Index: doc/src/sgml/runtime.sgml =================================================================== RCS file: /var/lib/cvs/pgsql/doc/src/sgml/runtime.sgml,v retrieving revision 1.296 diff -c -r1.296 runtime.sgml *** doc/src/sgml/runtime.sgml 13 Dec 2004 18:05:09 -0000 1.296 --- doc/src/sgml/runtime.sgml 14 Dec 2004 04:52:26 -0000 *************** *** 1350,1382 **** Specifies the delay between activity rounds for the background writer. In each round the writer issues writes ! for some number of dirty buffers (controllable by the ! following parameters). The selected buffers will always be ! the least recently used ones among the currently dirty ! buffers. It then sleeps for bgwriter_delay ! milliseconds, and repeats. The default value is 200. Note ! that on many systems, the effective resolution of sleep ! delays is 10 milliseconds; setting bgwriter_delay ! to a value that is not a multiple of 10 may have the same ! results as setting it to the next higher multiple of 10. ! This option can only be set at server start or in the ! postgresql.conf file. ! ! ! ! ! ! bgwriter_percent (integer) ! ! bgwriter_percent configuration parameter ! ! ! ! In each round, no more than this percentage of the currently ! dirty buffers will be written (rounding up any fraction to ! the next whole number of buffers). The default value is ! 1. This option can only be set at server start or in the ! postgresql.conf file. --- 1350,1367 ---- Specifies the delay between activity rounds for the background writer. In each round the writer issues writes ! for some number of dirty buffers (controllable by ! bgwriter_maxpages). The selected buffers ! will always be the least recently used ones among the ! currently dirty buffers. It then sleeps for ! bgwriter_delay milliseconds, and repeats. The ! default value is 200. Note that on many systems, the ! effective resolution of sleep delays is 10 milliseconds; ! setting bgwriter_delay to a value that is not a ! multiple of 10 may have the same results as setting it to the ! next higher multiple of 10. This option can only be set at ! server start or in the postgresql.conf ! file. *************** *** 1398,1409 **** ! Smaller values of bgwriter_percent and ! bgwriter_maxpages reduce the extra I/O load ! caused by the background writer, but leave more work to be done ! at checkpoint time. To reduce load spikes at checkpoints, ! increase the values. To disable background writing entirely, ! set bgwriter_percent and/or bgwriter_maxpages to zero. --- 1383,1396 ---- ! Decreasing bgwriter_maxpages or increasing ! bgwriter_delay will reduce the extra I/O load ! caused by the background writer, but will leave more work to be ! done at checkpoint time. To reduce load spikes at checkpoints, ! increase the number of pages written per round ! (bgwriter_maxpages) or reduce the delay ! between rounds (bgwriter_delay). To disable ! background writing entirely, set bgwriter_maxpages to zero. Index: src/backend/catalog/index.c =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/catalog/index.c,v retrieving revision 1.242 diff -c -r1.242 index.c *** src/backend/catalog/index.c 1 Dec 2004 19:00:39 -0000 1.242 --- src/backend/catalog/index.c 14 Dec 2004 04:32:39 -0000 *************** *** 1062,1068 **** /* Send out shared cache inval if necessary */ if (!IsBootstrapProcessingMode()) CacheInvalidateHeapTuple(pg_class, tuple); ! BufferSync(-1, -1); } else if (dirty) { --- 1062,1068 ---- /* Send out shared cache inval if necessary */ if (!IsBootstrapProcessingMode()) CacheInvalidateHeapTuple(pg_class, tuple); ! BufferSync(-1); } else if (dirty) { Index: src/backend/commands/dbcommands.c =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/commands/dbcommands.c,v retrieving revision 1.147 diff -c -r1.147 dbcommands.c *** src/backend/commands/dbcommands.c 18 Nov 2004 01:14:26 -0000 1.147 --- src/backend/commands/dbcommands.c 14 Dec 2004 04:40:19 -0000 *************** *** 332,338 **** * up-to-date for the copy. (We really only need to flush buffers for * the source database, but bufmgr.c provides no API for that.) */ ! BufferSync(-1, -1); /* * Close virtual file descriptors so the kernel has more available for --- 332,338 ---- * up-to-date for the copy. (We really only need to flush buffers for * the source database, but bufmgr.c provides no API for that.) */ ! BufferSync(-1); /* * Close virtual file descriptors so the kernel has more available for *************** *** 1206,1212 **** * up-to-date for the copy. (We really only need to flush buffers for * the source database, but bufmgr.c provides no API for that.) */ ! BufferSync(-1, -1); #ifndef WIN32 --- 1206,1212 ---- * up-to-date for the copy. (We really only need to flush buffers for * the source database, but bufmgr.c provides no API for that.) */ ! BufferSync(-1); #ifndef WIN32 Index: src/backend/postmaster/bgwriter.c =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/postmaster/bgwriter.c,v retrieving revision 1.11 diff -c -r1.11 bgwriter.c *** src/backend/postmaster/bgwriter.c 5 Nov 2004 17:11:28 -0000 1.11 --- src/backend/postmaster/bgwriter.c 14 Dec 2004 04:44:26 -0000 *************** *** 116,122 **** * GUC parameters */ int BgWriterDelay = 200; - int BgWriterPercent = 1; int BgWriterMaxPages = 100; int CheckPointTimeout = 300; --- 116,121 ---- *************** *** 372,378 **** n = 1; } else ! n = BufferSync(BgWriterPercent, BgWriterMaxPages); /* * Nap for the configured time or sleep for 10 seconds if there --- 371,377 ---- n = 1; } else ! n = BufferSync(BgWriterMaxPages); /* * Nap for the configured time or sleep for 10 seconds if there Index: src/backend/storage/buffer/bufmgr.c =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/storage/buffer/bufmgr.c,v retrieving revision 1.182 diff -c -r1.182 bufmgr.c *** src/backend/storage/buffer/bufmgr.c 24 Nov 2004 02:56:17 -0000 1.182 --- src/backend/storage/buffer/bufmgr.c 14 Dec 2004 04:40:18 -0000 *************** *** 671,717 **** * * This is called at checkpoint time to write out all dirty shared buffers, * and by the background writer process to write out some of the dirty blocks. ! * percent/maxpages should be -1 in the former case, and limit values (>= 0) * in the latter. * * Returns the number of buffers written. */ int ! BufferSync(int percent, int maxpages) { BufferDesc **dirty_buffers; BufferTag *buftags; int num_buffer_dirty; int i; ! /* If either limit is zero then we are disabled from doing anything... */ ! if (percent == 0 || maxpages == 0) return 0; /* * Get a list of all currently dirty buffers and how many there are. * We do not flush buffers that get dirtied after we started. They * have to wait until the next checkpoint. */ ! dirty_buffers = (BufferDesc **) palloc(NBuffers * sizeof(BufferDesc *)); ! buftags = (BufferTag *) palloc(NBuffers * sizeof(BufferTag)); LWLockAcquire(BufMgrLock, LW_EXCLUSIVE); num_buffer_dirty = StrategyDirtyBufferList(dirty_buffers, buftags, ! NBuffers); ! ! /* ! * If called by the background writer, we are usually asked to only ! * write out some portion of dirty buffers now, to prevent the IO ! * storm at checkpoint time. ! */ ! if (percent > 0) ! { ! Assert(percent <= 100); ! num_buffer_dirty = (num_buffer_dirty * percent + 99) / 100; ! } ! if (maxpages > 0 && num_buffer_dirty > maxpages) ! num_buffer_dirty = maxpages; /* Make sure we can handle the pin inside the loop */ ResourceOwnerEnlargeBuffers(CurrentResourceOwner); --- 671,710 ---- * * This is called at checkpoint time to write out all dirty shared buffers, * and by the background writer process to write out some of the dirty blocks. ! * maxpages should be -1 in the former case, and a limit value (>= 0) * in the latter. * * Returns the number of buffers written. */ int ! BufferSync(int maxpages) { BufferDesc **dirty_buffers; BufferTag *buftags; int num_buffer_dirty; int i; ! /* If maxpages is zero then we're effectively disabled */ ! if (maxpages == 0) return 0; + /* If -1, flush all dirty buffers */ + if (maxpages == -1) + maxpages = NBuffers; + /* + * Get a list of up to "maxpages" dirty buffers, starting from LRU and * Get a list of all currently dirty buffers and how many there are. * We do not flush buffers that get dirtied after we started. They * have to wait until the next checkpoint. */ ! dirty_buffers = (BufferDesc **) palloc(maxpages * sizeof(BufferDesc *)); ! buftags = (BufferTag *) palloc(maxpages * sizeof(BufferTag)); LWLockAcquire(BufMgrLock, LW_EXCLUSIVE); num_buffer_dirty = StrategyDirtyBufferList(dirty_buffers, buftags, ! maxpages); ! Assert(num_buffer_dirty <= maxpages); /* Make sure we can handle the pin inside the loop */ ResourceOwnerEnlargeBuffers(CurrentResourceOwner); *************** *** 947,953 **** void FlushBufferPool(void) { ! BufferSync(-1, -1); smgrsync(); } --- 940,946 ---- void FlushBufferPool(void) { ! BufferSync(-1); smgrsync(); } Index: src/backend/storage/buffer/freelist.c =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/storage/buffer/freelist.c,v retrieving revision 1.48 diff -c -r1.48 freelist.c *** src/backend/storage/buffer/freelist.c 16 Sep 2004 16:58:31 -0000 1.48 --- src/backend/storage/buffer/freelist.c 14 Dec 2004 04:22:02 -0000 *************** *** 753,810 **** int num_buffer_dirty = 0; int cdb_id_t1; int cdb_id_t2; - int buf_id; - BufferDesc *buf; /* ! * Traverse the T1 and T2 list LRU to MRU in "parallel" and add all ! * dirty buffers found in that order to the list. The ARC strategy ! * keeps all used buffers including pinned ones in the T1 or T2 list. ! * So we cannot miss any dirty buffers. */ cdb_id_t1 = StrategyControl->listHead[STRAT_LIST_T1]; cdb_id_t2 = StrategyControl->listHead[STRAT_LIST_T2]; while (cdb_id_t1 >= 0 || cdb_id_t2 >= 0) { if (cdb_id_t1 >= 0) { buf_id = StrategyCDB[cdb_id_t1].buf_id; - buf = &BufferDescriptors[buf_id]; - - if (buf->flags & BM_VALID) - { - if ((buf->flags & BM_DIRTY) || (buf->cntxDirty)) - { - buffers[num_buffer_dirty] = buf; - buftags[num_buffer_dirty] = buf->tag; - num_buffer_dirty++; - if (num_buffer_dirty >= max_buffers) - break; - } - } - cdb_id_t1 = StrategyCDB[cdb_id_t1].next; } ! ! if (cdb_id_t2 >= 0) { buf_id = StrategyCDB[cdb_id_t2].buf_id; ! buf = &BufferDescriptors[buf_id]; ! if (buf->flags & BM_VALID) { ! if ((buf->flags & BM_DIRTY) || (buf->cntxDirty)) ! { ! buffers[num_buffer_dirty] = buf; ! buftags[num_buffer_dirty] = buf->tag; ! num_buffer_dirty++; ! if (num_buffer_dirty >= max_buffers) ! break; ! } } - - cdb_id_t2 = StrategyCDB[cdb_id_t2].next; } } --- 753,797 ---- int num_buffer_dirty = 0; int cdb_id_t1; int cdb_id_t2; /* ! * Traverse the T1 and T2 list from LRU to MRU in "parallel" and ! * add all dirty buffers found in that order to the list. The ARC ! * strategy keeps all used buffers including pinned ones in the T1 ! * or T2 list. So we cannot miss any dirty buffers. */ cdb_id_t1 = StrategyControl->listHead[STRAT_LIST_T1]; cdb_id_t2 = StrategyControl->listHead[STRAT_LIST_T2]; while (cdb_id_t1 >= 0 || cdb_id_t2 >= 0) { + int buf_id; + BufferDesc *buf; + if (cdb_id_t1 >= 0) { buf_id = StrategyCDB[cdb_id_t1].buf_id; cdb_id_t1 = StrategyCDB[cdb_id_t1].next; } ! else { + Assert(cdb_id_t2 >= 0); buf_id = StrategyCDB[cdb_id_t2].buf_id; ! cdb_id_t2 = StrategyCDB[cdb_id_t2].next; ! } ! ! buf = &BufferDescriptors[buf_id]; ! if (buf->flags & BM_VALID) ! { ! if ((buf->flags & BM_DIRTY) || (buf->cntxDirty)) { ! buffers[num_buffer_dirty] = buf; ! buftags[num_buffer_dirty] = buf->tag; ! num_buffer_dirty++; ! if (num_buffer_dirty >= max_buffers) ! break; } } } Index: src/backend/utils/misc/guc.c =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/utils/misc/guc.c,v retrieving revision 1.250 diff -c -r1.250 guc.c *** src/backend/utils/misc/guc.c 24 Nov 2004 19:51:03 -0000 1.250 --- src/backend/utils/misc/guc.c 14 Dec 2004 04:44:40 -0000 *************** *** 1249,1263 **** }, { - {"bgwriter_percent", PGC_SIGHUP, RESOURCES, - gettext_noop("Background writer percentage of dirty buffers to flush per round"), - NULL - }, - &BgWriterPercent, - 1, 0, 100, NULL, NULL - }, - - { {"bgwriter_maxpages", PGC_SIGHUP, RESOURCES, gettext_noop("Background writer maximum number of pages to flush per round"), NULL --- 1249,1254 ---- Index: src/backend/utils/misc/postgresql.conf.sample =================================================================== RCS file: /var/lib/cvs/pgsql/src/backend/utils/misc/postgresql.conf.sample,v retrieving revision 1.134 diff -c -r1.134 postgresql.conf.sample *** src/backend/utils/misc/postgresql.conf.sample 5 Nov 2004 19:16:16 -0000 1.134 --- src/backend/utils/misc/postgresql.conf.sample 14 Dec 2004 04:54:47 -0000 *************** *** 96,106 **** #vacuum_cost_page_dirty = 20 # 0-10000 credits #vacuum_cost_limit = 200 # 0-10000 credits ! # - Background writer - #bgwriter_delay = 200 # 10-10000 milliseconds between rounds ! #bgwriter_percent = 1 # 0-100% of dirty buffers in each round ! #bgwriter_maxpages = 100 # 0-1000 buffers max per round #--------------------------------------------------------------------------- --- 96,105 ---- #vacuum_cost_page_dirty = 20 # 0-10000 credits #vacuum_cost_limit = 200 # 0-10000 credits ! # - Background Writer - #bgwriter_delay = 200 # 10-10000 milliseconds between rounds ! #bgwriter_maxpages = 100 # max buffers written per round, 0 disables #--------------------------------------------------------------------------- Index: src/include/postmaster/bgwriter.h =================================================================== RCS file: /var/lib/cvs/pgsql/src/include/postmaster/bgwriter.h,v retrieving revision 1.3 diff -c -r1.3 bgwriter.h *** src/include/postmaster/bgwriter.h 29 Aug 2004 04:13:09 -0000 1.3 --- src/include/postmaster/bgwriter.h 14 Dec 2004 04:44:44 -0000 *************** *** 18,24 **** /* GUC options */ extern int BgWriterDelay; - extern int BgWriterPercent; extern int BgWriterMaxPages; extern int CheckPointTimeout; extern int CheckPointWarning; --- 18,23 ---- Index: src/include/storage/bufmgr.h =================================================================== RCS file: /var/lib/cvs/pgsql/src/include/storage/bufmgr.h,v retrieving revision 1.88 diff -c -r1.88 bufmgr.h *** src/include/storage/bufmgr.h 16 Oct 2004 18:57:26 -0000 1.88 --- src/include/storage/bufmgr.h 14 Dec 2004 04:40:09 -0000 *************** *** 150,156 **** extern void AbortBufferIO(void); extern void BufmgrCommit(void); ! extern int BufferSync(int percent, int maxpages); extern void InitLocalBuffer(void); --- 150,156 ---- extern void AbortBufferIO(void); extern void BufmgrCommit(void); ! extern int BufferSync(int maxpages); extern void InitLocalBuffer(void);