diff options
Diffstat (limited to 'src/backend')
47 files changed, 881 insertions, 725 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 3c06ac45532..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, @@ -1847,7 +1844,7 @@ AtPrepare_MultiXact(void) * Clean up after successful PREPARE TRANSACTION */ void -PostPrepare_MultiXact(TransactionId xid) +PostPrepare_MultiXact(FullTransactionId fxid) { MultiXactId myOldestMember; @@ -1858,7 +1855,7 @@ PostPrepare_MultiXact(TransactionId xid) myOldestMember = OldestMemberMXactId[MyProcNumber]; if (MultiXactIdIsValid(myOldestMember)) { - ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(xid, false); + ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(fxid, false); /* * Even though storing MultiXactId is atomic, acquire lock to make @@ -1896,10 +1893,10 @@ PostPrepare_MultiXact(TransactionId xid) * Recover the state of a prepared transaction at startup */ void -multixact_twophase_recover(TransactionId xid, uint16 info, +multixact_twophase_recover(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(xid, false); + ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(fxid, false); MultiXactId oldestMember; /* @@ -1917,10 +1914,10 @@ multixact_twophase_recover(TransactionId xid, uint16 info, * Similar to AtEOXact_MultiXact but for COMMIT PREPARED */ void -multixact_twophase_postcommit(TransactionId xid, uint16 info, +multixact_twophase_postcommit(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(xid, true); + ProcNumber dummyProcNumber = TwoPhaseGetDummyProcNumber(fxid, true); Assert(len == sizeof(MultiXactId)); @@ -1932,10 +1929,10 @@ multixact_twophase_postcommit(TransactionId xid, uint16 info, * This is actually just the same as the COMMIT case. */ void -multixact_twophase_postabort(TransactionId xid, uint16 info, +multixact_twophase_postabort(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - multixact_twophase_postcommit(xid, info, recdata, len); + multixact_twophase_postcommit(fxid, info, recdata, len); } /* @@ -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 73a80559194..85cbe397cb2 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -159,7 +159,7 @@ typedef struct GlobalTransactionData */ XLogRecPtr prepare_start_lsn; /* XLOG offset of prepare record start */ XLogRecPtr prepare_end_lsn; /* XLOG offset of prepare record end */ - TransactionId xid; /* The GXACT id */ + FullTransactionId fxid; /* The GXACT full xid */ Oid owner; /* ID of user that executed the xact */ ProcNumber locking_backend; /* backend currently working on the xact */ @@ -197,6 +197,7 @@ static GlobalTransaction MyLockedGxact = NULL; static bool twophaseExitRegistered = false; +static void PrepareRedoRemoveFull(FullTransactionId fxid, bool giveWarning); static void RecordTransactionCommitPrepared(TransactionId xid, int nchildren, TransactionId *children, @@ -216,19 +217,19 @@ static void RecordTransactionAbortPrepared(TransactionId xid, int nstats, xl_xact_stats_item *stats, const char *gid); -static void ProcessRecords(char *bufptr, TransactionId xid, +static void ProcessRecords(char *bufptr, FullTransactionId fxid, const TwoPhaseCallback callbacks[]); static void RemoveGXact(GlobalTransaction gxact); static void XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len); -static char *ProcessTwoPhaseBuffer(TransactionId xid, +static char *ProcessTwoPhaseBuffer(FullTransactionId fxid, XLogRecPtr prepare_start_lsn, bool fromdisk, bool setParent, bool setNextXid); -static void MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, +static void MarkAsPreparingGuts(GlobalTransaction gxact, FullTransactionId fxid, const char *gid, TimestampTz prepared_at, Oid owner, Oid databaseid); -static void RemoveTwoPhaseFile(TransactionId xid, bool giveWarning); -static void RecreateTwoPhaseFile(TransactionId xid, void *content, int len); +static void RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning); +static void RecreateTwoPhaseFile(FullTransactionId fxid, void *content, int len); /* * Initialization of shared memory @@ -356,7 +357,7 @@ PostPrepare_Twophase(void) * Reserve the GID for the given transaction. */ GlobalTransaction -MarkAsPreparing(TransactionId xid, const char *gid, +MarkAsPreparing(FullTransactionId fxid, const char *gid, TimestampTz prepared_at, Oid owner, Oid databaseid) { GlobalTransaction gxact; @@ -407,7 +408,7 @@ MarkAsPreparing(TransactionId xid, const char *gid, gxact = TwoPhaseState->freeGXacts; TwoPhaseState->freeGXacts = gxact->next; - MarkAsPreparingGuts(gxact, xid, gid, prepared_at, owner, databaseid); + MarkAsPreparingGuts(gxact, fxid, gid, prepared_at, owner, databaseid); gxact->ondisk = false; @@ -430,11 +431,13 @@ MarkAsPreparing(TransactionId xid, const char *gid, * Note: This function should be called with appropriate locks held. */ static void -MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid, - TimestampTz prepared_at, Oid owner, Oid databaseid) +MarkAsPreparingGuts(GlobalTransaction gxact, FullTransactionId fxid, + const char *gid, TimestampTz prepared_at, Oid owner, + Oid databaseid) { PGPROC *proc; int i; + TransactionId xid = XidFromFullTransactionId(fxid); Assert(LWLockHeldByMeInMode(TwoPhaseStateLock, LW_EXCLUSIVE)); @@ -479,7 +482,7 @@ MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid, proc->subxidStatus.count = 0; gxact->prepared_at = prepared_at; - gxact->xid = xid; + gxact->fxid = fxid; gxact->owner = owner; gxact->locking_backend = MyProcNumber; gxact->valid = false; @@ -797,12 +800,12 @@ pg_prepared_xact(PG_FUNCTION_ARGS) * caller had better hold it. */ static GlobalTransaction -TwoPhaseGetGXact(TransactionId xid, bool lock_held) +TwoPhaseGetGXact(FullTransactionId fxid, bool lock_held) { GlobalTransaction result = NULL; int i; - static TransactionId cached_xid = InvalidTransactionId; + static FullTransactionId cached_fxid = {InvalidTransactionId}; static GlobalTransaction cached_gxact = NULL; Assert(!lock_held || LWLockHeldByMe(TwoPhaseStateLock)); @@ -811,7 +814,7 @@ TwoPhaseGetGXact(TransactionId xid, bool lock_held) * During a recovery, COMMIT PREPARED, or ABORT PREPARED, we'll be called * repeatedly for the same XID. We can save work with a simple cache. */ - if (xid == cached_xid) + if (FullTransactionIdEquals(fxid, cached_fxid)) return cached_gxact; if (!lock_held) @@ -821,7 +824,7 @@ TwoPhaseGetGXact(TransactionId xid, bool lock_held) { GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; - if (gxact->xid == xid) + if (FullTransactionIdEquals(gxact->fxid, fxid)) { result = gxact; break; @@ -832,9 +835,10 @@ TwoPhaseGetGXact(TransactionId xid, bool lock_held) LWLockRelease(TwoPhaseStateLock); if (result == NULL) /* should not happen */ - elog(ERROR, "failed to find GlobalTransaction for xid %u", xid); + elog(ERROR, "failed to find GlobalTransaction for xid %u", + XidFromFullTransactionId(fxid)); - cached_xid = xid; + cached_fxid = fxid; cached_gxact = result; return result; @@ -881,7 +885,7 @@ TwoPhaseGetXidByVirtualXID(VirtualTransactionId vxid, *have_more = true; break; } - result = gxact->xid; + result = XidFromFullTransactionId(gxact->fxid); } } @@ -892,7 +896,7 @@ TwoPhaseGetXidByVirtualXID(VirtualTransactionId vxid, /* * TwoPhaseGetDummyProcNumber - * Get the dummy proc number for prepared transaction specified by XID + * Get the dummy proc number for prepared transaction * * Dummy proc numbers are similar to proc numbers of real backends. They * start at MaxBackends, and are unique across all currently active real @@ -900,24 +904,24 @@ TwoPhaseGetXidByVirtualXID(VirtualTransactionId vxid, * TwoPhaseStateLock will not be taken, so the caller had better hold it. */ ProcNumber -TwoPhaseGetDummyProcNumber(TransactionId xid, bool lock_held) +TwoPhaseGetDummyProcNumber(FullTransactionId fxid, bool lock_held) { - GlobalTransaction gxact = TwoPhaseGetGXact(xid, lock_held); + GlobalTransaction gxact = TwoPhaseGetGXact(fxid, lock_held); return gxact->pgprocno; } /* * TwoPhaseGetDummyProc - * Get the PGPROC that represents a prepared transaction specified by XID + * Get the PGPROC that represents a prepared transaction * * If lock_held is set to true, TwoPhaseStateLock will not be taken, so the * caller had better hold it. */ PGPROC * -TwoPhaseGetDummyProc(TransactionId xid, bool lock_held) +TwoPhaseGetDummyProc(FullTransactionId fxid, bool lock_held) { - GlobalTransaction gxact = TwoPhaseGetGXact(xid, lock_held); + GlobalTransaction gxact = TwoPhaseGetGXact(fxid, lock_held); return GetPGProcByNumber(gxact->pgprocno); } @@ -942,10 +946,8 @@ AdjustToFullTransactionId(TransactionId xid) } static inline int -TwoPhaseFilePath(char *path, TransactionId xid) +TwoPhaseFilePath(char *path, FullTransactionId fxid) { - FullTransactionId fxid = AdjustToFullTransactionId(xid); - return snprintf(path, MAXPGPATH, TWOPHASE_DIR "/%08X%08X", EpochFromFullTransactionId(fxid), XidFromFullTransactionId(fxid)); @@ -1049,7 +1051,7 @@ void StartPrepare(GlobalTransaction gxact) { PGPROC *proc = GetPGProcByNumber(gxact->pgprocno); - TransactionId xid = gxact->xid; + TransactionId xid = XidFromFullTransactionId(gxact->fxid); TwoPhaseFileHeader hdr; TransactionId *children; RelFileLocator *commitrels; @@ -1281,10 +1283,11 @@ RegisterTwoPhaseRecord(TwoPhaseRmgrId rmid, uint16 info, * If it looks OK (has a valid magic number and CRC), return the palloc'd * contents of the file, issuing an error when finding corrupted data. If * missing_ok is true, which indicates that missing files can be safely - * ignored, then return NULL. This state can be reached when doing recovery. + * ignored, then return NULL. This state can be reached when doing recovery + * after discarding two-phase files from frozen epochs. */ static char * -ReadTwoPhaseFile(TransactionId xid, bool missing_ok) +ReadTwoPhaseFile(FullTransactionId fxid, bool missing_ok) { char path[MAXPGPATH]; char *buf; @@ -1296,7 +1299,7 @@ ReadTwoPhaseFile(TransactionId xid, bool missing_ok) file_crc; int r; - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); fd = OpenTransientFile(path, O_RDONLY | PG_BINARY); if (fd < 0) @@ -1426,12 +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)))); } @@ -1439,7 +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) @@ -1461,6 +1464,7 @@ StandbyTransactionIdIsPrepared(TransactionId xid) char *buf; TwoPhaseFileHeader *hdr; bool result; + FullTransactionId fxid; Assert(TransactionIdIsValid(xid)); @@ -1468,7 +1472,8 @@ StandbyTransactionIdIsPrepared(TransactionId xid) return false; /* nothing to do */ /* Read and validate file */ - buf = ReadTwoPhaseFile(xid, true); + fxid = AdjustToFullTransactionId(xid); + buf = ReadTwoPhaseFile(fxid, true); if (buf == NULL) return false; @@ -1488,6 +1493,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) { GlobalTransaction gxact; PGPROC *proc; + FullTransactionId fxid; TransactionId xid; bool ondisk; char *buf; @@ -1509,7 +1515,8 @@ FinishPreparedTransaction(const char *gid, bool isCommit) */ gxact = LockGXact(gid, GetUserId()); proc = GetPGProcByNumber(gxact->pgprocno); - xid = gxact->xid; + fxid = gxact->fxid; + xid = XidFromFullTransactionId(fxid); /* * Read and validate 2PC state data. State data will typically be stored @@ -1517,7 +1524,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * to disk if for some reason they have lived for a long time. */ if (gxact->ondisk) - buf = ReadTwoPhaseFile(xid, false); + buf = ReadTwoPhaseFile(fxid, false); else XlogReadTwoPhaseData(gxact->prepare_start_lsn, &buf, NULL); @@ -1636,11 +1643,11 @@ FinishPreparedTransaction(const char *gid, bool isCommit) /* And now do the callbacks */ if (isCommit) - ProcessRecords(bufptr, xid, twophase_postcommit_callbacks); + ProcessRecords(bufptr, fxid, twophase_postcommit_callbacks); else - ProcessRecords(bufptr, xid, twophase_postabort_callbacks); + ProcessRecords(bufptr, fxid, twophase_postabort_callbacks); - PredicateLockTwoPhaseFinish(xid, isCommit); + PredicateLockTwoPhaseFinish(fxid, isCommit); /* * Read this value while holding the two-phase lock, as the on-disk 2PC @@ -1664,7 +1671,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * And now we can clean up any files we may have left. */ if (ondisk) - RemoveTwoPhaseFile(xid, true); + RemoveTwoPhaseFile(fxid, true); MyLockedGxact = NULL; @@ -1677,7 +1684,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * Scan 2PC state data in memory and call the indicated callbacks for each 2PC record. */ static void -ProcessRecords(char *bufptr, TransactionId xid, +ProcessRecords(char *bufptr, FullTransactionId fxid, const TwoPhaseCallback callbacks[]) { for (;;) @@ -1691,24 +1698,28 @@ ProcessRecords(char *bufptr, TransactionId xid, bufptr += MAXALIGN(sizeof(TwoPhaseRecordOnDisk)); if (callbacks[record->rmid] != NULL) - callbacks[record->rmid] (xid, record->info, bufptr, record->len); + callbacks[record->rmid] (fxid, record->info, bufptr, record->len); bufptr += MAXALIGN(record->len); } } /* - * Remove the 2PC file for the specified XID. + * Remove the 2PC file. * * If giveWarning is false, do not complain about file-not-present; * this is an expected case during WAL replay. + * + * This routine is used at early stages at recovery where future and + * past orphaned files are checked, hence the FullTransactionId to build + * a complete file name fit for the removal. */ static void -RemoveTwoPhaseFile(TransactionId xid, bool giveWarning) +RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning) { char path[MAXPGPATH]; - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); if (unlink(path)) if (errno != ENOENT || giveWarning) ereport(WARNING, @@ -1723,7 +1734,7 @@ RemoveTwoPhaseFile(TransactionId xid, bool giveWarning) * Note: content and len don't include CRC. */ static void -RecreateTwoPhaseFile(TransactionId xid, void *content, int len) +RecreateTwoPhaseFile(FullTransactionId fxid, void *content, int len) { char path[MAXPGPATH]; pg_crc32c statefile_crc; @@ -1734,7 +1745,7 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len) COMP_CRC32C(statefile_crc, content, len); FIN_CRC32C(statefile_crc); - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); fd = OpenTransientFile(path, O_CREAT | O_TRUNC | O_WRONLY | PG_BINARY); @@ -1846,7 +1857,7 @@ CheckPointTwoPhase(XLogRecPtr redo_horizon) int len; XlogReadTwoPhaseData(gxact->prepare_start_lsn, &buf, &len); - RecreateTwoPhaseFile(gxact->xid, buf, len); + RecreateTwoPhaseFile(gxact->fxid, buf, len); gxact->ondisk = true; gxact->prepare_start_lsn = InvalidXLogRecPtr; gxact->prepare_end_lsn = InvalidXLogRecPtr; @@ -1897,19 +1908,17 @@ restoreTwoPhaseData(void) if (strlen(clde->d_name) == 16 && strspn(clde->d_name, "0123456789ABCDEF") == 16) { - TransactionId xid; FullTransactionId fxid; char *buf; fxid = FullTransactionIdFromU64(strtou64(clde->d_name, NULL, 16)); - xid = XidFromFullTransactionId(fxid); - buf = ProcessTwoPhaseBuffer(xid, InvalidXLogRecPtr, + buf = ProcessTwoPhaseBuffer(fxid, InvalidXLogRecPtr, true, false, false); if (buf == NULL) continue; - PrepareRedoAdd(buf, InvalidXLogRecPtr, + PrepareRedoAdd(fxid, buf, InvalidXLogRecPtr, InvalidXLogRecPtr, InvalidRepOriginId); } } @@ -1968,9 +1977,7 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) Assert(gxact->inredo); - xid = gxact->xid; - - buf = ProcessTwoPhaseBuffer(xid, + buf = ProcessTwoPhaseBuffer(gxact->fxid, gxact->prepare_start_lsn, gxact->ondisk, false, true); @@ -1981,6 +1988,7 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) * OK, we think this file is valid. Incorporate xid into the * running-minimum result. */ + xid = XidFromFullTransactionId(gxact->fxid); if (TransactionIdPrecedes(xid, result)) result = xid; @@ -2036,15 +2044,12 @@ StandbyRecoverPreparedTransactions(void) LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { - TransactionId xid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; Assert(gxact->inredo); - xid = gxact->xid; - - buf = ProcessTwoPhaseBuffer(xid, + buf = ProcessTwoPhaseBuffer(gxact->fxid, gxact->prepare_start_lsn, gxact->ondisk, true, false); if (buf != NULL) @@ -2077,16 +2082,14 @@ RecoverPreparedTransactions(void) LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { - TransactionId xid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; + FullTransactionId fxid = gxact->fxid; char *bufptr; TwoPhaseFileHeader *hdr; TransactionId *subxids; const char *gid; - xid = gxact->xid; - /* * Reconstruct subtrans state for the transaction --- needed because * pg_subtrans is not preserved over a restart. Note that we are @@ -2096,17 +2099,20 @@ RecoverPreparedTransactions(void) * SubTransSetParent has been set before, if the prepared transaction * generated xid assignment records. */ - buf = ProcessTwoPhaseBuffer(xid, + buf = ProcessTwoPhaseBuffer(gxact->fxid, gxact->prepare_start_lsn, gxact->ondisk, true, false); if (buf == NULL) continue; ereport(LOG, - (errmsg("recovering prepared transaction %u from shared memory", xid))); + (errmsg("recovering prepared transaction %u of epoch %u from shared memory", + XidFromFullTransactionId(gxact->fxid), + EpochFromFullTransactionId(gxact->fxid)))); hdr = (TwoPhaseFileHeader *) buf; - Assert(TransactionIdEquals(hdr->xid, xid)); + Assert(TransactionIdEquals(hdr->xid, + XidFromFullTransactionId(gxact->fxid))); bufptr = buf + MAXALIGN(sizeof(TwoPhaseFileHeader)); gid = (const char *) bufptr; bufptr += MAXALIGN(hdr->gidlen); @@ -2122,7 +2128,7 @@ RecoverPreparedTransactions(void) * Recreate its GXACT and dummy PGPROC. But, check whether it was * added in redo and already has a shmem entry for it. */ - MarkAsPreparingGuts(gxact, xid, gid, + MarkAsPreparingGuts(gxact, gxact->fxid, gid, hdr->prepared_at, hdr->owner, hdr->database); @@ -2137,7 +2143,7 @@ RecoverPreparedTransactions(void) /* * Recover other state (notably locks) using resource managers. */ - ProcessRecords(bufptr, xid, twophase_recover_callbacks); + ProcessRecords(bufptr, fxid, twophase_recover_callbacks); /* * Release locks held by the standby process after we process each @@ -2145,7 +2151,7 @@ RecoverPreparedTransactions(void) * additional locks at any one time. */ if (InHotStandby) - StandbyReleaseLockTree(xid, hdr->nsubxacts, subxids); + StandbyReleaseLockTree(hdr->xid, hdr->nsubxacts, subxids); /* * We're done with recovering this transaction. Clear MyLockedGxact, @@ -2164,7 +2170,7 @@ RecoverPreparedTransactions(void) /* * ProcessTwoPhaseBuffer * - * Given a transaction id, read it either from disk or read it directly + * Given a FullTransactionId, read it either from disk or read it directly * via shmem xlog record pointer using the provided "prepare_start_lsn". * * If setParent is true, set up subtransaction parent linkages. @@ -2173,13 +2179,12 @@ RecoverPreparedTransactions(void) * value scanned. */ static char * -ProcessTwoPhaseBuffer(TransactionId xid, +ProcessTwoPhaseBuffer(FullTransactionId fxid, XLogRecPtr prepare_start_lsn, bool fromdisk, bool setParent, bool setNextXid) { FullTransactionId nextXid = TransamVariables->nextXid; - TransactionId origNextXid = XidFromFullTransactionId(nextXid); TransactionId *subxids; char *buf; TwoPhaseFileHeader *hdr; @@ -2191,41 +2196,46 @@ ProcessTwoPhaseBuffer(TransactionId xid, Assert(prepare_start_lsn != InvalidXLogRecPtr); /* Already processed? */ - if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) + if (TransactionIdDidCommit(XidFromFullTransactionId(fxid)) || + TransactionIdDidAbort(XidFromFullTransactionId(fxid))) { if (fromdisk) { ereport(WARNING, - (errmsg("removing stale two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); + (errmsg("removing stale two-phase state file for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + RemoveTwoPhaseFile(fxid, true); } else { ereport(WARNING, - (errmsg("removing stale two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); + (errmsg("removing stale two-phase state from memory for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + PrepareRedoRemoveFull(fxid, true); } return NULL; } /* Reject XID if too new */ - if (TransactionIdFollowsOrEquals(xid, origNextXid)) + if (FullTransactionIdFollowsOrEquals(fxid, nextXid)) { if (fromdisk) { ereport(WARNING, - (errmsg("removing future two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); + (errmsg("removing future two-phase state file for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + RemoveTwoPhaseFile(fxid, true); } else { ereport(WARNING, - (errmsg("removing future two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); + (errmsg("removing future two-phase state from memory for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); + PrepareRedoRemoveFull(fxid, true); } return NULL; } @@ -2233,7 +2243,7 @@ ProcessTwoPhaseBuffer(TransactionId xid, if (fromdisk) { /* Read and validate file */ - buf = ReadTwoPhaseFile(xid, false); + buf = ReadTwoPhaseFile(fxid, false); } else { @@ -2243,18 +2253,20 @@ ProcessTwoPhaseBuffer(TransactionId xid, /* Deconstruct header */ hdr = (TwoPhaseFileHeader *) buf; - if (!TransactionIdEquals(hdr->xid, xid)) + if (!TransactionIdEquals(hdr->xid, XidFromFullTransactionId(fxid))) { if (fromdisk) ereport(ERROR, (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("corrupted two-phase state file for transaction %u", - xid))); + errmsg("corrupted two-phase state file for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); else ereport(ERROR, (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("corrupted two-phase state in memory for transaction %u", - xid))); + errmsg("corrupted two-phase state in memory for transaction %u of epoch %u", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)))); } /* @@ -2268,14 +2280,14 @@ ProcessTwoPhaseBuffer(TransactionId xid, { TransactionId subxid = subxids[i]; - Assert(TransactionIdFollows(subxid, xid)); + Assert(TransactionIdFollows(subxid, XidFromFullTransactionId(fxid))); /* update nextXid if needed */ if (setNextXid) AdvanceNextFullTransactionIdPastXid(subxid); if (setParent) - SubTransSetParent(subxid, xid); + SubTransSetParent(subxid, XidFromFullTransactionId(fxid)); } return buf; @@ -2466,8 +2478,9 @@ RecordTransactionAbortPrepared(TransactionId xid, * data, the entry is marked as located on disk. */ void -PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, - XLogRecPtr end_lsn, RepOriginId origin_id) +PrepareRedoAdd(FullTransactionId fxid, char *buf, + XLogRecPtr start_lsn, XLogRecPtr end_lsn, + RepOriginId origin_id) { TwoPhaseFileHeader *hdr = (TwoPhaseFileHeader *) buf; char *bufptr; @@ -2477,6 +2490,13 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, Assert(LWLockHeldByMeInMode(TwoPhaseStateLock, LW_EXCLUSIVE)); Assert(RecoveryInProgress()); + if (!FullTransactionIdIsValid(fxid)) + { + Assert(InRecovery); + fxid = FullTransactionIdFromAllowableAt(TransamVariables->nextXid, + hdr->xid); + } + bufptr = buf + MAXALIGN(sizeof(TwoPhaseFileHeader)); gid = (const char *) bufptr; @@ -2505,14 +2525,15 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, { char path[MAXPGPATH]; - TwoPhaseFilePath(path, hdr->xid); + Assert(InRecovery); + TwoPhaseFilePath(path, fxid); if (access(path, F_OK) == 0) { 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; } @@ -2536,7 +2557,7 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, gxact->prepared_at = hdr->prepared_at; gxact->prepare_start_lsn = start_lsn; gxact->prepare_end_lsn = end_lsn; - gxact->xid = hdr->xid; + gxact->fxid = fxid; gxact->owner = hdr->owner; gxact->locking_backend = INVALID_PROC_NUMBER; gxact->valid = false; @@ -2555,11 +2576,13 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, false /* backward */ , false /* WAL */ ); } - elog(DEBUG2, "added 2PC data in shared memory for transaction %u", gxact->xid); + elog(DEBUG2, "added 2PC data in shared memory for transaction %u of epoch %u", + XidFromFullTransactionId(gxact->fxid), + EpochFromFullTransactionId(gxact->fxid)); } /* - * PrepareRedoRemove + * PrepareRedoRemoveFull * * Remove the corresponding gxact entry from TwoPhaseState. Also remove * the 2PC file if a prepared transaction was saved via an earlier checkpoint. @@ -2567,8 +2590,8 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, * Caller must hold TwoPhaseStateLock in exclusive mode, because TwoPhaseState * is updated. */ -void -PrepareRedoRemove(TransactionId xid, bool giveWarning) +static void +PrepareRedoRemoveFull(FullTransactionId fxid, bool giveWarning) { GlobalTransaction gxact = NULL; int i; @@ -2581,7 +2604,7 @@ PrepareRedoRemove(TransactionId xid, bool giveWarning) { gxact = TwoPhaseState->prepXacts[i]; - if (gxact->xid == xid) + if (FullTransactionIdEquals(gxact->fxid, fxid)) { Assert(gxact->inredo); found = true; @@ -2598,13 +2621,29 @@ PrepareRedoRemove(TransactionId xid, bool giveWarning) /* * And now we can clean up any files we may have left. */ - elog(DEBUG2, "removing 2PC data for transaction %u", xid); + elog(DEBUG2, "removing 2PC data for transaction %u of epoch %u ", + XidFromFullTransactionId(fxid), + EpochFromFullTransactionId(fxid)); + if (gxact->ondisk) - RemoveTwoPhaseFile(xid, giveWarning); + RemoveTwoPhaseFile(fxid, giveWarning); + RemoveGXact(gxact); } /* + * Wrapper of PrepareRedoRemoveFull(), for TransactionIds. + */ +void +PrepareRedoRemove(TransactionId xid, bool giveWarning) +{ + FullTransactionId fxid = + FullTransactionIdFromAllowableAt(TransamVariables->nextXid, xid); + + PrepareRedoRemoveFull(fxid, giveWarning); +} + +/* * LookupGXact * Check if the prepared transaction with the given GID, lsn and timestamp * exists. @@ -2648,7 +2687,7 @@ LookupGXact(const char *gid, XLogRecPtr prepare_end_lsn, * between publisher and subscriber. */ if (gxact->ondisk) - buf = ReadTwoPhaseFile(gxact->xid, false); + buf = ReadTwoPhaseFile(gxact->fxid, false); else { Assert(gxact->prepare_start_lsn); diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c index b885513f765..41601fcb280 100644 --- a/src/backend/access/transam/xact.c +++ b/src/backend/access/transam/xact.c @@ -2515,7 +2515,7 @@ static void PrepareTransaction(void) { TransactionState s = CurrentTransactionState; - TransactionId xid = GetCurrentTransactionId(); + FullTransactionId fxid = GetCurrentFullTransactionId(); GlobalTransaction gxact; TimestampTz prepared_at; @@ -2644,7 +2644,7 @@ PrepareTransaction(void) * Reserve the GID for this transaction. This could fail if the requested * GID is invalid or already in use. */ - gxact = MarkAsPreparing(xid, prepareGID, prepared_at, + gxact = MarkAsPreparing(fxid, prepareGID, prepared_at, GetUserId(), MyDatabaseId); prepareGID = NULL; @@ -2694,7 +2694,7 @@ PrepareTransaction(void) * ProcArrayClearTransaction(). Otherwise, a GetLockConflicts() would * conclude "xact already committed or aborted" for our locks. */ - PostPrepare_Locks(xid); + PostPrepare_Locks(fxid); /* * Let others know about no transaction in progress by me. This has to be @@ -2738,9 +2738,9 @@ PrepareTransaction(void) PostPrepare_smgr(); - PostPrepare_MultiXact(xid); + PostPrepare_MultiXact(fxid); - PostPrepare_PredicateLocks(xid); + PostPrepare_PredicateLocks(fxid); ResourceOwnerRelease(TopTransactionResourceOwner, RESOURCE_RELEASE_LOCKS, @@ -6420,7 +6420,8 @@ xact_redo(XLogReaderState *record) * gxact entry. */ LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); - PrepareRedoAdd(XLogRecGetData(record), + PrepareRedoAdd(InvalidFullTransactionId, + XLogRecGetData(record), record->ReadRecPtr, record->EndRecPtr, XLogRecGetOrigin(record)); diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 47ffc0a2307..a8cc6402d62 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 @@ -2492,7 +2492,7 @@ 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 +2892,7 @@ 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 +2905,9 @@ 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 +2945,7 @@ 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 +3078,7 @@ 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 +3205,7 @@ 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), @@ -6921,7 +6921,7 @@ 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 +6945,7 @@ 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, @@ -7641,7 +7641,7 @@ 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 +7652,7 @@ 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 +7682,7 @@ 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 +7751,7 @@ 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 +7831,8 @@ 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 +8016,10 @@ 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. @@ -8281,8 +8280,8 @@ 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; } 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/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/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/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..f369fce2485 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -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); 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/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/storage/lmgr/lock.c b/src/backend/storage/lmgr/lock.c index 2776ceb295b..62f3471448e 100644 --- a/src/backend/storage/lmgr/lock.c +++ b/src/backend/storage/lmgr/lock.c @@ -3539,9 +3539,9 @@ AtPrepare_Locks(void) * but that probably costs more cycles. */ void -PostPrepare_Locks(TransactionId xid) +PostPrepare_Locks(FullTransactionId fxid) { - PGPROC *newproc = TwoPhaseGetDummyProc(xid, false); + PGPROC *newproc = TwoPhaseGetDummyProc(fxid, false); HASH_SEQ_STATUS status; LOCALLOCK *locallock; LOCK *lock; @@ -4324,11 +4324,11 @@ DumpAllLocks(void) * and PANIC anyway. */ void -lock_twophase_recover(TransactionId xid, uint16 info, +lock_twophase_recover(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { TwoPhaseLockRecord *rec = (TwoPhaseLockRecord *) recdata; - PGPROC *proc = TwoPhaseGetDummyProc(xid, false); + PGPROC *proc = TwoPhaseGetDummyProc(fxid, false); LOCKTAG *locktag; LOCKMODE lockmode; LOCKMETHODID lockmethodid; @@ -4505,7 +4505,7 @@ lock_twophase_recover(TransactionId xid, uint16 info, * starting up into hot standby mode. */ void -lock_twophase_standby_recover(TransactionId xid, uint16 info, +lock_twophase_standby_recover(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { TwoPhaseLockRecord *rec = (TwoPhaseLockRecord *) recdata; @@ -4524,7 +4524,7 @@ lock_twophase_standby_recover(TransactionId xid, uint16 info, if (lockmode == AccessExclusiveLock && locktag->locktag_type == LOCKTAG_RELATION) { - StandbyAcquireAccessExclusiveLock(xid, + StandbyAcquireAccessExclusiveLock(XidFromFullTransactionId(fxid), locktag->locktag_field1 /* dboid */ , locktag->locktag_field2 /* reloid */ ); } @@ -4537,11 +4537,11 @@ lock_twophase_standby_recover(TransactionId xid, uint16 info, * Find and release the lock indicated by the 2PC record. */ void -lock_twophase_postcommit(TransactionId xid, uint16 info, +lock_twophase_postcommit(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { TwoPhaseLockRecord *rec = (TwoPhaseLockRecord *) recdata; - PGPROC *proc = TwoPhaseGetDummyProc(xid, true); + PGPROC *proc = TwoPhaseGetDummyProc(fxid, true); LOCKTAG *locktag; LOCKMETHODID lockmethodid; LockMethod lockMethodTable; @@ -4563,10 +4563,10 @@ lock_twophase_postcommit(TransactionId xid, uint16 info, * This is actually just the same as the COMMIT case. */ void -lock_twophase_postabort(TransactionId xid, uint16 info, +lock_twophase_postabort(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { - lock_twophase_postcommit(xid, info, recdata, len); + lock_twophase_postcommit(fxid, info, recdata, len); } /* diff --git a/src/backend/storage/lmgr/predicate.c b/src/backend/storage/lmgr/predicate.c index d82114ffca1..c07fb588355 100644 --- a/src/backend/storage/lmgr/predicate.c +++ b/src/backend/storage/lmgr/predicate.c @@ -191,7 +191,7 @@ * AtPrepare_PredicateLocks(void); * PostPrepare_PredicateLocks(TransactionId xid); * PredicateLockTwoPhaseFinish(TransactionId xid, bool isCommit); - * predicatelock_twophase_recover(TransactionId xid, uint16 info, + * predicatelock_twophase_recover(FullTransactionId fxid, uint16 info, * void *recdata, uint32 len); */ @@ -4856,7 +4856,7 @@ AtPrepare_PredicateLocks(void) * anyway. We only need to clean up our local state. */ void -PostPrepare_PredicateLocks(TransactionId xid) +PostPrepare_PredicateLocks(FullTransactionId fxid) { if (MySerializableXact == InvalidSerializableXact) return; @@ -4879,12 +4879,12 @@ PostPrepare_PredicateLocks(TransactionId xid) * commits or aborts. */ void -PredicateLockTwoPhaseFinish(TransactionId xid, bool isCommit) +PredicateLockTwoPhaseFinish(FullTransactionId fxid, bool isCommit) { SERIALIZABLEXID *sxid; SERIALIZABLEXIDTAG sxidtag; - sxidtag.xid = xid; + sxidtag.xid = XidFromFullTransactionId(fxid); LWLockAcquire(SerializableXactHashLock, LW_SHARED); sxid = (SERIALIZABLEXID *) @@ -4906,10 +4906,11 @@ PredicateLockTwoPhaseFinish(TransactionId xid, bool isCommit) * Re-acquire a predicate lock belonging to a transaction that was prepared. */ void -predicatelock_twophase_recover(TransactionId xid, uint16 info, +predicatelock_twophase_recover(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { TwoPhasePredicateRecord *record; + TransactionId xid = XidFromFullTransactionId(fxid); Assert(len == sizeof(TwoPhasePredicateRecord)); diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c index 28587e2916b..69df741cbf6 100644 --- a/src/backend/utils/activity/pgstat_relation.c +++ b/src/backend/utils/activity/pgstat_relation.c @@ -744,7 +744,7 @@ PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) * Load the saved counts into our local pgstats state. */ void -pgstat_twophase_postcommit(TransactionId xid, uint16 info, +pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata; @@ -780,7 +780,7 @@ pgstat_twophase_postcommit(TransactionId xid, uint16 info, * as aborted. */ void -pgstat_twophase_postabort(TransactionId xid, uint16 info, +pgstat_twophase_postabort(FullTransactionId fxid, uint16 info, void *recdata, uint32 len) { TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata; 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(); } |