIC, "could not find WAL buffer for %X/%08X", LSN_FORMAT_ARGS(ptr)); } else @@ -1776,7 +1776,7 @@ WALReadFromBuffers(char *dstbuf, XLogRecPtr startptr, Size count, inserted = pg_atomic_read_u64(&XLogCtl->logInsertResult); if (startptr + count > inserted) ereport(ERROR, - errmsg("cannot read past end of generated WAL: requested %X/%X, current position %X/%X", + errmsg("cannot read past end of generated WAL: requested %X/%08X, current position %X/%08X", LSN_FORMAT_ARGS(startptr + count), LSN_FORMAT_ARGS(inserted))); @@ -2281,7 +2281,7 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic) #ifdef WAL_DEBUG if (XLOG_DEBUG && npages > 0) { - elog(DEBUG1, "initialized %d pages, up to %X/%X", + elog(DEBUG1, "initialized %d pages, up to %X/%08X", npages, LSN_FORMAT_ARGS(NewPageEndPtr)); } #endif @@ -2347,25 +2347,6 @@ check_wal_segment_size(int *newval, void **extra, GucSource source) } /* - * GUC check_hook for max_slot_wal_keep_size - * - * We don't allow the value of max_slot_wal_keep_size other than -1 during the - * binary upgrade. See start_postmaster() in pg_upgrade for more details. - */ -bool -check_max_slot_wal_keep_size(int *newval, void **extra, GucSource source) -{ - if (IsBinaryUpgrade && *newval != -1) - { - GUC_check_errdetail("\"%s\" must be set to -1 during binary upgrade mode.", - "max_slot_wal_keep_size"); - return false; - } - - return true; -} - -/* * At a checkpoint, how many WAL segments to recycle as preallocated future * XLOG segments? Returns the highest segment that should be preallocated. */ @@ -2492,7 +2473,7 @@ XLogWrite(XLogwrtRqst WriteRqst, TimeLineID tli, bool flexible) XLogRecPtr EndPtr = pg_atomic_read_u64(&XLogCtl->xlblocks[curridx]); if (LogwrtResult.Write >= EndPtr) - elog(PANIC, "xlog write request %X/%X is past end of log %X/%X", + elog(PANIC, "xlog write request %X/%08X is past end of log %X/%08X", LSN_FORMAT_ARGS(LogwrtResult.Write), LSN_FORMAT_ARGS(EndPtr)); @@ -2892,7 +2873,7 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) newMinRecoveryPoint = GetCurrentReplayRecPtr(&newMinRecoveryPointTLI); if (!force && newMinRecoveryPoint < lsn) elog(WARNING, - "xlog min recovery request %X/%X is past current point %X/%X", + "xlog min recovery request %X/%08X is past current point %X/%08X", LSN_FORMAT_ARGS(lsn), LSN_FORMAT_ARGS(newMinRecoveryPoint)); /* update control file */ @@ -2905,9 +2886,9 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) LocalMinRecoveryPointTLI = newMinRecoveryPointTLI; ereport(DEBUG2, - (errmsg_internal("updated min recovery point to %X/%X on timeline %u", - LSN_FORMAT_ARGS(newMinRecoveryPoint), - newMinRecoveryPointTLI))); + errmsg_internal("updated min recovery point to %X/%08X on timeline %u", + LSN_FORMAT_ARGS(newMinRecoveryPoint), + newMinRecoveryPointTLI)); } } LWLockRelease(ControlFileLock); @@ -2945,7 +2926,7 @@ XLogFlush(XLogRecPtr record) #ifdef WAL_DEBUG if (XLOG_DEBUG) - elog(LOG, "xlog flush request %X/%X; write %X/%X; flush %X/%X", + elog(LOG, "xlog flush request %X/%08X; write %X/%08X; flush %X/%08X", LSN_FORMAT_ARGS(record), LSN_FORMAT_ARGS(LogwrtResult.Write), LSN_FORMAT_ARGS(LogwrtResult.Flush)); @@ -3078,7 +3059,7 @@ XLogFlush(XLogRecPtr record) */ if (LogwrtResult.Flush < record) elog(ERROR, - "xlog flush request %X/%X is not satisfied --- flushed only to %X/%X", + "xlog flush request %X/%08X is not satisfied --- flushed only to %X/%08X", LSN_FORMAT_ARGS(record), LSN_FORMAT_ARGS(LogwrtResult.Flush)); } @@ -3205,7 +3186,7 @@ XLogBackgroundFlush(void) #ifdef WAL_DEBUG if (XLOG_DEBUG) - elog(LOG, "xlog bg flush request write %X/%X; flush: %X/%X, current is write %X/%X; flush %X/%X", + elog(LOG, "xlog bg flush request write %X/%08X; flush: %X/%08X, current is write %X/%08X; flush %X/%08X", LSN_FORMAT_ARGS(WriteRqst.Write), LSN_FORMAT_ARGS(WriteRqst.Flush), LSN_FORMAT_ARGS(LogwrtResult.Write), @@ -6505,7 +6486,7 @@ PerformRecoveryXLogAction(void) else { RequestCheckpoint(CHECKPOINT_END_OF_RECOVERY | - CHECKPOINT_IMMEDIATE | + CHECKPOINT_FAST | CHECKPOINT_WAIT); } @@ -6814,7 +6795,7 @@ ShutdownXLOG(int code, Datum arg) WalSndWaitStopping(); if (RecoveryInProgress()) - CreateRestartPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE); + CreateRestartPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_FAST); else { /* @@ -6826,7 +6807,7 @@ ShutdownXLOG(int code, Datum arg) if (XLogArchivingActive()) RequestXLogSwitch(false); - CreateCheckPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE); + CreateCheckPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_FAST); } } @@ -6842,24 +6823,24 @@ LogCheckpointStart(int flags, bool restartpoint) (errmsg("restartpoint starting:%s%s%s%s%s%s%s%s", (flags & CHECKPOINT_IS_SHUTDOWN) ? " shutdown" : "", (flags & CHECKPOINT_END_OF_RECOVERY) ? " end-of-recovery" : "", - (flags & CHECKPOINT_IMMEDIATE) ? " immediate" : "", + (flags & CHECKPOINT_FAST) ? " fast" : "", (flags & CHECKPOINT_FORCE) ? " force" : "", (flags & CHECKPOINT_WAIT) ? " wait" : "", (flags & CHECKPOINT_CAUSE_XLOG) ? " wal" : "", (flags & CHECKPOINT_CAUSE_TIME) ? " time" : "", - (flags & CHECKPOINT_FLUSH_ALL) ? " flush-all" : ""))); + (flags & CHECKPOINT_FLUSH_UNLOGGED) ? " flush-unlogged" : ""))); else ereport(LOG, /* translator: the placeholders show checkpoint options */ (errmsg("checkpoint starting:%s%s%s%s%s%s%s%s", (flags & CHECKPOINT_IS_SHUTDOWN) ? " shutdown" : "", (flags & CHECKPOINT_END_OF_RECOVERY) ? " end-of-recovery" : "", - (flags & CHECKPOINT_IMMEDIATE) ? " immediate" : "", + (flags & CHECKPOINT_FAST) ? " fast" : "", (flags & CHECKPOINT_FORCE) ? " force" : "", (flags & CHECKPOINT_WAIT) ? " wait" : "", (flags & CHECKPOINT_CAUSE_XLOG) ? " wal" : "", (flags & CHECKPOINT_CAUSE_TIME) ? " time" : "", - (flags & CHECKPOINT_FLUSH_ALL) ? " flush-all" : ""))); + (flags & CHECKPOINT_FLUSH_UNLOGGED) ? " flush-unlogged" : ""))); } /* @@ -6921,7 +6902,7 @@ LogCheckpointEnd(bool restartpoint) "%d removed, %d recycled; write=%ld.%03d s, " "sync=%ld.%03d s, total=%ld.%03d s; sync files=%d, " "longest=%ld.%03d s, average=%ld.%03d s; distance=%d kB, " - "estimate=%d kB; lsn=%X/%X, redo lsn=%X/%X", + "estimate=%d kB; lsn=%X/%08X, redo lsn=%X/%08X", CheckpointStats.ckpt_bufs_written, (double) CheckpointStats.ckpt_bufs_written * 100 / NBuffers, CheckpointStats.ckpt_slru_written, @@ -6945,7 +6926,7 @@ LogCheckpointEnd(bool restartpoint) "%d removed, %d recycled; write=%ld.%03d s, " "sync=%ld.%03d s, total=%ld.%03d s; sync files=%d, " "longest=%ld.%03d s, average=%ld.%03d s; distance=%d kB, " - "estimate=%d kB; lsn=%X/%X, redo lsn=%X/%X", + "estimate=%d kB; lsn=%X/%08X, redo lsn=%X/%08X", CheckpointStats.ckpt_bufs_written, (double) CheckpointStats.ckpt_bufs_written * 100 / NBuffers, CheckpointStats.ckpt_slru_written, @@ -7042,12 +7023,12 @@ update_checkpoint_display(int flags, bool restartpoint, bool reset) * flags is a bitwise OR of the following: * CHECKPOINT_IS_SHUTDOWN: checkpoint is for database shutdown. * CHECKPOINT_END_OF_RECOVERY: checkpoint is for end of WAL recovery. - * CHECKPOINT_IMMEDIATE: finish the checkpoint ASAP, - * ignoring checkpoint_completion_target parameter. + * CHECKPOINT_FAST: finish the checkpoint ASAP, ignoring + * checkpoint_completion_target parameter. * CHECKPOINT_FORCE: force a checkpoint even if no XLOG activity has occurred * since the last one (implied by CHECKPOINT_IS_SHUTDOWN or * CHECKPOINT_END_OF_RECOVERY). - * CHECKPOINT_FLUSH_ALL: also flush buffers of unlogged tables. + * CHECKPOINT_FLUSH_UNLOGGED: also flush buffers of unlogged tables. * * Note: flags contains other bits, of interest here only for logging purposes. * In particular note that this routine is synchronous and does not pay @@ -7641,7 +7622,7 @@ CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, XLogRecPtr pagePtr, if (!RecoveryInProgress()) elog(ERROR, "can only be used at end of recovery"); if (pagePtr % XLOG_BLCKSZ != 0) - elog(ERROR, "invalid position for missing continuation record %X/%X", + elog(ERROR, "invalid position for missing continuation record %X/%08X", LSN_FORMAT_ARGS(pagePtr)); /* The current WAL insert position should be right after the page header */ @@ -7652,7 +7633,7 @@ CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, XLogRecPtr pagePtr, startPos += SizeOfXLogShortPHD; recptr = GetXLogInsertRecPtr(); if (recptr != startPos) - elog(ERROR, "invalid WAL insert position %X/%X for OVERWRITE_CONTRECORD", + elog(ERROR, "invalid WAL insert position %X/%08X for OVERWRITE_CONTRECORD", LSN_FORMAT_ARGS(recptr)); START_CRIT_SECTION(); @@ -7682,7 +7663,7 @@ CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, XLogRecPtr pagePtr, /* check that the record was inserted to the right place */ if (ProcLastRecPtr != startPos) - elog(ERROR, "OVERWRITE_CONTRECORD was inserted to unexpected position %X/%X", + elog(ERROR, "OVERWRITE_CONTRECORD was inserted to unexpected position %X/%08X", LSN_FORMAT_ARGS(ProcLastRecPtr)); XLogFlush(recptr); @@ -7751,8 +7732,7 @@ RecoveryRestartPoint(const CheckPoint *checkPoint, XLogReaderState *record) if (XLogHaveInvalidPages()) { elog(DEBUG2, - "could not record restart point at %X/%X because there " - "are unresolved references to invalid pages", + "could not record restart point at %X/%08X because there are unresolved references to invalid pages", LSN_FORMAT_ARGS(checkPoint->redo)); return; } @@ -7832,8 +7812,8 @@ CreateRestartPoint(int flags) lastCheckPoint.redo <= ControlFile->checkPointCopy.redo) { ereport(DEBUG2, - (errmsg_internal("skipping restartpoint, already performed at %X/%X", - LSN_FORMAT_ARGS(lastCheckPoint.redo)))); + errmsg_internal("skipping restartpoint, already performed at %X/%08X", + LSN_FORMAT_ARGS(lastCheckPoint.redo))); UpdateMinRecoveryPoint(InvalidXLogRecPtr, true); if (flags & CHECKPOINT_IS_SHUTDOWN) @@ -8017,10 +7997,10 @@ CreateRestartPoint(int flags) xtime = GetLatestXTime(); ereport((log_checkpoints ? LOG : DEBUG2), - (errmsg("recovery restart point at %X/%X", - LSN_FORMAT_ARGS(lastCheckPoint.redo)), - xtime ? errdetail("Last completed transaction was at log time %s.", - timestamptz_to_str(xtime)) : 0)); + errmsg("recovery restart point at %X/%08X", + LSN_FORMAT_ARGS(lastCheckPoint.redo)), + xtime ? errdetail("Last completed transaction was at log time %s.", + timestamptz_to_str(xtime)) : 0); /* * Finally, execute archive_cleanup_command, if any. @@ -8151,17 +8131,19 @@ KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo) XLByteToSeg(recptr, currSegNo, wal_segment_size); segno = currSegNo; - /* - * Calculate how many segments are kept by slots first, adjusting for - * max_slot_wal_keep_size. - */ + /* Calculate how many segments are kept by slots. */ keep = XLogGetReplicationSlotMinimumLSN(); if (keep != InvalidXLogRecPtr && keep < recptr) { XLByteToSeg(keep, segno, wal_segment_size); - /* Cap by max_slot_wal_keep_size ... */ - if (max_slot_wal_keep_size_mb >= 0) + /* + * Account for max_slot_wal_keep_size to avoid keeping more than + * configured. However, don't do that during a binary upgrade: if + * slots were to be invalidated because of this, it would not be + * possible to preserve logical ones during the upgrade. + */ + if (max_slot_wal_keep_size_mb >= 0 && !IsBinaryUpgrade) { uint64 slot_keep_segs; @@ -8281,8 +8263,8 @@ XLogRestorePoint(const char *rpName) RecPtr = XLogInsert(RM_XLOG_ID, XLOG_RESTORE_POINT); ereport(LOG, - (errmsg("restore point \"%s\" created at %X/%X", - rpName, LSN_FORMAT_ARGS(RecPtr)))); + errmsg("restore point \"%s\" created at %X/%08X", + rpName, LSN_FORMAT_ARGS(RecPtr))); return RecPtr; } @@ -8947,9 +8929,8 @@ issue_xlog_fsync(int fd, XLogSegNo segno, TimeLineID tli) * backup state and tablespace map. * * Input parameters are "state" (the backup state), "fast" (if true, we do - * the checkpoint in immediate mode to make it faster), and "tablespaces" - * (if non-NULL, indicates a list of tablespaceinfo structs describing the - * cluster's tablespaces.). + * the checkpoint in fast mode), and "tablespaces" (if non-NULL, indicates a + * list of tablespaceinfo structs describing the cluster's tablespaces.). * * The tablespace map contents are appended to passed-in parameter * tablespace_map and the caller is responsible for including it in the backup @@ -9077,11 +9058,11 @@ do_pg_backup_start(const char *backupidstr, bool fast, List **tablespaces, * during recovery means that checkpointer is running, we can use * RequestCheckpoint() to establish a restartpoint. * - * We use CHECKPOINT_IMMEDIATE only if requested by user (via - * passing fast = true). Otherwise this can take awhile. + * We use CHECKPOINT_FAST only if requested by user (via passing + * fast = true). Otherwise this can take awhile. */ RequestCheckpoint(CHECKPOINT_FORCE | CHECKPOINT_WAIT | - (fast ? CHECKPOINT_IMMEDIATE : 0)); + (fast ? CHECKPOINT_FAST : 0)); /* * Now we need to fetch the checkpoint record location, and also diff --git a/src/backend/access/transam/xlogbackup.c b/src/backend/access/transam/xlogbackup.c index 342590e0a46..cda4b38b7d6 100644 --- a/src/backend/access/transam/xlogbackup.c +++ b/src/backend/access/transam/xlogbackup.c @@ -42,7 +42,7 @@ build_backup_content(BackupState *state, bool ishistoryfile) XLByteToSeg(state->startpoint, startsegno, wal_segment_size); XLogFileName(startxlogfile, state->starttli, startsegno, wal_segment_size); - appendStringInfo(result, "START WAL LOCATION: %X/%X (file %s)\n", + appendStringInfo(result, "START WAL LOCATION: %X/%08X (file %s)\n", LSN_FORMAT_ARGS(state->startpoint), startxlogfile); if (ishistoryfile) @@ -52,11 +52,11 @@ build_backup_content(BackupState *state, bool ishistoryfile) XLByteToSeg(state->stoppoint, stopsegno, wal_segment_size); XLogFileName(stopxlogfile, state->stoptli, stopsegno, wal_segment_size); - appendStringInfo(result, "STOP WAL LOCATION: %X/%X (file %s)\n", + appendStringInfo(result, "STOP WAL LOCATION: %X/%08X (file %s)\n", LSN_FORMAT_ARGS(state->stoppoint), stopxlogfile); } - appendStringInfo(result, "CHECKPOINT LOCATION: %X/%X\n", + appendStringInfo(result, "CHECKPOINT LOCATION: %X/%08X\n", LSN_FORMAT_ARGS(state->checkpointloc)); appendStringInfoString(result, "BACKUP METHOD: streamed\n"); appendStringInfo(result, "BACKUP FROM: %s\n", @@ -81,7 +81,7 @@ build_backup_content(BackupState *state, bool ishistoryfile) Assert(XLogRecPtrIsInvalid(state->istartpoint) == (state->istarttli == 0)); if (!XLogRecPtrIsInvalid(state->istartpoint)) { - appendStringInfo(result, "INCREMENTAL FROM LSN: %X/%X\n", + appendStringInfo(result, "INCREMENTAL FROM LSN: %X/%08X\n", LSN_FORMAT_ARGS(state->istartpoint)); appendStringInfo(result, "INCREMENTAL FROM TLI: %u\n", state->istarttli); diff --git a/src/backend/access/transam/xloginsert.c b/src/backend/access/transam/xloginsert.c index 5ee9d0b028e..c7571429e8e 100644 --- a/src/backend/access/transam/xloginsert.c +++ b/src/backend/access/transam/xloginsert.c @@ -530,6 +530,18 @@ XLogInsert(RmgrId rmid, uint8 info) } /* + * Simple wrapper to XLogInsert to insert a WAL record with elementary + * contents (only an int64 is supported as value currently). + */ +XLogRecPtr +XLogSimpleInsertInt64(RmgrId rmid, uint8 info, int64 value) +{ + XLogBeginInsert(); + XLogRegisterData(&value, sizeof(value)); + return XLogInsert(rmid, info); +} + +/* * Assemble a WAL record from the registered data and buffers into an * XLogRecData chain, ready for insertion with XLogInsertRecord(). * diff --git a/src/backend/access/transam/xlogprefetcher.c b/src/backend/access/transam/xlogprefetcher.c index 7735562db01..ed3aacabc98 100644 --- a/src/backend/access/transam/xlogprefetcher.c +++ b/src/backend/access/transam/xlogprefetcher.c @@ -546,7 +546,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing all readahead until %X/%X is replayed due to possible TLI change", + "suppressing all readahead until %X/%08X is replayed due to possible TLI change", LSN_FORMAT_ARGS(record->lsn)); #endif @@ -579,7 +579,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in database %u until %X/%X is replayed due to raw file copy", + "suppressing prefetch in database %u until %X/%08X is replayed due to raw file copy", rlocator.dbOid, LSN_FORMAT_ARGS(record->lsn)); #endif @@ -607,7 +607,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in relation %u/%u/%u until %X/%X is replayed, which creates the relation", + "suppressing prefetch in relation %u/%u/%u until %X/%08X is replayed, which creates the relation", xlrec->rlocator.spcOid, xlrec->rlocator.dbOid, xlrec->rlocator.relNumber, @@ -630,7 +630,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in relation %u/%u/%u from block %u until %X/%X is replayed, which truncates the relation", + "suppressing prefetch in relation %u/%u/%u from block %u until %X/%08X is replayed, which truncates the relation", xlrec->rlocator.spcOid, xlrec->rlocator.dbOid, xlrec->rlocator.relNumber, @@ -729,7 +729,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing all prefetch in relation %u/%u/%u until %X/%X is replayed, because the relation does not exist on disk", + "suppressing all prefetch in relation %u/%u/%u until %X/%08X is replayed, because the relation does not exist on disk", reln->smgr_rlocator.locator.spcOid, reln->smgr_rlocator.locator.dbOid, reln->smgr_rlocator.locator.relNumber, @@ -750,7 +750,7 @@ XLogPrefetcherNextBlock(uintptr_t pgsr_private, XLogRecPtr *lsn) { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "suppressing prefetch in relation %u/%u/%u from block %u until %X/%X is replayed, because the relation is too small", + "suppressing prefetch in relation %u/%u/%u from block %u until %X/%08X is replayed, because the relation is too small", reln->smgr_rlocator.locator.spcOid, reln->smgr_rlocator.locator.dbOid, reln->smgr_rlocator.locator.relNumber, @@ -928,7 +928,7 @@ XLogPrefetcherIsFiltered(XLogPrefetcher *prefetcher, RelFileLocator rlocator, { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%X is replayed (blocks >= %u filtered)", + "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%08X is replayed (blocks >= %u filtered)", rlocator.spcOid, rlocator.dbOid, rlocator.relNumber, blockno, LSN_FORMAT_ARGS(filter->filter_until_replayed), filter->filter_from_block); @@ -944,7 +944,7 @@ XLogPrefetcherIsFiltered(XLogPrefetcher *prefetcher, RelFileLocator rlocator, { #ifdef XLOGPREFETCHER_DEBUG_LEVEL elog(XLOGPREFETCHER_DEBUG_LEVEL, - "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%X is replayed (whole database)", + "prefetch of %u/%u/%u block %u suppressed; filtering until LSN %X/%08X is replayed (whole database)", rlocator.spcOid, rlocator.dbOid, rlocator.relNumber, blockno, LSN_FORMAT_ARGS(filter->filter_until_replayed)); #endif diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c index 2790ade1f91..ac1f801b1eb 100644 --- a/src/backend/access/transam/xlogreader.c +++ b/src/backend/access/transam/xlogreader.c @@ -617,7 +617,7 @@ restart: } else if (targetRecOff < pageHeaderSize) { - report_invalid_record(state, "invalid record offset at %X/%X: expected at least %u, got %u", + report_invalid_record(state, "invalid record offset at %X/%08X: expected at least %u, got %u", LSN_FORMAT_ARGS(RecPtr), pageHeaderSize, targetRecOff); goto err; @@ -626,7 +626,7 @@ restart: if ((((XLogPageHeader) state->readBuf)->xlp_info & XLP_FIRST_IS_CONTRECORD) && targetRecOff == pageHeaderSize) { - report_invalid_record(state, "contrecord is requested by %X/%X", + report_invalid_record(state, "contrecord is requested by %X/%08X", LSN_FORMAT_ARGS(RecPtr)); goto err; } @@ -667,7 +667,7 @@ restart: if (total_len < SizeOfXLogRecord) { report_invalid_record(state, - "invalid record length at %X/%X: expected at least %u, got %u", + "invalid record length at %X/%08X: expected at least %u, got %u", LSN_FORMAT_ARGS(RecPtr), (uint32) SizeOfXLogRecord, total_len); goto err; @@ -756,7 +756,7 @@ restart: if (!(pageHeader->xlp_info & XLP_FIRST_IS_CONTRECORD)) { report_invalid_record(state, - "there is no contrecord flag at %X/%X", + "there is no contrecord flag at %X/%08X", LSN_FORMAT_ARGS(RecPtr)); goto err; } @@ -769,7 +769,7 @@ restart: total_len != (pageHeader->xlp_rem_len + gotlen)) { report_invalid_record(state, - "invalid contrecord length %u (expected %lld) at %X/%X", + "invalid contrecord length %u (expected %lld) at %X/%08X", pageHeader->xlp_rem_len, ((long long) total_len) - gotlen, LSN_FORMAT_ARGS(RecPtr)); @@ -1132,7 +1132,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (record->xl_tot_len < SizeOfXLogRecord) { report_invalid_record(state, - "invalid record length at %X/%X: expected at least %u, got %u", + "invalid record length at %X/%08X: expected at least %u, got %u", LSN_FORMAT_ARGS(RecPtr), (uint32) SizeOfXLogRecord, record->xl_tot_len); return false; @@ -1140,7 +1140,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (!RmgrIdIsValid(record->xl_rmid)) { report_invalid_record(state, - "invalid resource manager ID %u at %X/%X", + "invalid resource manager ID %u at %X/%08X", record->xl_rmid, LSN_FORMAT_ARGS(RecPtr)); return false; } @@ -1153,7 +1153,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (!(record->xl_prev < RecPtr)) { report_invalid_record(state, - "record with incorrect prev-link %X/%X at %X/%X", + "record with incorrect prev-link %X/%08X at %X/%08X", LSN_FORMAT_ARGS(record->xl_prev), LSN_FORMAT_ARGS(RecPtr)); return false; @@ -1169,7 +1169,7 @@ ValidXLogRecordHeader(XLogReaderState *state, XLogRecPtr RecPtr, if (record->xl_prev != PrevRecPtr) { report_invalid_record(state, - "record with incorrect prev-link %X/%X at %X/%X", + "record with incorrect prev-link %X/%08X at %X/%08X", LSN_FORMAT_ARGS(record->xl_prev), LSN_FORMAT_ARGS(RecPtr)); return false; @@ -1207,7 +1207,7 @@ ValidXLogRecord(XLogReaderState *state, XLogRecord *record, XLogRecPtr recptr) if (!EQ_CRC32C(record->xl_crc, crc)) { report_invalid_record(state, - "incorrect resource manager data checksum in record at %X/%X", + "incorrect resource manager data checksum in record at %X/%08X", LSN_FORMAT_ARGS(recptr)); return false; } @@ -1241,7 +1241,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "invalid magic number %04X in WAL segment %s, LSN %X/%X, offset %u", + "invalid magic number %04X in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_magic, fname, LSN_FORMAT_ARGS(recptr), @@ -1256,7 +1256,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "invalid info bits %04X in WAL segment %s, LSN %X/%X, offset %u", + "invalid info bits %04X in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_info, fname, LSN_FORMAT_ARGS(recptr), @@ -1298,7 +1298,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, /* hmm, first page of file doesn't have a long header? */ report_invalid_record(state, - "invalid info bits %04X in WAL segment %s, LSN %X/%X, offset %u", + "invalid info bits %04X in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_info, fname, LSN_FORMAT_ARGS(recptr), @@ -1318,7 +1318,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "unexpected pageaddr %X/%X in WAL segment %s, LSN %X/%X, offset %u", + "unexpected pageaddr %X/%08X in WAL segment %s, LSN %X/%08X, offset %u", LSN_FORMAT_ARGS(hdr->xlp_pageaddr), fname, LSN_FORMAT_ARGS(recptr), @@ -1344,7 +1344,7 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr, XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize); report_invalid_record(state, - "out-of-sequence timeline ID %u (after %u) in WAL segment %s, LSN %X/%X, offset %u", + "out-of-sequence timeline ID %u (after %u) in WAL segment %s, LSN %X/%08X, offset %u", hdr->xlp_tli, state->latestPageTLI, fname, @@ -1756,7 +1756,7 @@ DecodeXLogRecord(XLogReaderState *state, if (block_id <= decoded->max_block_id) { report_invalid_record(state, - "out-of-order block_id %u at %X/%X", + "out-of-order block_id %u at %X/%08X", block_id, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1780,14 +1780,14 @@ DecodeXLogRecord(XLogReaderState *state, if (blk->has_data && blk->data_len == 0) { report_invalid_record(state, - "BKPBLOCK_HAS_DATA set, but no data included at %X/%X", + "BKPBLOCK_HAS_DATA set, but no data included at %X/%08X", LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; } if (!blk->has_data && blk->data_len != 0) { report_invalid_record(state, - "BKPBLOCK_HAS_DATA not set, but data length is %u at %X/%X", + "BKPBLOCK_HAS_DATA not set, but data length is %u at %X/%08X", (unsigned int) blk->data_len, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1823,7 +1823,7 @@ DecodeXLogRecord(XLogReaderState *state, blk->bimg_len == BLCKSZ)) { report_invalid_record(state, - "BKPIMAGE_HAS_HOLE set, but hole offset %u length %u block image length %u at %X/%X", + "BKPIMAGE_HAS_HOLE set, but hole offset %u length %u block image length %u at %X/%08X", (unsigned int) blk->hole_offset, (unsigned int) blk->hole_length, (unsigned int) blk->bimg_len, @@ -1839,7 +1839,7 @@ DecodeXLogRecord(XLogReaderState *state, (blk->hole_offset != 0 || blk->hole_length != 0)) { report_invalid_record(state, - "BKPIMAGE_HAS_HOLE not set, but hole offset %u length %u at %X/%X", + "BKPIMAGE_HAS_HOLE not set, but hole offset %u length %u at %X/%08X", (unsigned int) blk->hole_offset, (unsigned int) blk->hole_length, LSN_FORMAT_ARGS(state->ReadRecPtr)); @@ -1853,7 +1853,7 @@ DecodeXLogRecord(XLogReaderState *state, blk->bimg_len == BLCKSZ) { report_invalid_record(state, - "BKPIMAGE_COMPRESSED set, but block image length %u at %X/%X", + "BKPIMAGE_COMPRESSED set, but block image length %u at %X/%08X", (unsigned int) blk->bimg_len, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1868,7 +1868,7 @@ DecodeXLogRecord(XLogReaderState *state, blk->bimg_len != BLCKSZ) { report_invalid_record(state, - "neither BKPIMAGE_HAS_HOLE nor BKPIMAGE_COMPRESSED set, but block image length is %u at %X/%X", + "neither BKPIMAGE_HAS_HOLE nor BKPIMAGE_COMPRESSED set, but block image length is %u at %X/%08X", (unsigned int) blk->data_len, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; @@ -1884,7 +1884,7 @@ DecodeXLogRecord(XLogReaderState *state, if (rlocator == NULL) { report_invalid_record(state, - "BKPBLOCK_SAME_REL set but no previous rel at %X/%X", + "BKPBLOCK_SAME_REL set but no previous rel at %X/%08X", LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; } @@ -1896,7 +1896,7 @@ DecodeXLogRecord(XLogReaderState *state, else { report_invalid_record(state, - "invalid block_id %u at %X/%X", + "invalid block_id %u at %X/%08X", block_id, LSN_FORMAT_ARGS(state->ReadRecPtr)); goto err; } @@ -1963,7 +1963,7 @@ DecodeXLogRecord(XLogReaderState *state, shortdata_err: report_invalid_record(state, - "record with invalid length at %X/%X", + "record with invalid length at %X/%08X", LSN_FORMAT_ARGS(state->ReadRecPtr)); err: *errormsg = state->errormsg_buf; @@ -2073,14 +2073,14 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) !record->record->blocks[block_id].in_use) { report_invalid_record(record, - "could not restore image at %X/%X with invalid block %d specified", + "could not restore image at %X/%08X with invalid block %d specified", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; } if (!record->record->blocks[block_id].has_image) { - report_invalid_record(record, "could not restore image at %X/%X with invalid state, block %d", + report_invalid_record(record, "could not restore image at %X/%08X with invalid state, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; @@ -2107,7 +2107,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) bkpb->bimg_len, BLCKSZ - bkpb->hole_length) <= 0) decomp_success = false; #else - report_invalid_record(record, "could not restore image at %X/%X compressed with %s not supported by build, block %d", + report_invalid_record(record, "could not restore image at %X/%08X compressed with %s not supported by build, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), "LZ4", block_id); @@ -2124,7 +2124,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) if (ZSTD_isError(decomp_result)) decomp_success = false; #else - report_invalid_record(record, "could not restore image at %X/%X compressed with %s not supported by build, block %d", + report_invalid_record(record, "could not restore image at %X/%08X compressed with %s not supported by build, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), "zstd", block_id); @@ -2133,7 +2133,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) } else { - report_invalid_record(record, "could not restore image at %X/%X compressed with unknown method, block %d", + report_invalid_record(record, "could not restore image at %X/%08X compressed with unknown method, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; @@ -2141,7 +2141,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) if (!decomp_success) { - report_invalid_record(record, "could not decompress image at %X/%X, block %d", + report_invalid_record(record, "could not decompress image at %X/%08X, block %d", LSN_FORMAT_ARGS(record->ReadRecPtr), block_id); return false; diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c index 93d38914854..23878b2dd91 100644 --- a/src/backend/access/transam/xlogrecovery.c +++ b/src/backend/access/transam/xlogrecovery.c @@ -620,10 +620,10 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, * than ControlFile->checkPoint is used. */ ereport(LOG, - (errmsg("starting backup recovery with redo LSN %X/%X, checkpoint LSN %X/%X, on timeline ID %u", - LSN_FORMAT_ARGS(RedoStartLSN), - LSN_FORMAT_ARGS(CheckPointLoc), - CheckPointTLI))); + errmsg("starting backup recovery with redo LSN %X/%08X, checkpoint LSN %X/%08X, on timeline ID %u", + LSN_FORMAT_ARGS(RedoStartLSN), + LSN_FORMAT_ARGS(CheckPointLoc), + CheckPointTLI)); /* * When a backup_label file is present, we want to roll forward from @@ -636,8 +636,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); ereport(DEBUG1, - (errmsg_internal("checkpoint record is at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)))); + errmsg_internal("checkpoint record is at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc))); InRecovery = true; /* force recovery even if SHUTDOWNED */ /* @@ -652,23 +652,23 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, if (!ReadRecord(xlogprefetcher, LOG, false, checkPoint.ThisTimeLineID)) ereport(FATAL, - (errmsg("could not find redo location %X/%X referenced by checkpoint record at %X/%X", - LSN_FORMAT_ARGS(checkPoint.redo), LSN_FORMAT_ARGS(CheckPointLoc)), - errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" - "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" - "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", - DataDir, DataDir, DataDir, DataDir))); + errmsg("could not find redo location %X/%08X referenced by checkpoint record at %X/%08X", + LSN_FORMAT_ARGS(checkPoint.redo), LSN_FORMAT_ARGS(CheckPointLoc)), + errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" + "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" + "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", + DataDir, DataDir, DataDir, DataDir)); } } else { ereport(FATAL, - (errmsg("could not locate required checkpoint record at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)), - errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" - "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" - "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", - DataDir, DataDir, DataDir, DataDir))); + errmsg("could not locate required checkpoint record at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc)), + errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" or \"%s/standby.signal\" and add required recovery options.\n" + "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" + "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", + DataDir, DataDir, DataDir, DataDir)); wasShutdown = false; /* keep compiler quiet */ } @@ -773,8 +773,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, */ if (!XLogRecPtrIsInvalid(ControlFile->backupStartPoint)) ereport(LOG, - (errmsg("restarting backup recovery with redo LSN %X/%X", - LSN_FORMAT_ARGS(ControlFile->backupStartPoint)))); + errmsg("restarting backup recovery with redo LSN %X/%08X", + LSN_FORMAT_ARGS(ControlFile->backupStartPoint))); /* Get the last valid checkpoint record. */ CheckPointLoc = ControlFile->checkPoint; @@ -786,8 +786,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, if (record != NULL) { ereport(DEBUG1, - (errmsg_internal("checkpoint record is at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)))); + errmsg_internal("checkpoint record is at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc))); } else { @@ -798,8 +798,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, * simplify processing around checkpoints. */ ereport(PANIC, - (errmsg("could not locate a valid checkpoint record at %X/%X", - LSN_FORMAT_ARGS(CheckPointLoc)))); + errmsg("could not locate a valid checkpoint record at %X/%08X", + LSN_FORMAT_ARGS(CheckPointLoc))); } memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); @@ -824,8 +824,8 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, recoveryTargetName))); else if (recoveryTarget == RECOVERY_TARGET_LSN) ereport(LOG, - (errmsg("starting point-in-time recovery to WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryTargetLSN)))); + errmsg("starting point-in-time recovery to WAL location (LSN) \"%X/%08X\"", + LSN_FORMAT_ARGS(recoveryTargetLSN))); else if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE) ereport(LOG, (errmsg("starting point-in-time recovery to earliest consistent point"))); @@ -855,7 +855,7 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, (errmsg("requested timeline %u is not a child of this server's history", recoveryTargetTLI), /* translator: %s is a backup_label file or a pg_control file */ - errdetail("Latest checkpoint in file \"%s\" is at %X/%X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%X.", + errdetail("Latest checkpoint in file \"%s\" is at %X/%08X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%08X.", haveBackupLabel ? "backup_label" : "pg_control", LSN_FORMAT_ARGS(CheckPointLoc), CheckPointTLI, @@ -870,15 +870,15 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, tliOfPointInHistory(ControlFile->minRecoveryPoint - 1, expectedTLEs) != ControlFile->minRecoveryPointTLI) ereport(FATAL, - (errmsg("requested timeline %u does not contain minimum recovery point %X/%X on timeline %u", - recoveryTargetTLI, - LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint), - ControlFile->minRecoveryPointTLI))); + errmsg("requested timeline %u does not contain minimum recovery point %X/%08X on timeline %u", + recoveryTargetTLI, + LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint), + ControlFile->minRecoveryPointTLI)); ereport(DEBUG1, - (errmsg_internal("redo record is at %X/%X; shutdown %s", - LSN_FORMAT_ARGS(checkPoint.redo), - wasShutdown ? "true" : "false"))); + errmsg_internal("redo record is at %X/%08X; shutdown %s", + LSN_FORMAT_ARGS(checkPoint.redo), + wasShutdown ? "true" : "false")); ereport(DEBUG1, (errmsg_internal("next transaction ID: " UINT64_FORMAT "; next OID: %u", U64FromFullTransactionId(checkPoint.nextXid), @@ -1253,14 +1253,14 @@ read_backup_label(XLogRecPtr *checkPointLoc, TimeLineID *backupLabelTLI, * is pretty crude, but we are not expecting any variability in the file * format). */ - if (fscanf(lfp, "START WAL LOCATION: %X/%X (file %08X%16s)%c", + if (fscanf(lfp, "START WAL LOCATION: %X/%08X (file %08X%16s)%c", &hi, &lo, &tli_from_walseg, startxlogfilename, &ch) != 5 || ch != '\n') ereport(FATAL, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE))); RedoStartLSN = ((uint64) hi) << 32 | lo; RedoStartTLI = tli_from_walseg; - if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%X%c", + if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%08X%c", &hi, &lo, &ch) != 3 || ch != '\n') ereport(FATAL, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), @@ -1332,7 +1332,7 @@ read_backup_label(XLogRecPtr *checkPointLoc, TimeLineID *backupLabelTLI, tli_from_file, BACKUP_LABEL_FILE))); } - if (fscanf(lfp, "INCREMENTAL FROM LSN: %X/%X\n", &hi, &lo) > 0) + if (fscanf(lfp, "INCREMENTAL FROM LSN: %X/%08X\n", &hi, &lo) > 0) ereport(FATAL, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("this is an incremental backup, not a data directory"), @@ -1722,8 +1722,8 @@ PerformWalRecovery(void) if (record->xl_rmid != RM_XLOG_ID || (record->xl_info & ~XLR_INFO_MASK) != XLOG_CHECKPOINT_REDO) ereport(FATAL, - (errmsg("unexpected record type found at redo point %X/%X", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)))); + errmsg("unexpected record type found at redo point %X/%08X", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr))); } else { @@ -1745,8 +1745,8 @@ PerformWalRecovery(void) RmgrStartup(); ereport(LOG, - (errmsg("redo starts at %X/%X", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)))); + errmsg("redo starts at %X/%08X", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr))); /* Prepare to report progress of the redo phase. */ if (!StandbyMode) @@ -1758,7 +1758,7 @@ PerformWalRecovery(void) do { if (!StandbyMode) - ereport_startup_progress("redo in progress, elapsed time: %ld.%02d s, current LSN: %X/%X", + ereport_startup_progress("redo in progress, elapsed time: %ld.%02d s, current LSN: %X/%08X", LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)); #ifdef WAL_DEBUG @@ -1767,7 +1767,7 @@ PerformWalRecovery(void) StringInfoData buf; initStringInfo(&buf); - appendStringInfo(&buf, "REDO @ %X/%X; LSN %X/%X: ", + appendStringInfo(&buf, "REDO @ %X/%08X; LSN %X/%08X: ", LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), LSN_FORMAT_ARGS(xlogreader->EndRecPtr)); xlog_outrec(&buf, xlogreader); @@ -1880,9 +1880,9 @@ PerformWalRecovery(void) RmgrCleanup(); ereport(LOG, - (errmsg("redo done at %X/%X system usage: %s", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), - pg_rusage_show(&ru0)))); + errmsg("redo done at %X/%08X system usage: %s", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), + pg_rusage_show(&ru0))); xtime = GetLatestXTime(); if (xtime) ereport(LOG, @@ -2092,7 +2092,7 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_overwrite_contrecord)); if (xlrec.overwritten_lsn != record->overwrittenRecPtr) - elog(FATAL, "mismatching overwritten LSN %X/%X -> %X/%X", + elog(FATAL, "mismatching overwritten LSN %X/%08X -> %X/%08X", LSN_FORMAT_ARGS(xlrec.overwritten_lsn), LSN_FORMAT_ARGS(record->overwrittenRecPtr)); @@ -2101,9 +2101,9 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) missingContrecPtr = InvalidXLogRecPtr; ereport(LOG, - (errmsg("successfully skipped missing contrecord at %X/%X, overwritten at %s", - LSN_FORMAT_ARGS(xlrec.overwritten_lsn), - timestamptz_to_str(xlrec.overwrite_time)))); + errmsg("successfully skipped missing contrecord at %X/%08X, overwritten at %s", + LSN_FORMAT_ARGS(xlrec.overwritten_lsn), + timestamptz_to_str(xlrec.overwrite_time))); /* Verifying the record should only happen once */ record->overwrittenRecPtr = InvalidXLogRecPtr; @@ -2129,7 +2129,7 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) backupEndPoint = lsn; } else - elog(DEBUG1, "saw end-of-backup record for backup starting at %X/%X, waiting for %X/%X", + elog(DEBUG1, "saw end-of-backup record for backup starting at %X/%08X, waiting for %X/%08X", LSN_FORMAT_ARGS(startpoint), LSN_FORMAT_ARGS(backupStartPoint)); } } @@ -2224,9 +2224,9 @@ CheckRecoveryConsistency(void) backupEndRequired = false; ereport(LOG, - (errmsg("completed backup recovery with redo LSN %X/%X and end LSN %X/%X", - LSN_FORMAT_ARGS(saveBackupStartPoint), - LSN_FORMAT_ARGS(saveBackupEndPoint)))); + errmsg("completed backup recovery with redo LSN %X/%08X and end LSN %X/%08X", + LSN_FORMAT_ARGS(saveBackupStartPoint), + LSN_FORMAT_ARGS(saveBackupEndPoint))); } /* @@ -2255,8 +2255,8 @@ CheckRecoveryConsistency(void) reachedConsistency = true; SendPostmasterSignal(PMSIGNAL_RECOVERY_CONSISTENT); ereport(LOG, - (errmsg("consistent recovery state reached at %X/%X", - LSN_FORMAT_ARGS(lastReplayedEndRecPtr)))); + errmsg("consistent recovery state reached at %X/%08X", + LSN_FORMAT_ARGS(lastReplayedEndRecPtr))); } /* @@ -2293,7 +2293,7 @@ rm_redo_error_callback(void *arg) xlog_block_info(&buf, record); /* translator: %s is a WAL record description */ - errcontext("WAL redo at %X/%X for %s", + errcontext("WAL redo at %X/%08X for %s", LSN_FORMAT_ARGS(record->ReadRecPtr), buf.data); @@ -2328,7 +2328,7 @@ xlog_outdesc(StringInfo buf, XLogReaderState *record) static void xlog_outrec(StringInfo buf, XLogReaderState *record) { - appendStringInfo(buf, "prev %X/%X; xid %u", + appendStringInfo(buf, "prev %X/%08X; xid %u", LSN_FORMAT_ARGS(XLogRecGetPrev(record)), XLogRecGetXid(record)); @@ -2416,10 +2416,10 @@ checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI, lsn < minRecoveryPoint && newTLI > minRecoveryPointTLI) ereport(PANIC, - (errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%X on timeline %u", - newTLI, - LSN_FORMAT_ARGS(minRecoveryPoint), - minRecoveryPointTLI))); + errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%08X on timeline %u", + newTLI, + LSN_FORMAT_ARGS(minRecoveryPoint), + minRecoveryPointTLI)); /* Looks good */ } @@ -2621,8 +2621,8 @@ recoveryStopsBefore(XLogReaderState *record) recoveryStopTime = 0; recoveryStopName[0] = '\0'; ereport(LOG, - (errmsg("recovery stopping before WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryStopLSN)))); + errmsg("recovery stopping before WAL location (LSN) \"%X/%08X\"", + LSN_FORMAT_ARGS(recoveryStopLSN))); return true; } @@ -2789,8 +2789,8 @@ recoveryStopsAfter(XLogReaderState *record) recoveryStopTime = 0; recoveryStopName[0] = '\0'; ereport(LOG, - (errmsg("recovery stopping after WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryStopLSN)))); + errmsg("recovery stopping after WAL location (LSN) \"%X/%08X\"", + LSN_FORMAT_ARGS(recoveryStopLSN))); return true; } @@ -2910,7 +2910,7 @@ getRecoveryStopReason(void) timestamptz_to_str(recoveryStopTime)); else if (recoveryTarget == RECOVERY_TARGET_LSN) snprintf(reason, sizeof(reason), - "%s LSN %X/%X\n", + "%s LSN %X/%08X\n", recoveryStopAfter ? "after" : "before", LSN_FORMAT_ARGS(recoveryStopLSN)); else if (recoveryTarget == RECOVERY_TARGET_NAME) @@ -3213,11 +3213,11 @@ ReadRecord(XLogPrefetcher *xlogprefetcher, int emode, XLogFileName(fname, xlogreader->seg.ws_tli, segno, wal_segment_size); ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), - (errmsg("unexpected timeline ID %u in WAL segment %s, LSN %X/%X, offset %u", - xlogreader->latestPageTLI, - fname, - LSN_FORMAT_ARGS(xlogreader->latestPagePtr), - offset))); + errmsg("unexpected timeline ID %u in WAL segment %s, LSN %X/%08X, offset %u", + xlogreader->latestPageTLI, + fname, + LSN_FORMAT_ARGS(xlogreader->latestPagePtr), + offset)); record = NULL; } @@ -3429,14 +3429,14 @@ retry: errno = save_errno; ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), (errcode_for_file_access(), - errmsg("could not read from WAL segment %s, LSN %X/%X, offset %u: %m", + errmsg("could not read from WAL segment %s, LSN %X/%08X, offset %u: %m", fname, LSN_FORMAT_ARGS(targetPagePtr), readOff))); } else ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("could not read from WAL segment %s, LSN %X/%X, offset %u: read %d of %zu", + errmsg("could not read from WAL segment %s, LSN %X/%08X, offset %u: read %d of %zu", fname, LSN_FORMAT_ARGS(targetPagePtr), readOff, r, (Size) XLOG_BLCKSZ))); goto next_record_is_invalid; @@ -3718,7 +3718,7 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, wait_time = wal_retrieve_retry_interval - TimestampDifferenceMilliseconds(last_fail_time, now); - elog(LOG, "waiting for WAL to become available at %X/%X", + elog(LOG, "waiting for WAL to become available at %X/%08X", LSN_FORMAT_ARGS(RecPtr)); /* Do background tasks that might benefit us later. */ @@ -3864,7 +3864,7 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, tli = tliOfPointInHistory(tliRecPtr, expectedTLEs); if (curFileTLI > 0 && tli < curFileTLI) - elog(ERROR, "according to history file, WAL location %X/%X belongs to timeline %u, but previous recovered WAL file came from timeline %u", + elog(ERROR, "according to history file, WAL location %X/%08X belongs to timeline %u, but previous recovered WAL file came from timeline %u", LSN_FORMAT_ARGS(tliRecPtr), tli, curFileTLI); } @@ -4177,10 +4177,10 @@ rescanLatestTimeLine(TimeLineID replayTLI, XLogRecPtr replayLSN) if (currentTle->end < replayLSN) { ereport(LOG, - (errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%X", - newtarget, - replayTLI, - LSN_FORMAT_ARGS(replayLSN)))); + errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%08X", + newtarget, + replayTLI, + LSN_FORMAT_ARGS(replayLSN))); return false; } diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c index c389b27f77d..27ea52fdfee 100644 --- a/src/backend/access/transam/xlogutils.c +++ b/src/backend/access/transam/xlogutils.c @@ -795,7 +795,7 @@ XLogReadDetermineTimeline(XLogReaderState *state, XLogRecPtr wantPage, list_free_deep(timelineHistory); - elog(DEBUG3, "switched to timeline %u valid until %X/%X", + elog(DEBUG3, "switched to timeline %u valid until %X/%08X", state->currTLI, LSN_FORMAT_ARGS(state->currTLIValidUntil)); } diff --git a/src/backend/backup/backup_manifest.c b/src/backend/backup/backup_manifest.c index 22e2be37c95..d05252f383c 100644 --- a/src/backend/backup/backup_manifest.c +++ b/src/backend/backup/backup_manifest.c @@ -281,7 +281,7 @@ AddWALInfoToBackupManifest(backup_manifest_info *manifest, XLogRecPtr startptr, } AppendToManifest(manifest, - "%s{ \"Timeline\": %u, \"Start-LSN\": \"%X/%X\", \"End-LSN\": \"%X/%X\" }", + "%s{ \"Timeline\": %u, \"Start-LSN\": \"%X/%08X\", \"End-LSN\": \"%X/%08X\" }", first_wal_range ? "" : ",\n", entry->tli, LSN_FORMAT_ARGS(tl_beginptr), diff --git a/src/backend/backup/basebackup_copy.c b/src/backend/backup/basebackup_copy.c index a284ce318ff..18b0b5a52d3 100644 --- a/src/backend/backup/basebackup_copy.c +++ b/src/backend/backup/basebackup_copy.c @@ -361,7 +361,7 @@ SendXlogRecPtrResult(XLogRecPtr ptr, TimeLineID tli) tstate = begin_tup_output_tupdesc(dest, tupdesc, &TTSOpsVirtual); /* Data row */ - values[0] = CStringGetTextDatum(psprintf("%X/%X", LSN_FORMAT_ARGS(ptr))); + values[0] = CStringGetTextDatum(psprintf("%X/%08X", LSN_FORMAT_ARGS(ptr))); values[1] = Int64GetDatum(tli); do_tup_output(tstate, values, nulls); diff --git a/src/backend/backup/basebackup_incremental.c b/src/backend/backup/basebackup_incremental.c index 28491b1e0ab..a0d48ff0fef 100644 --- a/src/backend/backup/basebackup_incremental.c +++ b/src/backend/backup/basebackup_incremental.c @@ -409,7 +409,7 @@ PrepareForIncrementalBackup(IncrementalBackupInfo *ib, if (range->start_lsn < tlep[i]->begin) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("manifest requires WAL from initial timeline %u starting at %X/%X, but that timeline begins at %X/%X", + errmsg("manifest requires WAL from initial timeline %u starting at %X/%08X, but that timeline begins at %X/%08X", range->tli, LSN_FORMAT_ARGS(range->start_lsn), LSN_FORMAT_ARGS(tlep[i]->begin)))); @@ -419,7 +419,7 @@ PrepareForIncrementalBackup(IncrementalBackupInfo *ib, if (range->start_lsn != tlep[i]->begin) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("manifest requires WAL from continuation timeline %u starting at %X/%X, but that timeline begins at %X/%X", + errmsg("manifest requires WAL from continuation timeline %u starting at %X/%08X, but that timeline begins at %X/%08X", range->tli, LSN_FORMAT_ARGS(range->start_lsn), LSN_FORMAT_ARGS(tlep[i]->begin)))); @@ -430,7 +430,7 @@ PrepareForIncrementalBackup(IncrementalBackupInfo *ib, if (range->end_lsn > backup_state->startpoint) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("manifest requires WAL from final timeline %u ending at %X/%X, but this backup starts at %X/%X", + errmsg("manifest requires WAL from final timeline %u ending at %X/%08X, but this backup starts at %X/%08X", range->tli, LSN_FORMAT_ARGS(range->end_lsn), LSN_FORMAT_ARGS(backup_state->startpoint)), @@ -441,7 +441,7 @@ PrepareForIncrementalBackup(IncrementalBackupInfo *ib, if (range->end_lsn != tlep[i]->end) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("manifest requires WAL from non-final timeline %u ending at %X/%X, but this server switched timelines at %X/%X", + errmsg("manifest requires WAL from non-final timeline %u ending at %X/%08X, but this server switched timelines at %X/%08X", range->tli, LSN_FORMAT_ARGS(range->end_lsn), LSN_FORMAT_ARGS(tlep[i]->end)))); @@ -522,18 +522,18 @@ PrepareForIncrementalBackup(IncrementalBackupInfo *ib, if (XLogRecPtrIsInvalid(tli_missing_lsn)) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("WAL summaries are required on timeline %u from %X/%X to %X/%X, but no summaries for that timeline and LSN range exist", + errmsg("WAL summaries are required on timeline %u from %X/%08X to %X/%08X, but no summaries for that timeline and LSN range exist", tle->tli, LSN_FORMAT_ARGS(tli_start_lsn), LSN_FORMAT_ARGS(tli_end_lsn)))); else ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("WAL summaries are required on timeline %u from %X/%X to %X/%X, but the summaries for that timeline and LSN range are incomplete", + errmsg("WAL summaries are required on timeline %u from %X/%08X to %X/%08X, but the summaries for that timeline and LSN range are incomplete", tle->tli, LSN_FORMAT_ARGS(tli_start_lsn), LSN_FORMAT_ARGS(tli_end_lsn)), - errdetail("The first unsummarized LSN in this range is %X/%X.", + errdetail("The first unsummarized LSN in this range is %X/%08X.", LSN_FORMAT_ARGS(tli_missing_lsn)))); } diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index e5dbbe61b81..b2d5332effc 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -666,6 +666,14 @@ GRANT SELECT ON pg_shmem_allocations_numa TO pg_read_all_stats; REVOKE EXECUTE ON FUNCTION pg_get_shmem_allocations_numa() FROM PUBLIC; GRANT EXECUTE ON FUNCTION pg_get_shmem_allocations_numa() TO pg_read_all_stats; +CREATE VIEW pg_dsm_registry_allocations AS + SELECT * FROM pg_get_dsm_registry_allocations(); + +REVOKE ALL ON pg_dsm_registry_allocations FROM PUBLIC; +GRANT SELECT ON pg_dsm_registry_allocations TO pg_read_all_stats; +REVOKE EXECUTE ON FUNCTION pg_get_dsm_registry_allocations() FROM PUBLIC; +GRANT EXECUTE ON FUNCTION pg_get_dsm_registry_allocations() TO pg_read_all_stats; + CREATE VIEW pg_backend_memory_contexts AS SELECT * FROM pg_get_backend_memory_contexts(); diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c index c95eb945016..502a45163c8 100644 --- a/src/backend/commands/dbcommands.c +++ b/src/backend/commands/dbcommands.c @@ -570,8 +570,8 @@ CreateDatabaseUsingFileCopy(Oid src_dboid, Oid dst_dboid, Oid src_tsid, * any CREATE DATABASE commands. */ if (!IsBinaryUpgrade) - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | - CHECKPOINT_WAIT | CHECKPOINT_FLUSH_ALL); + RequestCheckpoint(CHECKPOINT_FAST | CHECKPOINT_FORCE | + CHECKPOINT_WAIT | CHECKPOINT_FLUSH_UNLOGGED); /* * Iterate through all tablespaces of the template database, and copy each @@ -673,7 +673,7 @@ CreateDatabaseUsingFileCopy(Oid src_dboid, Oid dst_dboid, Oid src_tsid, * strategy that avoids these problems. */ if (!IsBinaryUpgrade) - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | + RequestCheckpoint(CHECKPOINT_FAST | CHECKPOINT_FORCE | CHECKPOINT_WAIT); } @@ -1870,7 +1870,7 @@ dropdb(const char *dbname, bool missing_ok, bool force) * Force a checkpoint to make sure the checkpointer has received the * message sent by ForgetDatabaseSyncRequests. */ - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | CHECKPOINT_WAIT); + RequestCheckpoint(CHECKPOINT_FAST | CHECKPOINT_FORCE | CHECKPOINT_WAIT); /* Close all smgr fds in all backends. */ WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE)); @@ -2120,8 +2120,8 @@ movedb(const char *dbname, const char *tblspcname) * On Windows, this also ensures that background procs don't hold any open * files, which would cause rmdir() to fail. */ - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | CHECKPOINT_WAIT - | CHECKPOINT_FLUSH_ALL); + RequestCheckpoint(CHECKPOINT_FAST | CHECKPOINT_FORCE | CHECKPOINT_WAIT + | CHECKPOINT_FLUSH_UNLOGGED); /* Close all smgr fds in all backends. */ WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE)); @@ -2252,7 +2252,7 @@ movedb(const char *dbname, const char *tblspcname) * any unlogged operations done in the new DB tablespace before the * next checkpoint. */ - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | CHECKPOINT_WAIT); + RequestCheckpoint(CHECKPOINT_FAST | CHECKPOINT_FORCE | CHECKPOINT_WAIT); /* * Force synchronous commit, thus minimizing the window between diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index 4ff246cd943..e23b0de7242 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -1539,7 +1539,7 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, if (!XLogRecPtrIsInvalid(remote_lsn) && opts.lsn < remote_lsn) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("skip WAL location (LSN %X/%X) must be greater than origin LSN %X/%X", + errmsg("skip WAL location (LSN %X/%08X) must be greater than origin LSN %X/%08X", LSN_FORMAT_ARGS(opts.lsn), LSN_FORMAT_ARGS(remote_lsn)))); } diff --git a/src/backend/commands/tablespace.c b/src/backend/commands/tablespace.c index a9005cc7212..df31eace47a 100644 --- a/src/backend/commands/tablespace.c +++ b/src/backend/commands/tablespace.c @@ -500,7 +500,7 @@ DropTableSpace(DropTableSpaceStmt *stmt) * mustn't delete. So instead, we force a checkpoint which will clean * out any lingering files, and try again. */ - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | CHECKPOINT_WAIT); + RequestCheckpoint(CHECKPOINT_FAST | CHECKPOINT_FORCE | CHECKPOINT_WAIT); /* * On Windows, an unlinked file persists in the directory listing diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c index 3d44815ed5a..1f04a2c182c 100644 --- a/src/backend/optimizer/path/costsize.c +++ b/src/backend/optimizer/path/costsize.c @@ -2247,7 +2247,7 @@ append_nonpartial_cost(List *subpaths, int numpaths, int parallel_workers) * Determines and returns the cost of an Append node. */ void -cost_append(AppendPath *apath) +cost_append(AppendPath *apath, PlannerInfo *root) { ListCell *l; @@ -2309,26 +2309,52 @@ cost_append(AppendPath *apath) foreach(l, apath->subpaths) { Path *subpath = (Path *) lfirst(l); - Path sort_path; /* dummy for result of cost_sort */ + int presorted_keys; + Path sort_path; /* dummy for result of + * cost_sort/cost_incremental_sort */ - if (!pathkeys_contained_in(pathkeys, subpath->pathkeys)) + if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys, + &presorted_keys)) { /* * We'll need to insert a Sort node, so include costs for - * that. We can use the parent's LIMIT if any, since we + * that. We choose to use incremental sort if it is + * enabled and there are presorted keys; otherwise we use + * full sort. + * + * We can use the parent's LIMIT if any, since we * certainly won't pull more than that many tuples from * any child. */ - cost_sort(&sort_path, - NULL, /* doesn't currently need root */ - pathkeys, - subpath->disabled_nodes, - subpath->total_cost, - subpath->rows, - subpath->pathtarget->width, - 0.0, - work_mem, - apath->limit_tuples); + if (enable_incremental_sort && presorted_keys > 0) + { + cost_incremental_sort(&sort_path, + root, + pathkeys, + presorted_keys, + subpath->disabled_nodes, + subpath->startup_cost, + subpath->total_cost, + subpath->rows, + subpath->pathtarget->width, + 0.0, + work_mem, + apath->limit_tuples); + } + else + { + cost_sort(&sort_path, + root, + pathkeys, + subpath->disabled_nodes, + subpath->total_cost, + subpath->rows, + subpath->pathtarget->width, + 0.0, + work_mem, + apath->limit_tuples); + } + subpath = &sort_path; } diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c index 0b61aef962c..8a9f1d7a943 100644 --- a/src/backend/optimizer/plan/createplan.c +++ b/src/backend/optimizer/plan/createplan.c @@ -1318,6 +1318,7 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) Oid *sortOperators; Oid *collations; bool *nullsFirst; + int presorted_keys; /* * Compute sort column info, and adjust subplan's tlist as needed. @@ -1353,14 +1354,38 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) numsortkeys * sizeof(bool)) == 0); /* Now, insert a Sort node if subplan isn't sufficiently ordered */ - if (!pathkeys_contained_in(pathkeys, subpath->pathkeys)) + if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys, + &presorted_keys)) { - Sort *sort = make_sort(subplan, numsortkeys, + Plan *sort_plan; + + /* + * We choose to use incremental sort if it is enabled and + * there are presorted keys; otherwise we use full sort. + */ + if (enable_incremental_sort && presorted_keys > 0) + { + sort_plan = (Plan *) + make_incrementalsort(subplan, numsortkeys, presorted_keys, sortColIdx, sortOperators, collations, nullsFirst); - label_sort_with_costsize(root, sort, best_path->limit_tuples); - subplan = (Plan *) sort; + label_incrementalsort_with_costsize(root, + (IncrementalSort *) sort_plan, + pathkeys, + best_path->limit_tuples); + } + else + { + sort_plan = (Plan *) make_sort(subplan, numsortkeys, + sortColIdx, sortOperators, + collations, nullsFirst); + + label_sort_with_costsize(root, (Sort *) sort_plan, + best_path->limit_tuples); + } + + subplan = sort_plan; } } @@ -1491,6 +1516,7 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, Oid *sortOperators; Oid *collations; bool *nullsFirst; + int presorted_keys; /* Build the child plan */ /* Must insist that all children return the same tlist */ @@ -1525,14 +1551,38 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, numsortkeys * sizeof(bool)) == 0); /* Now, insert a Sort node if subplan isn't sufficiently ordered */ - if (!pathkeys_contained_in(pathkeys, subpath->pathkeys)) + if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys, + &presorted_keys)) { - Sort *sort = make_sort(subplan, numsortkeys, + Plan *sort_plan; + + /* + * We choose to use incremental sort if it is enabled and there + * are presorted keys; otherwise we use full sort. + */ + if (enable_incremental_sort && presorted_keys > 0) + { + sort_plan = (Plan *) + make_incrementalsort(subplan, numsortkeys, presorted_keys, sortColIdx, sortOperators, collations, nullsFirst); - label_sort_with_costsize(root, sort, best_path->limit_tuples); - subplan = (Plan *) sort; + label_incrementalsort_with_costsize(root, + (IncrementalSort *) sort_plan, + pathkeys, + best_path->limit_tuples); + } + else + { + sort_plan = (Plan *) make_sort(subplan, numsortkeys, + sortColIdx, sortOperators, + collations, nullsFirst); + + label_sort_with_costsize(root, (Sort *) sort_plan, + best_path->limit_tuples); + } + + subplan = sort_plan; } subplans = lappend(subplans, subplan); diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c index e0192d4a491..9cc602788ea 100644 --- a/src/backend/optimizer/util/pathnode.c +++ b/src/backend/optimizer/util/pathnode.c @@ -1404,12 +1404,12 @@ create_append_path(PlannerInfo *root, pathnode->path.total_cost = child->total_cost; } else - cost_append(pathnode); + cost_append(pathnode, root); /* Must do this last, else cost_append complains */ pathnode->path.pathkeys = child->pathkeys; } else - cost_append(pathnode); + cost_append(pathnode, root); /* If the caller provided a row estimate, override the computed value. */ if (rows >= 0) @@ -1515,6 +1515,9 @@ create_merge_append_path(PlannerInfo *root, foreach(l, subpaths) { Path *subpath = (Path *) lfirst(l); + int presorted_keys; + Path sort_path; /* dummy for result of + * cost_sort/cost_incremental_sort */ /* All child paths should be unparameterized */ Assert(bms_is_empty(PATH_REQ_OUTER(subpath))); @@ -1523,32 +1526,52 @@ create_merge_append_path(PlannerInfo *root, pathnode->path.parallel_safe = pathnode->path.parallel_safe && subpath->parallel_safe; - if (pathkeys_contained_in(pathkeys, subpath->pathkeys)) + if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys, + &presorted_keys)) { - /* Subpath is adequately ordered, we won't need to sort it */ - input_disabled_nodes += subpath->disabled_nodes; - input_startup_cost += subpath->startup_cost; - input_total_cost += subpath->total_cost; - } - else - { - /* We'll need to insert a Sort node, so include cost for that */ - Path sort_path; /* dummy for result of cost_sort */ + /* + * We'll need to insert a Sort node, so include costs for that. We + * choose to use incremental sort if it is enabled and there are + * presorted keys; otherwise we use full sort. + * + * We can use the parent's LIMIT if any, since we certainly won't + * pull more than that many tuples from any child. + */ + if (enable_incremental_sort && presorted_keys > 0) + { + cost_incremental_sort(&sort_path, + root, + pathkeys, + presorted_keys, + subpath->disabled_nodes, + subpath->startup_cost, + subpath->total_cost, + subpath->rows, + subpath->pathtarget->width, + 0.0, + work_mem, + pathnode->limit_tuples); + } + else + { + cost_sort(&sort_path, + root, + pathkeys, + subpath->disabled_nodes, + subpath->total_cost, + subpath->rows, + subpath->pathtarget->width, + 0.0, + work_mem, + pathnode->limit_tuples); + } - cost_sort(&sort_path, - root, - pathkeys, - subpath->disabled_nodes, - subpath->total_cost, - subpath->rows, - subpath->pathtarget->width, - 0.0, - work_mem, - pathnode->limit_tuples); - input_disabled_nodes += sort_path.disabled_nodes; - input_startup_cost += sort_path.startup_cost; - input_total_cost += sort_path.total_cost; + subpath = &sort_path; } + + input_disabled_nodes += subpath->disabled_nodes; + input_startup_cost += subpath->startup_cost; + input_total_cost += subpath->total_cost; } /* diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index 70a0d832a11..73345bb3c70 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -2034,6 +2034,13 @@ CheckPointStmt: $$ = (Node *) n; } + | CHECKPOINT '(' utility_option_list ')' + { + CheckPointStmt *n = makeNode(CheckPointStmt); + + $$ = (Node *) n; + n->options = $3; + } ; diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c index fda91ffd1ce..2809e298a44 100644 --- a/src/backend/postmaster/checkpointer.c +++ b/src/backend/postmaster/checkpointer.c @@ -42,6 +42,8 @@ #include "access/xlog.h" #include "access/xlog_internal.h" #include "access/xlogrecovery.h" +#include "catalog/pg_authid.h" +#include "commands/defrem.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" @@ -61,6 +63,7 @@ #include "storage/shmem.h" #include "storage/smgr.h" #include "storage/spin.h" +#include "utils/acl.h" #include "utils/guc.h" #include "utils/memutils.h" #include "utils/resowner.h" @@ -161,7 +164,7 @@ static pg_time_t last_xlog_switch_time; static void ProcessCheckpointerInterrupts(void); static void CheckArchiveTimeout(void); static bool IsCheckpointOnSchedule(double progress); -static bool ImmediateCheckpointRequested(void); +static bool FastCheckpointRequested(void); static bool CompactCheckpointerRequestQueue(void); static void UpdateSharedMemoryConfig(void); @@ -734,12 +737,12 @@ CheckArchiveTimeout(void) } /* - * Returns true if an immediate checkpoint request is pending. (Note that - * this does not check the *current* checkpoint's IMMEDIATE flag, but whether - * there is one pending behind it.) + * Returns true if a fast checkpoint request is pending. (Note that this does + * not check the *current* checkpoint's FAST flag, but whether there is one + * pending behind it.) */ static bool -ImmediateCheckpointRequested(void) +FastCheckpointRequested(void) { volatile CheckpointerShmemStruct *cps = CheckpointerShmem; @@ -747,7 +750,7 @@ ImmediateCheckpointRequested(void) * We don't need to acquire the ckpt_lck in this case because we're only * looking at a single flag bit. */ - if (cps->ckpt_flags & CHECKPOINT_IMMEDIATE) + if (cps->ckpt_flags & CHECKPOINT_FAST) return true; return false; } @@ -760,7 +763,7 @@ ImmediateCheckpointRequested(void) * checkpoint_completion_target. * * The checkpoint request flags should be passed in; currently the only one - * examined is CHECKPOINT_IMMEDIATE, which disables delays between writes. + * examined is CHECKPOINT_FAST, which disables delays between writes. * * 'progress' is an estimate of how much of the work has been done, as a * fraction between 0.0 meaning none, and 1.0 meaning all done. @@ -778,10 +781,10 @@ CheckpointWriteDelay(int flags, double progress) * Perform the usual duties and take a nap, unless we're behind schedule, * in which case we just try to catch up as quickly as possible. */ - if (!(flags & CHECKPOINT_IMMEDIATE) && + if (!(flags & CHECKPOINT_FAST) && !ShutdownXLOGPending && !ShutdownRequestPending && - !ImmediateCheckpointRequested() && + !FastCheckpointRequested() && IsCheckpointOnSchedule(progress)) { if (ConfigReloadPending) @@ -977,17 +980,67 @@ CheckpointerShmemInit(void) } /* + * ExecCheckpoint + * Primary entry point for manual CHECKPOINT commands + * + * This is mainly a wrapper for RequestCheckpoint(). + */ +void +ExecCheckpoint(ParseState *pstate, CheckPointStmt *stmt) +{ + bool fast = true; + bool unlogged = false; + + foreach_ptr(DefElem, opt, stmt->options) + { + if (strcmp(opt->defname, "mode") == 0) + { + char *mode = defGetString(opt); + + if (strcmp(mode, "spread") == 0) + fast = false; + else if (strcmp(mode, "fast") != 0) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("unrecognized MODE option \"%s\"", mode), + parser_errposition(pstate, opt->location))); + } + else if (strcmp(opt->defname, "flush_unlogged") == 0) + unlogged = defGetBoolean(opt); + else + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("unrecognized CHECKPOINT option \"%s\"", opt->defname), + parser_errposition(pstate, opt->location))); + } + + if (!has_privs_of_role(GetUserId(), ROLE_PG_CHECKPOINT)) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + /* translator: %s is name of an SQL command (e.g., CHECKPOINT) */ + errmsg("permission denied to execute %s command", + "CHECKPOINT"), + errdetail("Only roles with privileges of the \"%s\" role may execute this command.", + "pg_checkpoint"))); + + RequestCheckpoint(CHECKPOINT_WAIT | + (fast ? CHECKPOINT_FAST : 0) | + (unlogged ? CHECKPOINT_FLUSH_UNLOGGED : 0) | + (RecoveryInProgress() ? 0 : CHECKPOINT_FORCE)); +} + +/* * RequestCheckpoint * Called in backend processes to request a checkpoint * * flags is a bitwise OR of the following: * CHECKPOINT_IS_SHUTDOWN: checkpoint is for database shutdown. * CHECKPOINT_END_OF_RECOVERY: checkpoint is for end of WAL recovery. - * CHECKPOINT_IMMEDIATE: finish the checkpoint ASAP, + * CHECKPOINT_FAST: finish the checkpoint ASAP, * ignoring checkpoint_completion_target parameter. * CHECKPOINT_FORCE: force a checkpoint even if no XLOG activity has occurred * since the last one (implied by CHECKPOINT_IS_SHUTDOWN or - * CHECKPOINT_END_OF_RECOVERY). + * CHECKPOINT_END_OF_RECOVERY, and the CHECKPOINT command). * CHECKPOINT_WAIT: wait for completion before returning (otherwise, * just signal checkpointer to do it, and return). * CHECKPOINT_CAUSE_XLOG: checkpoint is requested due to xlog filling. @@ -1009,7 +1062,7 @@ RequestCheckpoint(int flags) * There's no point in doing slow checkpoints in a standalone backend, * because there's no other backends the checkpoint could disrupt. */ - CreateCheckPoint(flags | CHECKPOINT_IMMEDIATE); + CreateCheckPoint(flags | CHECKPOINT_FAST); /* Free all smgr objects, as CheckpointerMain() normally would. */ smgrdestroyall(); diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 490f7ce3664..cca9b946e53 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -4337,15 +4337,15 @@ maybe_start_bgworkers(void) static bool maybe_reap_io_worker(int pid) { - for (int id = 0; id < MAX_IO_WORKERS; ++id) + for (int i = 0; i < MAX_IO_WORKERS; ++i) { - if (io_worker_children[id] && - io_worker_children[id]->pid == pid) + if (io_worker_children[i] && + io_worker_children[i]->pid == pid) { - ReleasePostmasterChildSlot(io_worker_children[id]); + ReleasePostmasterChildSlot(io_worker_children[i]); --io_worker_count; - io_worker_children[id] = NULL; + io_worker_children[i] = NULL; return true; } } @@ -4389,22 +4389,22 @@ maybe_adjust_io_workers(void) while (io_worker_count < io_workers) { PMChild *child; - int id; + int i; /* find unused entry in io_worker_children array */ - for (id = 0; id < MAX_IO_WORKERS; ++id) + for (i = 0; i < MAX_IO_WORKERS; ++i) { - if (io_worker_children[id] == NULL) + if (io_worker_children[i] == NULL) break; } - if (id == MAX_IO_WORKERS) - elog(ERROR, "could not find a free IO worker ID"); + if (i == MAX_IO_WORKERS) + elog(ERROR, "could not find a free IO worker slot"); /* Try to launch one. */ child = StartChildProcess(B_IO_WORKER); if (child != NULL) { - io_worker_children[id] = child; + io_worker_children[i] = child; ++io_worker_count; } else @@ -4415,11 +4415,11 @@ maybe_adjust_io_workers(void) if (io_worker_count > io_workers) { /* ask the IO worker in the highest slot to exit */ - for (int id = MAX_IO_WORKERS - 1; id >= 0; --id) + for (int i = MAX_IO_WORKERS - 1; i >= 0; --i) { - if (io_worker_children[id] != NULL) + if (io_worker_children[i] != NULL) { - kill(io_worker_children[id]->pid, SIGUSR2); + kill(io_worker_children[i]->pid, SIGUSR2); break; } } diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c index 0fec4f1f871..777c9a8d555 100644 --- a/src/backend/postmaster/walsummarizer.c +++ b/src/backend/postmaster/walsummarizer.c @@ -385,7 +385,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len) switch_lsn = tliSwitchPoint(current_tli, tles, &switch_tli); ereport(DEBUG1, - errmsg_internal("switch point from TLI %u to TLI %u is at %X/%X", + errmsg_internal("switch point from TLI %u to TLI %u is at %X/%08X", current_tli, switch_tli, LSN_FORMAT_ARGS(switch_lsn))); } @@ -741,7 +741,7 @@ WaitForWalSummarization(XLogRecPtr lsn) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("WAL summarization is not progressing"), - errdetail("Summarization is needed through %X/%X, but is stuck at %X/%X on disk and %X/%X in memory.", + errdetail("Summarization is needed through %X/%08X, but is stuck at %X/%08X on disk and %X/%08X in memory.", LSN_FORMAT_ARGS(lsn), LSN_FORMAT_ARGS(summarized_lsn), LSN_FORMAT_ARGS(pending_lsn)))); @@ -755,12 +755,12 @@ WaitForWalSummarization(XLogRecPtr lsn) current_time) / 1000; ereport(WARNING, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg_plural("still waiting for WAL summarization through %X/%X after %ld second", - "still waiting for WAL summarization through %X/%X after %ld seconds", + errmsg_plural("still waiting for WAL summarization through %X/%08X after %ld second", + "still waiting for WAL summarization through %X/%08X after %ld seconds", elapsed_seconds, LSN_FORMAT_ARGS(lsn), elapsed_seconds), - errdetail("Summarization has reached %X/%X on disk and %X/%X in memory.", + errdetail("Summarization has reached %X/%08X on disk and %X/%08X in memory.", LSN_FORMAT_ARGS(summarized_lsn), LSN_FORMAT_ARGS(pending_lsn)))); } @@ -981,7 +981,7 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, if (private_data->end_of_wal) { ereport(DEBUG1, - errmsg_internal("could not read WAL from timeline %u at %X/%X: end of WAL at %X/%X", + errmsg_internal("could not read WAL from timeline %u at %X/%08X: end of WAL at %X/%08X", tli, LSN_FORMAT_ARGS(start_lsn), LSN_FORMAT_ARGS(private_data->read_upto))); @@ -1000,8 +1000,8 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, } else ereport(ERROR, - (errmsg("could not find a valid record after %X/%X", - LSN_FORMAT_ARGS(start_lsn)))); + errmsg("could not find a valid record after %X/%08X", + LSN_FORMAT_ARGS(start_lsn))); } /* We shouldn't go backward. */ @@ -1034,7 +1034,7 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, * able to read a complete record. */ ereport(DEBUG1, - errmsg_internal("could not read WAL from timeline %u at %X/%X: end of WAL at %X/%X", + errmsg_internal("could not read WAL from timeline %u at %X/%08X: end of WAL at %X/%08X", tli, LSN_FORMAT_ARGS(xlogreader->EndRecPtr), LSN_FORMAT_ARGS(private_data->read_upto))); @@ -1045,13 +1045,13 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, if (errormsg) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not read WAL from timeline %u at %X/%X: %s", + errmsg("could not read WAL from timeline %u at %X/%08X: %s", tli, LSN_FORMAT_ARGS(xlogreader->EndRecPtr), errormsg))); else ereport(ERROR, (errcode_for_file_access(), - errmsg("could not read WAL from timeline %u at %X/%X", + errmsg("could not read WAL from timeline %u at %X/%08X", tli, LSN_FORMAT_ARGS(xlogreader->EndRecPtr)))); } @@ -1222,7 +1222,7 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, /* Tell the user what we did. */ ereport(DEBUG1, - errmsg_internal("summarized WAL on TLI %u from %X/%X to %X/%X", + errmsg_internal("summarized WAL on TLI %u from %X/%08X to %X/%08X", tli, LSN_FORMAT_ARGS(summary_start_lsn), LSN_FORMAT_ARGS(summary_end_lsn))); @@ -1234,7 +1234,7 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, /* If we skipped a non-zero amount of WAL, log a debug message. */ if (summary_end_lsn > summary_start_lsn && fast_forward) ereport(DEBUG1, - errmsg_internal("skipped summarizing WAL on TLI %u from %X/%X to %X/%X", + errmsg_internal("skipped summarizing WAL on TLI %u from %X/%08X to %X/%08X", tli, LSN_FORMAT_ARGS(summary_start_lsn), LSN_FORMAT_ARGS(summary_end_lsn))); @@ -1580,7 +1580,7 @@ summarizer_read_local_xlog_page(XLogReaderState *state, /* Debugging output. */ ereport(DEBUG1, - errmsg_internal("timeline %u became historic, can read up to %X/%X", + errmsg_internal("timeline %u became historic, can read up to %X/%08X", private_data->tli, LSN_FORMAT_ARGS(private_data->read_upto))); } diff --git a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c index 7b4ddf7a8f5..f7b5d093681 100644 --- a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c +++ b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c @@ -534,7 +534,7 @@ libpqrcv_startstreaming(WalReceiverConn *conn, if (options->logical) appendStringInfoString(&cmd, " LOGICAL"); - appendStringInfo(&cmd, " %X/%X", LSN_FORMAT_ARGS(options->startpoint)); + appendStringInfo(&cmd, " %X/%08X", LSN_FORMAT_ARGS(options->startpoint)); /* * Additional options are different depending on if we are doing logical diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index f1eb798f3e9..7e363a7c05b 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -567,7 +567,7 @@ CreateDecodingContext(XLogRecPtr start_lsn, * kinds of client errors; so the client may wish to check that * confirmed_flush_lsn matches its expectations. */ - elog(LOG, "%X/%X has been already streamed, forwarding to %X/%X", + elog(LOG, "%X/%08X has been already streamed, forwarding to %X/%08X", LSN_FORMAT_ARGS(start_lsn), LSN_FORMAT_ARGS(slot->data.confirmed_flush)); @@ -610,7 +610,7 @@ CreateDecodingContext(XLogRecPtr start_lsn, ereport(LOG, (errmsg("starting logical decoding for slot \"%s\"", NameStr(slot->data.name)), - errdetail("Streaming transactions committing after %X/%X, reading WAL from %X/%X.", + errdetail("Streaming transactions committing after %X/%08X, reading WAL from %X/%08X.", LSN_FORMAT_ARGS(slot->data.confirmed_flush), LSN_FORMAT_ARGS(slot->data.restart_lsn)))); @@ -637,7 +637,7 @@ DecodingContextFindStartpoint(LogicalDecodingContext *ctx) /* Initialize from where to start reading WAL. */ XLogBeginRead(ctx->reader, slot->data.restart_lsn); - elog(DEBUG1, "searching for logical decoding starting point, starting at %X/%X", + elog(DEBUG1, "searching for logical decoding starting point, starting at %X/%08X", LSN_FORMAT_ARGS(slot->data.restart_lsn)); /* Wait for a consistent starting point */ @@ -758,7 +758,7 @@ output_plugin_error_callback(void *arg) /* not all callbacks have an associated LSN */ if (state->report_location != InvalidXLogRecPtr) - errcontext("slot \"%s\", output plugin \"%s\", in the %s callback, associated LSN %X/%X", + errcontext("slot \"%s\", output plugin \"%s\", in the %s callback, associated LSN %X/%08X", NameStr(state->ctx->slot->data.name), NameStr(state->ctx->slot->data.plugin), state->callback_name, @@ -1725,7 +1725,7 @@ LogicalIncreaseXminForSlot(XLogRecPtr current_lsn, TransactionId xmin) SpinLockRelease(&slot->mutex); if (got_new_xmin) - elog(DEBUG1, "got new catalog xmin %u at %X/%X", xmin, + elog(DEBUG1, "got new catalog xmin %u at %X/%08X", xmin, LSN_FORMAT_ARGS(current_lsn)); /* candidate already valid with the current flush position, apply */ @@ -1785,7 +1785,7 @@ LogicalIncreaseRestartDecodingForSlot(XLogRecPtr current_lsn, XLogRecPtr restart slot->candidate_restart_lsn = restart_lsn; SpinLockRelease(&slot->mutex); - elog(DEBUG1, "got new restart lsn %X/%X at %X/%X", + elog(DEBUG1, "got new restart lsn %X/%08X at %X/%08X", LSN_FORMAT_ARGS(restart_lsn), LSN_FORMAT_ARGS(current_lsn)); } @@ -1800,7 +1800,7 @@ LogicalIncreaseRestartDecodingForSlot(XLogRecPtr current_lsn, XLogRecPtr restart confirmed_flush = slot->data.confirmed_flush; SpinLockRelease(&slot->mutex); - elog(DEBUG1, "failed to increase restart lsn: proposed %X/%X, after %X/%X, current candidate %X/%X, current after %X/%X, flushed up to %X/%X", + elog(DEBUG1, "failed to increase restart lsn: proposed %X/%08X, after %X/%08X, current candidate %X/%08X, current after %X/%08X, flushed up to %X/%08X", LSN_FORMAT_ARGS(restart_lsn), LSN_FORMAT_ARGS(current_lsn), LSN_FORMAT_ARGS(candidate_restart_lsn), diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c index a17bacf88e7..87f10e50dcc 100644 --- a/src/backend/replication/logical/origin.c +++ b/src/backend/replication/logical/origin.c @@ -826,9 +826,9 @@ StartupReplicationOrigin(void) last_state++; ereport(LOG, - (errmsg("recovered replication state of node %d to %X/%X", - disk_state.roident, - LSN_FORMAT_ARGS(disk_state.remote_lsn)))); + errmsg("recovered replication state of node %d to %X/%08X", + disk_state.roident, + LSN_FORMAT_ARGS(disk_state.remote_lsn))); } /* now check checksum */ diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 3ec3abfa3da..2f0c08b8fbd 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -213,7 +213,7 @@ update_local_synced_slot(RemoteSlot *remote_slot, Oid remote_dbid, ereport(slot->data.persistency == RS_TEMPORARY ? LOG : DEBUG1, errmsg("could not synchronize replication slot \"%s\"", remote_slot->name), - errdetail("Synchronization could lead to data loss, because the remote slot needs WAL at LSN %X/%X and catalog xmin %u, but the standby has LSN %X/%X and catalog xmin %u.", + errdetail("Synchronization could lead to data loss, because the remote slot needs WAL at LSN %X/%08X and catalog xmin %u, but the standby has LSN %X/%08X and catalog xmin %u.", LSN_FORMAT_ARGS(remote_slot->restart_lsn), remote_slot->catalog_xmin, LSN_FORMAT_ARGS(slot->data.restart_lsn), @@ -275,7 +275,7 @@ update_local_synced_slot(RemoteSlot *remote_slot, Oid remote_dbid, ereport(ERROR, errmsg_internal("synchronized confirmed_flush for slot \"%s\" differs from remote slot", remote_slot->name), - errdetail_internal("Remote slot has LSN %X/%X but local slot has LSN %X/%X.", + errdetail_internal("Remote slot has LSN %X/%08X but local slot has LSN %X/%08X.", LSN_FORMAT_ARGS(remote_slot->confirmed_lsn), LSN_FORMAT_ARGS(slot->data.confirmed_flush))); } @@ -593,7 +593,7 @@ update_and_persist_local_synced_slot(RemoteSlot *remote_slot, Oid remote_dbid) { ereport(LOG, errmsg("could not synchronize replication slot \"%s\"", remote_slot->name), - errdetail("Synchronization could lead to data loss, because the standby could not build a consistent snapshot to decode WALs at LSN %X/%X.", + errdetail("Synchronization could lead to data loss, because the standby could not build a consistent snapshot to decode WALs at LSN %X/%08X.", LSN_FORMAT_ARGS(slot->data.restart_lsn))); return false; @@ -642,7 +642,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid) ereport(AmLogicalSlotSyncWorkerProcess() ? LOG : ERROR, errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("skipping slot synchronization because the received slot sync" - " LSN %X/%X for slot \"%s\" is ahead of the standby position %X/%X", + " LSN %X/%08X for slot \"%s\" is ahead of the standby position %X/%08X", LSN_FORMAT_ARGS(remote_slot->confirmed_lsn), remote_slot->name, LSN_FORMAT_ARGS(latestFlushPtr))); @@ -733,7 +733,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid) ereport(ERROR, errmsg_internal("cannot synchronize local slot \"%s\"", remote_slot->name), - errdetail_internal("Local slot's start streaming location LSN(%X/%X) is ahead of remote slot's LSN(%X/%X).", + errdetail_internal("Local slot's start streaming location LSN(%X/%08X) is ahead of remote slot's LSN(%X/%08X).", LSN_FORMAT_ARGS(slot->data.confirmed_flush), LSN_FORMAT_ARGS(remote_slot->confirmed_lsn))); diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index adf18c397db..8532bfd27e5 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -774,7 +774,7 @@ SnapBuildDistributeSnapshotAndInval(SnapBuild *builder, XLogRecPtr lsn, Transact if (rbtxn_is_prepared(txn)) continue; - elog(DEBUG2, "adding a new snapshot and invalidations to %u at %X/%X", + elog(DEBUG2, "adding a new snapshot and invalidations to %u at %X/%08X", txn->xid, LSN_FORMAT_ARGS(lsn)); /* @@ -1271,10 +1271,10 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn builder->initial_xmin_horizon)) { ereport(DEBUG1, - (errmsg_internal("skipping snapshot at %X/%X while building logical decoding snapshot, xmin horizon too low", - LSN_FORMAT_ARGS(lsn)), - errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid))); + errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", + LSN_FORMAT_ARGS(lsn)), + errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", + builder->initial_xmin_horizon, running->oldestRunningXid)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1310,9 +1310,9 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn builder->next_phase_at = InvalidTransactionId; ereport(LOG, - (errmsg("logical decoding found consistent point at %X/%X", - LSN_FORMAT_ARGS(lsn)), - errdetail("There are no running transactions."))); + errmsg("logical decoding found consistent point at %X/%08X", + LSN_FORMAT_ARGS(lsn)), + errdetail("There are no running transactions.")); return false; } @@ -1359,10 +1359,10 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn Assert(TransactionIdIsNormal(builder->xmax)); ereport(LOG, - (errmsg("logical decoding found initial starting point at %X/%X", - LSN_FORMAT_ARGS(lsn)), - errdetail("Waiting for transactions (approximately %d) older than %u to end.", - running->xcnt, running->nextXid))); + errmsg("logical decoding found initial starting point at %X/%08X", + LSN_FORMAT_ARGS(lsn)), + errdetail("Waiting for transactions (approximately %d) older than %u to end.", + running->xcnt, running->nextXid)); SnapBuildWaitSnapshot(running, running->nextXid); } @@ -1383,10 +1383,10 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn builder->next_phase_at = running->nextXid; ereport(LOG, - (errmsg("logical decoding found initial consistent point at %X/%X", - LSN_FORMAT_ARGS(lsn)), - errdetail("Waiting for transactions (approximately %d) older than %u to end.", - running->xcnt, running->nextXid))); + errmsg("logical decoding found initial consistent point at %X/%08X", + LSN_FORMAT_ARGS(lsn)), + errdetail("Waiting for transactions (approximately %d) older than %u to end.", + running->xcnt, running->nextXid)); SnapBuildWaitSnapshot(running, running->nextXid); } @@ -1407,9 +1407,9 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn builder->next_phase_at = InvalidTransactionId; ereport(LOG, - (errmsg("logical decoding found consistent point at %X/%X", - LSN_FORMAT_ARGS(lsn)), - errdetail("There are no old transactions anymore."))); + errmsg("logical decoding found consistent point at %X/%08X", + LSN_FORMAT_ARGS(lsn)), + errdetail("There are no old transactions anymore.")); } /* @@ -1913,9 +1913,9 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn) Assert(builder->state == SNAPBUILD_CONSISTENT); ereport(LOG, - (errmsg("logical decoding found consistent point at %X/%X", - LSN_FORMAT_ARGS(lsn)), - errdetail("Logical decoding will begin using saved snapshot."))); + errmsg("logical decoding found consistent point at %X/%08X", + LSN_FORMAT_ARGS(lsn)), + errdetail("Logical decoding will begin using saved snapshot.")); return true; snapshot_not_interesting: @@ -2061,7 +2061,7 @@ SnapBuildSnapshotExists(XLogRecPtr lsn) int ret; struct stat stat_buf; - sprintf(path, "%s/%X-%X.snap", + sprintf(path, "%s/%08X-%08X.snap", PG_LOGICAL_SNAPSHOTS_DIR, LSN_FORMAT_ARGS(lsn)); diff --git a/src/backend/replication/logical/tablesync.c b/src/backend/replication/logical/tablesync.c index c90f23ee5b0..e4fd6347fd1 100644 --- a/src/backend/replication/logical/tablesync.c +++ b/src/backend/replication/logical/tablesync.c @@ -1553,7 +1553,7 @@ LogicalRepSyncTableStart(XLogRecPtr *origin_startpos) copy_table_done: elog(DEBUG1, - "LogicalRepSyncTableStart: '%s' origin_startpos lsn %X/%X", + "LogicalRepSyncTableStart: '%s' origin_startpos lsn %X/%08X", originname, LSN_FORMAT_ARGS(*origin_startpos)); /* diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index fd11805a44c..c5fb627aa56 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -1016,7 +1016,7 @@ apply_handle_commit(StringInfo s) if (commit_data.commit_lsn != remote_final_lsn) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect commit LSN %X/%X in commit message (expected %X/%X)", + errmsg_internal("incorrect commit LSN %X/%08X in commit message (expected %X/%08X)", LSN_FORMAT_ARGS(commit_data.commit_lsn), LSN_FORMAT_ARGS(remote_final_lsn)))); @@ -1108,7 +1108,7 @@ apply_handle_prepare(StringInfo s) if (prepare_data.prepare_lsn != remote_final_lsn) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect prepare LSN %X/%X in prepare message (expected %X/%X)", + errmsg_internal("incorrect prepare LSN %X/%08X in prepare message (expected %X/%08X)", LSN_FORMAT_ARGS(prepare_data.prepare_lsn), LSN_FORMAT_ARGS(remote_final_lsn)))); @@ -3903,7 +3903,7 @@ send_feedback(XLogRecPtr recvpos, bool force, bool requestReply) pq_sendint64(reply_message, now); /* sendTime */ pq_sendbyte(reply_message, requestReply); /* replyRequested */ - elog(DEBUG2, "sending feedback (force %d) to recv %X/%X, write %X/%X, flush %X/%X", + elog(DEBUG2, "sending feedback (force %d) to recv %X/%08X, write %X/%08X, flush %X/%08X", force, LSN_FORMAT_ARGS(recvpos), LSN_FORMAT_ARGS(writepos), @@ -4909,7 +4909,7 @@ maybe_start_skipping_changes(XLogRecPtr finish_lsn) skip_xact_finish_lsn = finish_lsn; ereport(LOG, - errmsg("logical replication starts skipping transaction at LSN %X/%X", + errmsg("logical replication starts skipping transaction at LSN %X/%08X", LSN_FORMAT_ARGS(skip_xact_finish_lsn))); } @@ -4923,8 +4923,8 @@ stop_skipping_changes(void) return; ereport(LOG, - (errmsg("logical replication completed skipping transaction at LSN %X/%X", - LSN_FORMAT_ARGS(skip_xact_finish_lsn)))); + errmsg("logical replication completed skipping transaction at LSN %X/%08X", + LSN_FORMAT_ARGS(skip_xact_finish_lsn))); /* Stop skipping changes */ skip_xact_finish_lsn = InvalidXLogRecPtr; @@ -5012,7 +5012,7 @@ clear_subscription_skip_lsn(XLogRecPtr finish_lsn) if (myskiplsn != finish_lsn) ereport(WARNING, errmsg("skip-LSN of subscription \"%s\" cleared", MySubscription->name), - errdetail("Remote transaction's finish WAL location (LSN) %X/%X did not match skip-LSN %X/%X.", + errdetail("Remote transaction's finish WAL location (LSN) %X/%08X did not match skip-LSN %X/%08X.", LSN_FORMAT_ARGS(finish_lsn), LSN_FORMAT_ARGS(myskiplsn))); } @@ -5049,7 +5049,7 @@ apply_error_callback(void *arg) logicalrep_message_type(errarg->command), errarg->remote_xid); else - errcontext("processing remote data for replication origin \"%s\" during message type \"%s\" in transaction %u, finished at %X/%X", + errcontext("processing remote data for replication origin \"%s\" during message type \"%s\" in transaction %u, finished at %X/%08X", errarg->origin_name, logicalrep_message_type(errarg->command), errarg->remote_xid, @@ -5067,7 +5067,7 @@ apply_error_callback(void *arg) errarg->rel->remoterel.relname, errarg->remote_xid); else - errcontext("processing remote data for replication origin \"%s\" during message type \"%s\" for replication target relation \"%s.%s\" in transaction %u, finished at %X/%X", + errcontext("processing remote data for replication origin \"%s\" during message type \"%s\" for replication target relation \"%s.%s\" in transaction %u, finished at %X/%08X", errarg->origin_name, logicalrep_message_type(errarg->command), errarg->rel->remoterel.nspname, @@ -5086,7 +5086,7 @@ apply_error_callback(void *arg) errarg->rel->remoterel.attnames[errarg->remote_attnum], errarg->remote_xid); else - errcontext("processing remote data for replication origin \"%s\" during message type \"%s\" for replication target relation \"%s.%s\" column \"%s\" in transaction %u, finished at %X/%X", + errcontext("processing remote data for replication origin \"%s\" during message type \"%s\" for replication target relation \"%s.%s\" column \"%s\" in transaction %u, finished at %X/%08X", errarg->origin_name, logicalrep_message_type(errarg->command), errarg->rel->remoterel.nspname, diff --git a/src/backend/replication/repl_gram.y b/src/backend/replication/repl_gram.y index 7440aae5a1a..8a649199ec6 100644 --- a/src/backend/replication/repl_gram.y +++ b/src/backend/replication/repl_gram.y @@ -279,7 +279,7 @@ alter_replication_slot: ; /* - * START_REPLICATION [SLOT slot] [PHYSICAL] %X/%X [TIMELINE %u] + * START_REPLICATION [SLOT slot] [PHYSICAL] %X/%08X [TIMELINE %u] */ start_replication: K_START_REPLICATION opt_slot opt_physical RECPTR opt_timeline @@ -295,7 +295,7 @@ start_replication: } ; -/* START_REPLICATION SLOT slot LOGICAL %X/%X options */ +/* START_REPLICATION SLOT slot LOGICAL %X/%08X options */ start_logical_replication: K_START_REPLICATION K_SLOT IDENT K_LOGICAL RECPTR plugin_options { diff --git a/src/backend/replication/repl_scanner.l b/src/backend/replication/repl_scanner.l index 014ea8d25c6..b6930e28659 100644 --- a/src/backend/replication/repl_scanner.l +++ b/src/backend/replication/repl_scanner.l @@ -155,7 +155,7 @@ UPLOAD_MANIFEST { return K_UPLOAD_MANIFEST; } {hexdigit}+\/{hexdigit}+ { uint32 hi, lo; - if (sscanf(yytext, "%X/%X", &hi, &lo) != 2) + if (sscanf(yytext, "%X/%08X", &hi, &lo) != 2) replication_yyerror(NULL, yyscanner, "invalid streaming start location"); yylval->recptr = ((uint64) hi) << 32 | lo; return RECPTR; diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index f9fec50ae88..e44ad576bc7 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -154,7 +154,7 @@ int max_replication_slots = 10; /* the maximum number of replication * Invalidate replication slots that have remained idle longer than this * duration; '0' disables it. */ -int idle_replication_slot_timeout_mins = 0; +int idle_replication_slot_timeout_secs = 0; /* * This GUC lists streaming replication standby server slot names that @@ -1591,8 +1591,8 @@ ReportSlotInvalidation(ReplicationSlotInvalidationCause cause, uint64 ex = oldestLSN - restart_lsn; appendStringInfo(&err_detail, - ngettext("The slot's restart_lsn %X/%X exceeds the limit by %" PRIu64 " byte.", - "The slot's restart_lsn %X/%X exceeds the limit by %" PRIu64 " bytes.", + ngettext("The slot's restart_lsn %X/%08X exceeds the limit by %" PRIu64 " byte.", + "The slot's restart_lsn %X/%08X exceeds the limit by %" PRIu64 " bytes.", ex), LSN_FORMAT_ARGS(restart_lsn), ex); @@ -1612,13 +1612,10 @@ ReportSlotInvalidation(ReplicationSlotInvalidationCause cause, case RS_INVAL_IDLE_TIMEOUT: { - int minutes = slot_idle_seconds / SECS_PER_MINUTE; - int secs = slot_idle_seconds % SECS_PER_MINUTE; - /* translator: %s is a GUC variable name */ - appendStringInfo(&err_detail, _("The slot's idle time of %dmin %02ds exceeds the configured \"%s\" duration of %dmin."), - minutes, secs, "idle_replication_slot_timeout", - idle_replication_slot_timeout_mins); + appendStringInfo(&err_detail, _("The slot's idle time of %lds exceeds the configured \"%s\" duration of %ds."), + slot_idle_seconds, "idle_replication_slot_timeout", + idle_replication_slot_timeout_secs); /* translator: %s is a GUC variable name */ appendStringInfo(&err_hint, _("You might need to increase \"%s\"."), "idle_replication_slot_timeout"); @@ -1656,7 +1653,7 @@ ReportSlotInvalidation(ReplicationSlotInvalidationCause cause, static inline bool CanInvalidateIdleSlot(ReplicationSlot *s) { - return (idle_replication_slot_timeout_mins != 0 && + return (idle_replication_slot_timeout_secs != 0 && !XLogRecPtrIsInvalid(s->data.restart_lsn) && s->inactive_since > 0 && !(RecoveryInProgress() && s->data.synced)); @@ -1717,9 +1714,9 @@ DetermineSlotInvalidationCause(uint32 possible_causes, ReplicationSlot *s, if (CanInvalidateIdleSlot(s)) { /* - * We simulate the invalidation due to idle_timeout as the minimum - * time idle time is one minute which makes tests take a long - * time. + * Simulate the invalidation due to idle_timeout to test the + * timeout behavior promptly, without waiting for it to trigger + * naturally. */ #ifdef USE_INJECTION_POINTS if (IS_INJECTION_POINT_ATTACHED("slot-timeout-inval")) @@ -1734,7 +1731,7 @@ DetermineSlotInvalidationCause(uint32 possible_causes, ReplicationSlot *s, * idle_replication_slot_timeout GUC. */ if (TimestampDifferenceExceedsSeconds(s->inactive_since, now, - idle_replication_slot_timeout_mins * SECS_PER_MINUTE)) + idle_replication_slot_timeout_secs)) { *inactive_since = s->inactive_since; return RS_INVAL_IDLE_TIMEOUT; @@ -1891,15 +1888,6 @@ InvalidatePossiblyObsoleteSlot(uint32 possible_causes, SpinLockRelease(&s->mutex); /* - * The logical replication slots shouldn't be invalidated as GUC - * max_slot_wal_keep_size is set to -1 and - * idle_replication_slot_timeout is set to 0 during the binary - * upgrade. See check_old_cluster_for_valid_slots() where we ensure - * that no invalidated before the upgrade. - */ - Assert(!(*invalidated && SlotIsLogical(s) && IsBinaryUpgrade)); - - /* * Calculate the idle time duration of the slot if slot is marked * invalidated with RS_INVAL_IDLE_TIMEOUT. */ @@ -2045,6 +2033,10 @@ restart: if (!s->in_use) continue; + /* Prevent invalidation of logical slots during binary upgrade */ + if (SlotIsLogical(s) && IsBinaryUpgrade) + continue; + if (InvalidatePossiblyObsoleteSlot(possible_causes, s, oldestLSN, dboid, snapshotConflictHorizon, &invalidated)) @@ -3057,22 +3049,3 @@ WaitForStandbyConfirmation(XLogRecPtr wait_for_lsn) ConditionVariableCancelSleep(); } - -/* - * GUC check_hook for idle_replication_slot_timeout - * - * The value of idle_replication_slot_timeout must be set to 0 during - * a binary upgrade. See start_postmaster() in pg_upgrade for more details. - */ -bool -check_idle_replication_slot_timeout(int *newval, void **extra, GucSource source) -{ - if (IsBinaryUpgrade && *newval != 0) - { - GUC_check_errdetail("\"%s\" must be set to 0 during binary upgrade mode.", - "idle_replication_slot_timeout"); - return false; - } - - return true; -} diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 36cc2ed4e44..69f4c6157c5 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -566,7 +566,7 @@ pg_replication_slot_advance(PG_FUNCTION_ARGS) if (moveto < minlsn) ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("cannot advance replication slot to %X/%X, minimum is %X/%X", + errmsg("cannot advance replication slot to %X/%08X, minimum is %X/%08X", LSN_FORMAT_ARGS(moveto), LSN_FORMAT_ARGS(minlsn)))); /* Do the actual slot update, depending on the slot type */ diff --git a/src/backend/replication/syncrep.c b/src/backend/replication/syncrep.c index cc35984ad00..32cf3a48b89 100644 --- a/src/backend/replication/syncrep.c +++ b/src/backend/replication/syncrep.c @@ -258,7 +258,7 @@ SyncRepWaitForLSN(XLogRecPtr lsn, bool commit) { char buffer[32]; - sprintf(buffer, "waiting for %X/%X", LSN_FORMAT_ARGS(lsn)); + sprintf(buffer, "waiting for %X/%08X", LSN_FORMAT_ARGS(lsn)); set_ps_display_suffix(buffer); } @@ -566,7 +566,7 @@ SyncRepReleaseWaiters(void) LWLockRelease(SyncRepLock); - elog(DEBUG3, "released %d procs up to write %X/%X, %d procs up to flush %X/%X, %d procs up to apply %X/%X", + elog(DEBUG3, "released %d procs up to write %X/%08X, %d procs up to flush %X/%08X, %d procs up to apply %X/%08X", numwrite, LSN_FORMAT_ARGS(writePtr), numflush, LSN_FORMAT_ARGS(flushPtr), numapply, LSN_FORMAT_ARGS(applyPtr)); diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 8c4d0fd9aed..b6281101711 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -386,12 +386,12 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len) { if (first_stream) ereport(LOG, - (errmsg("started streaming WAL from primary at %X/%X on timeline %u", - LSN_FORMAT_ARGS(startpoint), startpointTLI))); + errmsg("started streaming WAL from primary at %X/%08X on timeline %u", + LSN_FORMAT_ARGS(startpoint), startpointTLI)); else ereport(LOG, - (errmsg("restarted WAL streaming at %X/%X on timeline %u", - LSN_FORMAT_ARGS(startpoint), startpointTLI))); + errmsg("restarted WAL streaming at %X/%08X on timeline %u", + LSN_FORMAT_ARGS(startpoint), startpointTLI)); first_stream = false; /* Initialize LogstreamResult and buffers for processing messages */ @@ -470,7 +470,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len) { ereport(LOG, (errmsg("replication terminated by primary server"), - errdetail("End of WAL reached on timeline %u at %X/%X.", + errdetail("End of WAL reached on timeline %u at %X/%08X.", startpointTLI, LSN_FORMAT_ARGS(LogstreamResult.Write)))); endofwal = true; @@ -711,7 +711,7 @@ WalRcvWaitForStartPosition(XLogRecPtr *startpoint, TimeLineID *startpointTLI) { char activitymsg[50]; - snprintf(activitymsg, sizeof(activitymsg), "restarting at %X/%X", + snprintf(activitymsg, sizeof(activitymsg), "restarting at %X/%08X", LSN_FORMAT_ARGS(*startpoint)); set_ps_display(activitymsg); } @@ -1014,7 +1014,7 @@ XLogWalRcvFlush(bool dying, TimeLineID tli) { char activitymsg[50]; - snprintf(activitymsg, sizeof(activitymsg), "streaming %X/%X", + snprintf(activitymsg, sizeof(activitymsg), "streaming %X/%08X", LSN_FORMAT_ARGS(LogstreamResult.Write)); set_ps_display(activitymsg); } @@ -1138,7 +1138,7 @@ XLogWalRcvSendReply(bool force, bool requestReply) pq_sendbyte(&reply_message, requestReply ? 1 : 0); /* Send it */ - elog(DEBUG2, "sending write %X/%X flush %X/%X apply %X/%X%s", + elog(DEBUG2, "sending write %X/%08X flush %X/%08X apply %X/%08X%s", LSN_FORMAT_ARGS(writePtr), LSN_FORMAT_ARGS(flushPtr), LSN_FORMAT_ARGS(applyPtr), diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index f2c33250e8b..28b8591efa5 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -408,7 +408,7 @@ IdentifySystem(void) else logptr = GetFlushRecPtr(&currTLI); - snprintf(xloc, sizeof(xloc), "%X/%X", LSN_FORMAT_ARGS(logptr)); + snprintf(xloc, sizeof(xloc), "%X/%08X", LSN_FORMAT_ARGS(logptr)); if (MyDatabaseId != InvalidOid) { @@ -515,7 +515,7 @@ ReadReplicationSlot(ReadReplicationSlotCmd *cmd) { char xloc[64]; - snprintf(xloc, sizeof(xloc), "%X/%X", + snprintf(xloc, sizeof(xloc), "%X/%08X", LSN_FORMAT_ARGS(slot_contents.data.restart_lsn)); values[i] = CStringGetTextDatum(xloc); nulls[i] = false; @@ -892,12 +892,12 @@ StartReplication(StartReplicationCmd *cmd) switchpoint < cmd->startpoint) { ereport(ERROR, - (errmsg("requested starting point %X/%X on timeline %u is not in this server's history", - LSN_FORMAT_ARGS(cmd->startpoint), - cmd->timeline), - errdetail("This server's history forked from timeline %u at %X/%X.", - cmd->timeline, - LSN_FORMAT_ARGS(switchpoint)))); + errmsg("requested starting point %X/%08X on timeline %u is not in this server's history", + LSN_FORMAT_ARGS(cmd->startpoint), + cmd->timeline), + errdetail("This server's history forked from timeline %u at %X/%08X.", + cmd->timeline, + LSN_FORMAT_ARGS(switchpoint))); } sendTimeLineValidUpto = switchpoint; } @@ -939,9 +939,9 @@ StartReplication(StartReplicationCmd *cmd) if (FlushPtr < cmd->startpoint) { ereport(ERROR, - (errmsg("requested starting point %X/%X is ahead of the WAL flush position of this server %X/%X", - LSN_FORMAT_ARGS(cmd->startpoint), - LSN_FORMAT_ARGS(FlushPtr)))); + errmsg("requested starting point %X/%08X is ahead of the WAL flush position of this server %X/%08X", + LSN_FORMAT_ARGS(cmd->startpoint), + LSN_FORMAT_ARGS(FlushPtr))); } /* Start streaming from the requested point */ @@ -983,7 +983,7 @@ StartReplication(StartReplicationCmd *cmd) Datum values[2]; bool nulls[2] = {0}; - snprintf(startpos_str, sizeof(startpos_str), "%X/%X", + snprintf(startpos_str, sizeof(startpos_str), "%X/%08X", LSN_FORMAT_ARGS(sendTimeLineValidUpto)); dest = CreateDestReceiver(DestRemoteSimple); @@ -1324,7 +1324,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd) ReplicationSlotPersist(); } - snprintf(xloc, sizeof(xloc), "%X/%X", + snprintf(xloc, sizeof(xloc), "%X/%08X", LSN_FORMAT_ARGS(MyReplicationSlot->data.confirmed_flush)); dest = CreateDestReceiver(DestRemoteSimple); @@ -2429,7 +2429,7 @@ ProcessStandbyReplyMessage(void) /* Copy because timestamptz_to_str returns a static buffer */ replyTimeStr = pstrdup(timestamptz_to_str(replyTime)); - elog(DEBUG2, "write %X/%X flush %X/%X apply %X/%X%s reply_time %s", + elog(DEBUG2, "write %X/%08X flush %X/%08X apply %X/%08X%s reply_time %s", LSN_FORMAT_ARGS(writePtr), LSN_FORMAT_ARGS(flushPtr), LSN_FORMAT_ARGS(applyPtr), @@ -3251,7 +3251,7 @@ XLogSendPhysical(void) WalSndCaughtUp = true; - elog(DEBUG1, "walsender reached end of timeline at %X/%X (sent up to %X/%X)", + elog(DEBUG1, "walsender reached end of timeline at %X/%08X (sent up to %X/%08X)", LSN_FORMAT_ARGS(sendTimeLineValidUpto), LSN_FORMAT_ARGS(sentPtr)); return; @@ -3392,7 +3392,7 @@ retry: { char activitymsg[50]; - snprintf(activitymsg, sizeof(activitymsg), "streaming %X/%X", + snprintf(activitymsg, sizeof(activitymsg), "streaming %X/%08X", LSN_FORMAT_ARGS(sentPtr)); set_ps_display(activitymsg); } diff --git a/src/backend/storage/aio/method_io_uring.c b/src/backend/storage/aio/method_io_uring.c index b78048328e1..0a8c054162f 100644 --- a/src/backend/storage/aio/method_io_uring.c +++ b/src/backend/storage/aio/method_io_uring.c @@ -29,6 +29,9 @@ #ifdef IOMETHOD_IO_URING_ENABLED +#include <sys/mman.h> +#include <unistd.h> + #include <liburing.h> #include "miscadmin.h" @@ -94,12 +97,32 @@ PgAioUringContext struct io_uring io_uring_ring; } PgAioUringContext; +/* + * Information about the capabilities that io_uring has. + * + * Depending on liburing and kernel version different features are + * supported. At least for the kernel a kernel version check does not suffice + * as various vendors do backport features to older kernels :(. + */ +typedef struct PgAioUringCaps +{ + bool checked; + /* -1 if io_uring_queue_init_mem() is unsupported */ + int mem_init_size; +} PgAioUringCaps; + + /* PgAioUringContexts for all backends */ static PgAioUringContext *pgaio_uring_contexts; /* the current backend's context */ static PgAioUringContext *pgaio_my_uring_context; +static PgAioUringCaps pgaio_uring_caps = +{ + .checked = false, + .mem_init_size = -1, +}; static uint32 pgaio_uring_procs(void) @@ -111,16 +134,145 @@ pgaio_uring_procs(void) return MaxBackends + NUM_AUXILIARY_PROCS - MAX_IO_WORKERS; } -static Size +/* + * Initializes pgaio_uring_caps, unless that's already done. + */ +static void +pgaio_uring_check_capabilities(void) +{ + if (pgaio_uring_caps.checked) + return; + + /* + * By default io_uring creates a shared memory mapping for each io_uring + * instance, leading to a large number of memory mappings. Unfortunately a + * large number of memory mappings slows things down, backend exit is + * particularly affected. To address that, newer kernels (6.5) support + * using user-provided memory for the memory, by putting the relevant + * memory into shared memory we don't need any additional mappings. + * + * To know whether this is supported, we unfortunately need to probe the + * kernel by trying to create a ring with userspace-provided memory. This + * also has a secondary benefit: We can determine precisely how much + * memory we need for each io_uring instance. + */ +#if defined(HAVE_LIBURING_QUEUE_INIT_MEM) && defined(IORING_SETUP_NO_MMAP) + { + struct io_uring test_ring; + size_t ring_size; + void *ring_ptr; + struct io_uring_params p = {0}; + int ret; + + /* + * Liburing does not yet provide an API to query how much memory a + * ring will need. So we over-estimate it here. As the memory is freed + * just below that's small temporary waste of memory. + * + * 1MB is more than enough for rings within io_max_concurrency's + * range. + */ + ring_size = 1024 * 1024; + + /* + * Hard to believe a system exists where 1MB would not be a multiple + * of the page size. But it's cheap to ensure... + */ + ring_size -= ring_size % sysconf(_SC_PAGESIZE); + + ring_ptr = mmap(NULL, ring_size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (ring_ptr == MAP_FAILED) + elog(ERROR, + "mmap(%zu) to determine io_uring_queue_init_mem() support failed: %m", + ring_size); + + ret = io_uring_queue_init_mem(io_max_concurrency, &test_ring, &p, ring_ptr, ring_size); + if (ret > 0) + { + pgaio_uring_caps.mem_init_size = ret; + + elog(DEBUG1, + "can use combined memory mapping for io_uring, each ring needs %d bytes", + ret); + + /* clean up the created ring, it was just for a test */ + io_uring_queue_exit(&test_ring); + } + else + { + /* + * There are different reasons for ring creation to fail, but it's + * ok to treat that just as io_uring_queue_init_mem() not being + * supported. We'll report a more detailed error in + * pgaio_uring_shmem_init(). + */ + errno = -ret; + elog(DEBUG1, + "cannot use combined memory mapping for io_uring, ring creation failed: %m"); + + } + + if (munmap(ring_ptr, ring_size) != 0) + elog(ERROR, "munmap() failed: %m"); + } +#else + { + elog(DEBUG1, + "can't use combined memory mapping for io_uring, kernel or liburing too old"); + } +#endif + + pgaio_uring_caps.checked = true; +} + +/* + * Memory for all PgAioUringContext instances + */ +static size_t pgaio_uring_context_shmem_size(void) { return mul_size(pgaio_uring_procs(), sizeof(PgAioUringContext)); } +/* + * Memory for the combined memory used by io_uring instances. Returns 0 if + * that is not supported by kernel/liburing. + */ +static size_t +pgaio_uring_ring_shmem_size(void) +{ + size_t sz = 0; + + if (pgaio_uring_caps.mem_init_size > 0) + { + /* + * Memory for rings needs to be allocated to the page boundary, + * reserve space. Luckily it does not need to be aligned to hugepage + * boundaries, even if huge pages are used. + */ + sz = add_size(sz, sysconf(_SC_PAGESIZE)); + sz = add_size(sz, mul_size(pgaio_uring_procs(), + pgaio_uring_caps.mem_init_size)); + } + + return sz; +} + static size_t pgaio_uring_shmem_size(void) { - return pgaio_uring_context_shmem_size(); + size_t sz; + + /* + * Kernel and liburing support for various features influences how much + * shmem we need, perform the necessary checks. + */ + pgaio_uring_check_capabilities(); + + sz = pgaio_uring_context_shmem_size(); + sz = add_size(sz, pgaio_uring_ring_shmem_size()); + + return sz; } static void @@ -128,13 +280,38 @@ pgaio_uring_shmem_init(bool first_time) { int TotalProcs = pgaio_uring_procs(); bool found; + char *shmem; + size_t ring_mem_remain = 0; + char *ring_mem_next = 0; - pgaio_uring_contexts = (PgAioUringContext *) - ShmemInitStruct("AioUring", pgaio_uring_shmem_size(), &found); - + /* + * We allocate memory for all PgAioUringContext instances and, if + * supported, the memory required for each of the io_uring instances, in + * one ShmemInitStruct(). + */ + shmem = ShmemInitStruct("AioUringContext", pgaio_uring_shmem_size(), &found); if (found) return; + pgaio_uring_contexts = (PgAioUringContext *) shmem; + shmem += pgaio_uring_context_shmem_size(); + + /* if supported, handle memory alignment / sizing for io_uring memory */ + if (pgaio_uring_caps.mem_init_size > 0) + { + ring_mem_remain = pgaio_uring_ring_shmem_size(); + ring_mem_next = (char *) shmem; + + /* align to page boundary, see also pgaio_uring_ring_shmem_size() */ + ring_mem_next = (char *) TYPEALIGN(sysconf(_SC_PAGESIZE), ring_mem_next); + + /* account for alignment */ + ring_mem_remain -= ring_mem_next - shmem; + shmem += ring_mem_next - shmem; + + shmem += ring_mem_remain; + } + for (int contextno = 0; contextno < TotalProcs; contextno++) { PgAioUringContext *context = &pgaio_uring_contexts[contextno]; @@ -158,7 +335,28 @@ pgaio_uring_shmem_init(bool first_time) * be worth using that - also need to evaluate if that causes * noticeable additional contention? */ - ret = io_uring_queue_init(io_max_concurrency, &context->io_uring_ring, 0); + + /* + * If supported (c.f. pgaio_uring_check_capabilities()), create ring + * with its data in shared memory. Otherwise fall back io_uring + * creating a memory mapping for each ring. + */ +#if defined(HAVE_LIBURING_QUEUE_INIT_MEM) && defined(IORING_SETUP_NO_MMAP) + if (pgaio_uring_caps.mem_init_size > 0) + { + struct io_uring_params p = {0}; + + ret = io_uring_queue_init_mem(io_max_concurrency, &context->io_uring_ring, &p, ring_mem_next, ring_mem_remain); + + ring_mem_remain -= ret; + ring_mem_next += ret; + } + else +#endif + { + ret = io_uring_queue_init(io_max_concurrency, &context->io_uring_ring, 0); + } + if (ret < 0) { char *hint = NULL; diff --git a/src/backend/storage/aio/method_worker.c b/src/backend/storage/aio/method_worker.c index 36be179678d..bf8f77e6ff6 100644 --- a/src/backend/storage/aio/method_worker.c +++ b/src/backend/storage/aio/method_worker.c @@ -52,26 +52,26 @@ #define IO_WORKER_WAKEUP_FANOUT 2 -typedef struct AioWorkerSubmissionQueue +typedef struct PgAioWorkerSubmissionQueue { uint32 size; uint32 mask; uint32 head; uint32 tail; - uint32 ios[FLEXIBLE_ARRAY_MEMBER]; -} AioWorkerSubmissionQueue; + uint32 sqes[FLEXIBLE_ARRAY_MEMBER]; +} PgAioWorkerSubmissionQueue; -typedef struct AioWorkerSlot +typedef struct PgAioWorkerSlot { Latch *latch; bool in_use; -} AioWorkerSlot; +} PgAioWorkerSlot; -typedef struct AioWorkerControl +typedef struct PgAioWorkerControl { uint64 idle_worker_mask; - AioWorkerSlot workers[FLEXIBLE_ARRAY_MEMBER]; -} AioWorkerControl; + PgAioWorkerSlot workers[FLEXIBLE_ARRAY_MEMBER]; +} PgAioWorkerControl; static size_t pgaio_worker_shmem_size(void); @@ -96,8 +96,8 @@ int io_workers = 3; static int io_worker_queue_size = 64; static int MyIoWorkerId; -static AioWorkerSubmissionQueue *io_worker_submission_queue; -static AioWorkerControl *io_worker_control; +static PgAioWorkerSubmissionQueue *io_worker_submission_queue; +static PgAioWorkerControl *io_worker_control; static size_t @@ -106,15 +106,15 @@ pgaio_worker_queue_shmem_size(int *queue_size) /* Round size up to next power of two so we can make a mask. */ *queue_size = pg_nextpower2_32(io_worker_queue_size); - return offsetof(AioWorkerSubmissionQueue, ios) + + return offsetof(PgAioWorkerSubmissionQueue, sqes) + sizeof(uint32) * *queue_size; } static size_t pgaio_worker_control_shmem_size(void) { - return offsetof(AioWorkerControl, workers) + - sizeof(AioWorkerSlot) * MAX_IO_WORKERS; + return offsetof(PgAioWorkerControl, workers) + + sizeof(PgAioWorkerSlot) * MAX_IO_WORKERS; } static size_t @@ -162,7 +162,7 @@ pgaio_worker_shmem_init(bool first_time) } static int -pgaio_choose_idle_worker(void) +pgaio_worker_choose_idle(void) { int worker; @@ -172,6 +172,7 @@ pgaio_choose_idle_worker(void) /* Find the lowest bit position, and clear it. */ worker = pg_rightmost_one_pos64(io_worker_control->idle_worker_mask); io_worker_control->idle_worker_mask &= ~(UINT64_C(1) << worker); + Assert(io_worker_control->workers[worker].in_use); return worker; } @@ -179,7 +180,7 @@ pgaio_choose_idle_worker(void) static bool pgaio_worker_submission_queue_insert(PgAioHandle *ioh) { - AioWorkerSubmissionQueue *queue; + PgAioWorkerSubmissionQueue *queue; uint32 new_head; queue = io_worker_submission_queue; @@ -191,7 +192,7 @@ pgaio_worker_submission_queue_insert(PgAioHandle *ioh) return false; /* full */ } - queue->ios[queue->head] = pgaio_io_get_id(ioh); + queue->sqes[queue->head] = pgaio_io_get_id(ioh); queue->head = new_head; return true; @@ -200,14 +201,14 @@ pgaio_worker_submission_queue_insert(PgAioHandle *ioh) static uint32 pgaio_worker_submission_queue_consume(void) { - AioWorkerSubmissionQueue *queue; + PgAioWorkerSubmissionQueue *queue; uint32 result; queue = io_worker_submission_queue; if (queue->tail == queue->head) return UINT32_MAX; /* empty */ - result = queue->ios[queue->tail]; + result = queue->sqes[queue->tail]; queue->tail = (queue->tail + 1) & (queue->size - 1); return result; @@ -240,37 +241,37 @@ pgaio_worker_needs_synchronous_execution(PgAioHandle *ioh) } static void -pgaio_worker_submit_internal(int nios, PgAioHandle *ios[]) +pgaio_worker_submit_internal(int num_staged_ios, PgAioHandle **staged_ios) { PgAioHandle *synchronous_ios[PGAIO_SUBMIT_BATCH_SIZE]; int nsync = 0; Latch *wakeup = NULL; int worker; - Assert(nios <= PGAIO_SUBMIT_BATCH_SIZE); + Assert(num_staged_ios <= PGAIO_SUBMIT_BATCH_SIZE); LWLockAcquire(AioWorkerSubmissionQueueLock, LW_EXCLUSIVE); - for (int i = 0; i < nios; ++i) + for (int i = 0; i < num_staged_ios; ++i) { - Assert(!pgaio_worker_needs_synchronous_execution(ios[i])); - if (!pgaio_worker_submission_queue_insert(ios[i])) + Assert(!pgaio_worker_needs_synchronous_execution(staged_ios[i])); + if (!pgaio_worker_submission_queue_insert(staged_ios[i])) { /* * We'll do it synchronously, but only after we've sent as many as * we can to workers, to maximize concurrency. */ - synchronous_ios[nsync++] = ios[i]; + synchronous_ios[nsync++] = staged_ios[i]; continue; } if (wakeup == NULL) { /* Choose an idle worker to wake up if we haven't already. */ - worker = pgaio_choose_idle_worker(); + worker = pgaio_worker_choose_idle(); if (worker >= 0) wakeup = io_worker_control->workers[worker].latch; - pgaio_debug_io(DEBUG4, ios[i], + pgaio_debug_io(DEBUG4, staged_ios[i], "choosing worker %d", worker); } @@ -316,6 +317,7 @@ pgaio_worker_die(int code, Datum arg) Assert(io_worker_control->workers[MyIoWorkerId].in_use); Assert(io_worker_control->workers[MyIoWorkerId].latch == MyLatch); + io_worker_control->idle_worker_mask &= ~(UINT64_C(1) << MyIoWorkerId); io_worker_control->workers[MyIoWorkerId].in_use = false; io_worker_control->workers[MyIoWorkerId].latch = NULL; LWLockRelease(AioWorkerSubmissionQueueLock); @@ -488,7 +490,7 @@ IoWorkerMain(const void *startup_data, size_t startup_data_len) IO_WORKER_WAKEUP_FANOUT); for (int i = 0; i < nwakeups; ++i) { - if ((worker = pgaio_choose_idle_worker()) < 0) + if ((worker = pgaio_worker_choose_idle()) < 0) break; latches[nlatches++] = io_worker_control->workers[worker].latch; } @@ -573,6 +575,12 @@ IoWorkerMain(const void *startup_data, size_t startup_data_len) } CHECK_FOR_INTERRUPTS(); + + if (ConfigReloadPending) + { + ConfigReloadPending = false; + ProcessConfigFile(PGC_SIGHUP); + } } error_context_stack = errcallback.previous; diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c index bd68d7e0ca9..6afdd28dba6 100644 --- a/src/backend/storage/buffer/bufmgr.c +++ b/src/backend/storage/buffer/bufmgr.c @@ -3339,10 +3339,10 @@ UnpinBufferNoOwner(BufferDesc *buf) * BufferSync -- Write out all dirty buffers in the pool. * * This is called at checkpoint time to write out all dirty shared buffers. - * The checkpoint request flags should be passed in. If CHECKPOINT_IMMEDIATE - * is set, we disable delays between writes; if CHECKPOINT_IS_SHUTDOWN, - * CHECKPOINT_END_OF_RECOVERY or CHECKPOINT_FLUSH_ALL is set, we write even - * unlogged buffers, which are otherwise skipped. The remaining flags + * The checkpoint request flags should be passed in. If CHECKPOINT_FAST is + * set, we disable delays between writes; if CHECKPOINT_IS_SHUTDOWN, + * CHECKPOINT_END_OF_RECOVERY or CHECKPOINT_FLUSH_UNLOGGED is set, we write + * even unlogged buffers, which are otherwise skipped. The remaining flags * currently have no effect here. */ static void @@ -3367,7 +3367,7 @@ BufferSync(int flags) * recovery, we write all dirty buffers. */ if (!((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY | - CHECKPOINT_FLUSH_ALL)))) + CHECKPOINT_FLUSH_UNLOGGED)))) mask |= BM_PERMANENT; /* diff --git a/src/backend/storage/ipc/dsm_registry.c b/src/backend/storage/ipc/dsm_registry.c index 828c2ff0c7f..1682cc6d34c 100644 --- a/src/backend/storage/ipc/dsm_registry.c +++ b/src/backend/storage/ipc/dsm_registry.c @@ -40,10 +40,12 @@ #include "postgres.h" +#include "funcapi.h" #include "lib/dshash.h" #include "storage/dsm_registry.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "utils/builtins.h" #include "utils/memutils.h" #define DSMR_NAME_LEN 128 @@ -88,6 +90,13 @@ typedef enum DSMREntryType DSMR_ENTRY_TYPE_DSH, } DSMREntryType; +static const char *const DSMREntryTypeNames[] = +{ + [DSMR_ENTRY_TYPE_DSM] = "segment", + [DSMR_ENTRY_TYPE_DSA] = "area", + [DSMR_ENTRY_TYPE_DSH] = "hash", +}; + typedef struct DSMRegistryEntry { char name[DSMR_NAME_LEN]; @@ -435,3 +444,43 @@ GetNamedDSHash(const char *name, const dshash_parameters *params, bool *found) return ret; } + +Datum +pg_get_dsm_registry_allocations(PG_FUNCTION_ARGS) +{ + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + DSMRegistryEntry *entry; + MemoryContext oldcontext; + dshash_seq_status status; + + InitMaterializedSRF(fcinfo, MAT_SRF_USE_EXPECTED_DESC); + + /* Be sure any local memory allocated by DSM/DSA routines is persistent. */ + oldcontext = MemoryContextSwitchTo(TopMemoryContext); + init_dsm_registry(); + MemoryContextSwitchTo(oldcontext); + + dshash_seq_init(&status, dsm_registry_table, false); + while ((entry = dshash_seq_next(&status)) != NULL) + { + Datum vals[3]; + bool nulls[3] = {0}; + + vals[0] = CStringGetTextDatum(entry->name); + vals[1] = CStringGetTextDatum(DSMREntryTypeNames[entry->type]); + + /* + * Since we can't know the size of DSA/dshash entries without first + * attaching to them, return NULL for those. + */ + if (entry->type == DSMR_ENTRY_TYPE_DSM) + vals[2] = Int64GetDatum(entry->data.dsm.size); + else + nulls[2] = true; + + tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, vals, nulls); + } + dshash_seq_term(&status); + + return (Datum) 0; +} diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index 7fa8d9247e0..4222bdab078 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1376,7 +1376,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) if (xlrec.subxid_overflow) elog(DEBUG2, - "snapshot of %d running transactions overflowed (lsn %X/%X oldest xid %u latest complete %u next xid %u)", + "snapshot of %d running transactions overflowed (lsn %X/%08X oldest xid %u latest complete %u next xid %u)", CurrRunningXacts->xcnt, LSN_FORMAT_ARGS(recptr), CurrRunningXacts->oldestRunningXid, @@ -1384,7 +1384,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) CurrRunningXacts->nextXid); else elog(DEBUG2, - "snapshot of %d+%d running transaction ids (lsn %X/%X oldest xid %u latest complete %u next xid %u)", + "snapshot of %d+%d running transaction ids (lsn %X/%08X oldest xid %u latest complete %u next xid %u)", CurrRunningXacts->xcnt, CurrRunningXacts->subxcnt, LSN_FORMAT_ARGS(recptr), CurrRunningXacts->oldestRunningXid, diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c index aff8510755f..4c1faf5575c 100644 --- a/src/backend/tcop/utility.c +++ b/src/backend/tcop/utility.c @@ -943,17 +943,7 @@ standard_ProcessUtility(PlannedStmt *pstmt, break; case T_CheckPointStmt: - if (!has_privs_of_role(GetUserId(), ROLE_PG_CHECKPOINT)) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - /* translator: %s is name of a SQL command, eg CHECKPOINT */ - errmsg("permission denied to execute %s command", - "CHECKPOINT"), - errdetail("Only roles with privileges of the \"%s\" role may execute this command.", - "pg_checkpoint"))); - - RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_WAIT | - (RecoveryInProgress() ? 0 : CHECKPOINT_FORCE)); + ExecCheckpoint(pstate, (CheckPointStmt *) parsetree); break; /* diff --git a/src/backend/tsearch/ts_locale.c b/src/backend/tsearch/ts_locale.c index b77d8c23d36..4801fe90089 100644 --- a/src/backend/tsearch/ts_locale.c +++ b/src/backend/tsearch/ts_locale.c @@ -36,7 +36,7 @@ t_isalpha(const char *ptr) { int clen = pg_mblen(ptr); wchar_t character[WC_BUF_LEN]; - pg_locale_t mylocale = 0; /* TODO */ + locale_t mylocale = 0; /* TODO */ if (clen == 1 || database_ctype_is_c) return isalpha(TOUCHAR(ptr)); @@ -51,7 +51,7 @@ t_isalnum(const char *ptr) { int clen = pg_mblen(ptr); wchar_t character[WC_BUF_LEN]; - pg_locale_t mylocale = 0; /* TODO */ + locale_t mylocale = 0; /* TODO */ if (clen == 1 || database_ctype_is_c) return isalnum(TOUCHAR(ptr)); diff --git a/src/backend/tsearch/wparser_def.c b/src/backend/tsearch/wparser_def.c index 79bcd32a063..e2dd3da3aa3 100644 --- a/src/backend/tsearch/wparser_def.c +++ b/src/backend/tsearch/wparser_def.c @@ -299,7 +299,7 @@ TParserInit(char *str, int len) */ if (prs->charmaxlen > 1) { - pg_locale_t mylocale = 0; /* TODO */ + locale_t mylocale = 0; /* TODO */ prs->usewide = true; if (database_ctype_is_c) diff --git a/src/backend/utils/adt/acl.c b/src/backend/utils/adt/acl.c index ca3c5ee3df3..1213f9106d5 100644 --- a/src/backend/utils/adt/acl.c +++ b/src/backend/utils/adt/acl.c @@ -135,6 +135,22 @@ static void RoleMembershipCacheCallback(Datum arg, int cacheid, uint32 hashvalue /* + * Test whether an identifier char can be left unquoted in ACLs. + * + * Formerly, we used isalnum() even on non-ASCII characters, resulting in + * unportable behavior. To ensure dump compatibility with old versions, + * we now treat high-bit-set characters as always requiring quoting during + * putid(), but getid() will always accept them without quotes. + */ +static inline bool +is_safe_acl_char(unsigned char c, bool is_getid) +{ + if (IS_HIGHBIT_SET(c)) + return is_getid; + return isalnum(c) || c == '_'; +} + +/* * getid * Consumes the first alphanumeric string (identifier) found in string * 's', ignoring any leading white space. If it finds a double quote @@ -159,21 +175,22 @@ getid(const char *s, char *n, Node *escontext) while (isspace((unsigned char) *s)) s++; - /* This code had better match what putid() does, below */ for (; *s != '\0' && - (isalnum((unsigned char) *s) || - *s == '_' || - *s == '"' || - in_quotes); + (in_quotes || *s == '"' || is_safe_acl_char(*s, true)); s++) { if (*s == '"') { + if (!in_quotes) + { + in_quotes = true; + continue; + } /* safe to look at next char (could be '\0' though) */ if (*(s + 1) != '"') { - in_quotes = !in_quotes; + in_quotes = false; continue; } /* it's an escaped double quote; skip the escaping char */ @@ -207,10 +224,10 @@ putid(char *p, const char *s) const char *src; bool safe = true; + /* Detect whether we need to use double quotes */ for (src = s; *src; src++) { - /* This test had better match what getid() does, above */ - if (!isalnum((unsigned char) *src) && *src != '_') + if (!is_safe_acl_char(*src, false)) { safe = false; break; diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c index e9f9fc1e369..8d88b53c375 100644 --- a/src/backend/utils/adt/pg_locale_libc.c +++ b/src/backend/utils/adt/pg_locale_libc.c @@ -457,7 +457,7 @@ strlower_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, /* Output workspace cannot have more codes than input bytes */ workspace = (wchar_t *) palloc((srclen + 1) * sizeof(wchar_t)); - char2wchar(workspace, srclen + 1, src, srclen, locale); + char2wchar(workspace, srclen + 1, src, srclen, loc); for (curr_char = 0; workspace[curr_char] != 0; curr_char++) workspace[curr_char] = towlower_l(workspace[curr_char], loc); @@ -468,7 +468,7 @@ strlower_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, max_size = curr_char * pg_database_encoding_max_length(); result = palloc(max_size + 1); - result_size = wchar2char(result, workspace, max_size + 1, locale); + result_size = wchar2char(result, workspace, max_size + 1, loc); if (result_size + 1 > destsize) return result_size; @@ -552,7 +552,7 @@ strtitle_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, /* Output workspace cannot have more codes than input bytes */ workspace = (wchar_t *) palloc((srclen + 1) * sizeof(wchar_t)); - char2wchar(workspace, srclen + 1, src, srclen, locale); + char2wchar(workspace, srclen + 1, src, srclen, loc); for (curr_char = 0; workspace[curr_char] != 0; curr_char++) { @@ -569,7 +569,7 @@ strtitle_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, max_size = curr_char * pg_database_encoding_max_length(); result = palloc(max_size + 1); - result_size = wchar2char(result, workspace, max_size + 1, locale); + result_size = wchar2char(result, workspace, max_size + 1, loc); if (result_size + 1 > destsize) return result_size; @@ -640,7 +640,7 @@ strupper_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, /* Output workspace cannot have more codes than input bytes */ workspace = (wchar_t *) palloc((srclen + 1) * sizeof(wchar_t)); - char2wchar(workspace, srclen + 1, src, srclen, locale); + char2wchar(workspace, srclen + 1, src, srclen, loc); for (curr_char = 0; workspace[curr_char] != 0; curr_char++) workspace[curr_char] = towupper_l(workspace[curr_char], loc); @@ -651,7 +651,7 @@ strupper_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen, max_size = curr_char * pg_database_encoding_max_length(); result = palloc(max_size + 1); - result_size = wchar2char(result, workspace, max_size + 1, locale); + result_size = wchar2char(result, workspace, max_size + 1, loc); if (result_size + 1 > destsize) return result_size; @@ -1130,7 +1130,7 @@ wcstombs_l(char *dest, const wchar_t *src, size_t n, locale_t loc) * zero-terminated. The output will be zero-terminated iff there is room. */ size_t -wchar2char(char *to, const wchar_t *from, size_t tolen, pg_locale_t locale) +wchar2char(char *to, const wchar_t *from, size_t tolen, locale_t loc) { size_t result; @@ -1160,7 +1160,7 @@ wchar2char(char *to, const wchar_t *from, size_t tolen, pg_locale_t locale) } else #endif /* WIN32 */ - if (locale == (pg_locale_t) 0) + if (loc == (locale_t) 0) { /* Use wcstombs directly for the default locale */ result = wcstombs(to, from, tolen); @@ -1168,7 +1168,7 @@ wchar2char(char *to, const wchar_t *from, size_t tolen, pg_locale_t locale) else { /* Use wcstombs_l for nondefault locales */ - result = wcstombs_l(to, from, tolen, locale->info.lt); + result = wcstombs_l(to, from, tolen, loc); } return result; @@ -1185,7 +1185,7 @@ wchar2char(char *to, const wchar_t *from, size_t tolen, pg_locale_t locale) */ size_t char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen, - pg_locale_t locale) + locale_t loc) { size_t result; @@ -1220,7 +1220,7 @@ char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen, /* mbstowcs requires ending '\0' */ char *str = pnstrdup(from, fromlen); - if (locale == (pg_locale_t) 0) + if (loc == (locale_t) 0) { /* Use mbstowcs directly for the default locale */ result = mbstowcs(to, str, tolen); @@ -1228,7 +1228,7 @@ char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen, else { /* Use mbstowcs_l for nondefault locales */ - result = mbstowcs_l(to, str, tolen, locale->info.lt); + result = mbstowcs_l(to, str, tolen, loc); } pfree(str); diff --git a/src/backend/utils/adt/pg_lsn.c b/src/backend/utils/adt/pg_lsn.c index 16311590a14..12de2446f5b 100644 --- a/src/backend/utils/adt/pg_lsn.c +++ b/src/backend/utils/adt/pg_lsn.c @@ -83,7 +83,7 @@ pg_lsn_out(PG_FUNCTION_ARGS) char buf[MAXPG_LSNLEN + 1]; char *result; - snprintf(buf, sizeof buf, "%X/%X", LSN_FORMAT_ARGS(lsn)); + snprintf(buf, sizeof buf, "%X/%08X", LSN_FORMAT_ARGS(lsn)); result = pstrdup(buf); PG_RETURN_CSTRING(result); } diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index 2bd39b6ac4b..f7b731825fc 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -532,7 +532,7 @@ xmltext(PG_FUNCTION_ARGS) volatile xmlChar *xmlbuf = NULL; PgXmlErrorContext *xmlerrcxt; - /* Otherwise, we gotta spin up some error handling. */ + /* First we gotta spin up some error handling. */ xmlerrcxt = pg_xml_init(PG_XML_STRICTNESS_ALL); PG_TRY(); @@ -685,7 +685,7 @@ xmltotext_with_options(xmltype *data, XmlOptionType xmloption_arg, bool indent) volatile xmlBufferPtr buf = NULL; volatile xmlSaveCtxtPtr ctxt = NULL; ErrorSaveContext escontext = {T_ErrorSaveContext}; - PgXmlErrorContext *xmlerrcxt; + PgXmlErrorContext *volatile xmlerrcxt = NULL; #endif if (xmloption_arg != XMLOPTION_DOCUMENT && !indent) @@ -726,13 +726,18 @@ xmltotext_with_options(xmltype *data, XmlOptionType xmloption_arg, bool indent) return (text *) data; } - /* Otherwise, we gotta spin up some error handling. */ - xmlerrcxt = pg_xml_init(PG_XML_STRICTNESS_ALL); - + /* + * Otherwise, we gotta spin up some error handling. Unlike most other + * routines in this module, we already have a libxml "doc" structure to + * free, so we need to call pg_xml_init() inside the PG_TRY and be + * prepared for it to fail (typically due to palloc OOM). + */ PG_TRY(); { size_t decl_len = 0; + xmlerrcxt = pg_xml_init(PG_XML_STRICTNESS_ALL); + /* The serialized data will go into this buffer. */ buf = xmlBufferCreate(); @@ -863,10 +868,10 @@ xmltotext_with_options(xmltype *data, XmlOptionType xmloption_arg, bool indent) xmlSaveClose(ctxt); if (buf) xmlBufferFree(buf); - if (doc) - xmlFreeDoc(doc); + xmlFreeDoc(doc); - pg_xml_done(xmlerrcxt, true); + if (xmlerrcxt) + pg_xml_done(xmlerrcxt, true); PG_RE_THROW(); } diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index 511dc32d519..d14b1678e7f 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -3081,7 +3081,7 @@ struct config_int ConfigureNamesInt[] = }, &max_slot_wal_keep_size_mb, -1, -1, MAX_KILOBYTES, - check_max_slot_wal_keep_size, NULL, NULL + NULL, NULL, NULL }, { @@ -3100,11 +3100,11 @@ struct config_int ConfigureNamesInt[] = gettext_noop("Sets the duration a replication slot can remain idle before " "it is invalidated."), NULL, - GUC_UNIT_MIN + GUC_UNIT_S }, - &idle_replication_slot_timeout_mins, - 0, 0, INT_MAX / SECS_PER_MINUTE, - check_idle_replication_slot_timeout, NULL, NULL + &idle_replication_slot_timeout_secs, + 0, 0, INT_MAX, + NULL, NULL, NULL }, { diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 341f88adc87..a9d8293474a 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -342,7 +342,7 @@ # (change requires restart) #wal_keep_size = 0 # in megabytes; 0 disables #max_slot_wal_keep_size = -1 # in megabytes; -1 disables -#idle_replication_slot_timeout = 0 # in minutes; 0 disables +#idle_replication_slot_timeout = 0 # in seconds; 0 disables #wal_sender_timeout = 60s # in milliseconds; 0 disables #track_commit_timestamp = off # collect timestamp of transaction commit # (change requires restart) |