? GNUmakefile ? config.log ? config.status ? contrib/pg_standby/pg_standby ? contrib/pgbench/pgbench ? src/Makefile.global ? src/backend/postgres ? src/backend/catalog/postgres.bki ? src/backend/catalog/postgres.description ? src/backend/catalog/postgres.shdescription ? src/backend/snowball/snowball_create.sql ? src/backend/utils/probes.h ? src/backend/utils/mb/conversion_procs/conversion_create.sql ? src/bin/initdb/initdb ? src/bin/pg_config/pg_config ? src/bin/pg_controldata/pg_controldata ? src/bin/pg_ctl/pg_ctl ? src/bin/pg_dump/pg_dump ? src/bin/pg_dump/pg_dumpall ? src/bin/pg_dump/pg_restore ? src/bin/pg_resetxlog/pg_resetxlog ? src/bin/psql/psql ? src/bin/scripts/clusterdb ? src/bin/scripts/createdb ? src/bin/scripts/createlang ? src/bin/scripts/createuser ? src/bin/scripts/dropdb ? src/bin/scripts/droplang ? src/bin/scripts/dropuser ? src/bin/scripts/reindexdb ? src/bin/scripts/vacuumdb ? src/include/pg_config.h ? src/include/stamp-h ? src/interfaces/ecpg/compatlib/exports.list ? src/interfaces/ecpg/compatlib/libecpg_compat.so.3.1 ? src/interfaces/ecpg/ecpglib/exports.list ? src/interfaces/ecpg/ecpglib/libecpg.so.6.1 ? src/interfaces/ecpg/include/ecpg_config.h ? src/interfaces/ecpg/include/stamp-h ? src/interfaces/ecpg/pgtypeslib/exports.list ? src/interfaces/ecpg/pgtypeslib/libpgtypes.so.3.1 ? src/interfaces/ecpg/preproc/ecpg ? src/interfaces/libpq/exports.list ? src/interfaces/libpq/libpq.so.5.2 ? src/port/pg_config_paths.h ? src/test/regress/pg_regress ? src/test/regress/testtablespace ? src/timezone/zic Index: contrib/pg_standby/pg_standby.c =================================================================== RCS file: /projects/cvsroot/pgsql/contrib/pg_standby/pg_standby.c,v retrieving revision 1.20 diff -c -r1.20 pg_standby.c *** contrib/pg_standby/pg_standby.c 18 Mar 2009 20:30:35 -0000 1.20 --- contrib/pg_standby/pg_standby.c 25 Mar 2009 06:26:40 -0000 *************** *** 52,65 **** int keepfiles = 0; /* number of WAL files to keep, 0 keep all */ int maxretries = 3; /* number of retries on restore command */ bool debug = false; /* are we debugging? */ ! bool triggered = false; /* have we been triggered? */ bool need_cleanup = false; /* do we need to remove files from * archive? */ static volatile sig_atomic_t signaled = false; char *archiveLocation; /* where to find the archive? */ - char *triggerPath; /* where to find the trigger file? */ char *xlogFilePath; /* where we are going to restore to */ char *nextWALFileName; /* the file we need to get from archive */ char *restartWALFileName; /* the file from which we can restart restore */ --- 52,64 ---- int keepfiles = 0; /* number of WAL files to keep, 0 keep all */ int maxretries = 3; /* number of retries on restore command */ bool debug = false; /* are we debugging? */ ! bool triggered = false; /* have we been triggered (cancel)? */ bool need_cleanup = false; /* do we need to remove files from * archive? */ static volatile sig_atomic_t signaled = false; char *archiveLocation; /* where to find the archive? */ char *xlogFilePath; /* where we are going to restore to */ char *nextWALFileName; /* the file we need to get from archive */ char *restartWALFileName; /* the file from which we can restart restore */ *************** *** 69,74 **** --- 68,92 ---- char exclusiveCleanupFileName[MAXPGPATH]; /* the file we need to * get from archive */ + /* + * Where to find the trigger file? + * + * Two types (finish and cancel) of trigger files are supported. + * + * When "finish" trigger file exists, pg_standby acts as cp or ln command itself, + * and recovery waits to finish until all the available WAL files are redone. It's + * guaranteed that no "available" commit transactions are lost. But it might take + * some times before finishing recovery. + * + * On the other hand, the existence of "cancel" trigger file causes recovery to + * end immediately even if the available WAL files remain. So, some transactions + * might be lost. + * + * When both of them exist, we prefer "cancel" trigger file to "finish" one. + */ + char *finishTriggerPath; + char *cancelTriggerPath; + #define RESTORE_COMMAND_COPY 0 #define RESTORE_COMMAND_LINK 1 int restoreCommandType; *************** *** 355,364 **** * Is there a trigger file? */ static bool ! CheckForExternalTrigger(void) { int rc; /* * Look for a trigger file, if that option has been selected * --- 373,389 ---- * Is there a trigger file? */ static bool ! CheckForExternalTrigger(char *triggerPath, bool delete_trigger) { int rc; + if (debug) + { + if (triggerPath) + fprintf(stderr, " Checking for trigger file...: %s", triggerPath); + fflush(stderr); + } + /* * Look for a trigger file, if that option has been selected * *************** *** 367,388 **** */ if (triggerPath && stat(triggerPath, &stat_buf) == 0) { ! fprintf(stderr, "trigger file found\n"); fflush(stderr); ! /* ! * If trigger file found, we *must* delete it. Here's why: When ! * recovery completes, we will be asked again for the same file from ! * the archive using pg_standby so must remove trigger file so we can ! * reload file again and come up correctly. ! */ ! rc = unlink(triggerPath); ! if (rc != 0) { ! fprintf(stderr, "\n ERROR: could not remove \"%s\": %s", triggerPath, strerror(errno)); ! fflush(stderr); ! exit(rc); } return true; } --- 392,411 ---- */ if (triggerPath && stat(triggerPath, &stat_buf) == 0) { ! fprintf(stderr, "trigger file found: %s\n", triggerPath); fflush(stderr); ! if (delete_trigger) { ! rc = unlink(triggerPath); ! if (rc != 0) ! { ! fprintf(stderr, "\n ERROR: could not remove \"%s\": %s", triggerPath, strerror(errno)); ! fflush(stderr); ! exit(rc); ! } } + return true; } *************** *** 450,456 **** " (default=3)\n"); printf(" -s SLEEPTIME seconds to wait between file checks (min=1, max=60,\n" " default=5)\n"); ! printf(" -t TRIGGERFILE defines a trigger file to initiate failover (no default)\n"); printf(" -w MAXWAITTIME max seconds to wait for a file (0=no limit) (default=0)\n"); printf(" --help show this help, then exit\n"); printf(" --version output version information, then exit\n"); --- 473,480 ---- " (default=3)\n"); printf(" -s SLEEPTIME seconds to wait between file checks (min=1, max=60,\n" " default=5)\n"); ! printf(" -t CANCELTRIGGERFILE defines a trigger file to cancel recovery (no default)\n"); ! printf(" -T FINISHTRIGGERFILE defines a trigger file to finish recovery (no default)\n"); printf(" -w MAXWAITTIME max seconds to wait for a file (0=no limit) (default=0)\n"); printf(" --help show this help, then exit\n"); printf(" --version output version information, then exit\n"); *************** *** 513,519 **** (void) signal(SIGQUIT, sigquit_handler); #endif ! while ((c = getopt(argc, argv, "cdk:lr:s:t:w:")) != -1) { switch (c) { --- 537,543 ---- (void) signal(SIGQUIT, sigquit_handler); #endif ! while ((c = getopt(argc, argv, "cdk:lr:s:t:T:w:")) != -1) { switch (c) { *************** *** 550,560 **** exit(2); } break; ! case 't': /* Trigger file */ ! triggerPath = optarg; ! if (CheckForExternalTrigger()) exit(1); /* Normal exit, with non-zero */ break; case 'w': /* Max wait time */ maxwaittime = atoi(optarg); if (maxwaittime < 0) --- 574,587 ---- exit(2); } break; ! case 't': /* Cancel trigger file */ ! cancelTriggerPath = optarg; ! if (CheckForExternalTrigger(cancelTriggerPath, true)) exit(1); /* Normal exit, with non-zero */ break; + case 'T': /* Finish trigger file */ + finishTriggerPath = optarg; + break; case 'w': /* Max wait time */ maxwaittime = atoi(optarg); if (maxwaittime < 0) *************** *** 633,639 **** if (debug) { ! fprintf(stderr, "\nTrigger file : %s", triggerPath ? triggerPath : ""); fprintf(stderr, "\nWaiting for WAL file : %s", nextWALFileName); fprintf(stderr, "\nWAL file path : %s", WALFilePath); fprintf(stderr, "\nRestoring to... : %s", xlogFilePath); --- 660,669 ---- if (debug) { ! fprintf(stderr, "\nCancel trigger file : %s", ! cancelTriggerPath ? cancelTriggerPath : ""); ! fprintf(stderr, "\nFinish trigger file : %s", ! finishTriggerPath ? finishTriggerPath : ""); fprintf(stderr, "\nWaiting for WAL file : %s", nextWALFileName); fprintf(stderr, "\nWAL file path : %s", WALFilePath); fprintf(stderr, "\nRestoring to... : %s", xlogFilePath); *************** *** 673,724 **** } } ! /* ! * Main wait loop ! */ ! while (!CustomizableNextWALFileReady() && !triggered) ! { ! if (sleeptime <= 60) ! pg_usleep(sleeptime * 1000000L); ! ! if (signaled) { ! triggered = true; ! if (debug) { ! fprintf(stderr, "\nsignaled to exit\n"); ! fflush(stderr); } ! } ! else ! { ! ! if (debug) { ! fprintf(stderr, "\nWAL file not present yet."); ! if (triggerPath) ! fprintf(stderr, " Checking for trigger file..."); ! fflush(stderr); } ! waittime += sleeptime; ! ! if (!triggered && (CheckForExternalTrigger() || (waittime >= maxwaittime && maxwaittime > 0))) ! { ! triggered = true; ! if (debug && waittime >= maxwaittime && maxwaittime > 0) ! fprintf(stderr, "\nTimed out after %d seconds\n", waittime); ! } } } /* - * Action on exit - */ - if (triggered) - exit(1); /* Normal exit, with non-zero */ - - /* * Once we have restored this file successfully we can remove some prior * WAL files. If this restore fails we musn't remove any file because some * of them will be requested again immediately after the failed restore, --- 703,771 ---- } } ! /* ! * If "finish" trigger file exists, we would skip the wait loop and try to ! * restore the log, which makes pg_standby act as cp or ln command. ! */ ! if (!CheckForExternalTrigger(finishTriggerPath, false)) ! { ! /* ! * Main wait loop ! */ ! while (!CustomizableNextWALFileReady() && !triggered) { ! if (sleeptime <= 60) ! pg_usleep(sleeptime * 1000000L); ! ! if (signaled) { ! triggered = true; ! if (debug) ! { ! fprintf(stderr, "\nsignaled to exit\n"); ! fflush(stderr); ! } } ! else { ! if (debug) ! { ! fprintf(stderr, "\nWAL file not present yet."); ! fflush(stderr); ! } ! ! waittime += sleeptime; ! ! /* ! * If "cancel" trigger file found, we *must* delete it. Here's why: When ! * recovery finishes, we will be asked again for the same file from ! * the archive using pg_standby so must remove trigger file so we can ! * reload file again and come up correctly. ! */ ! if (!triggered && (CheckForExternalTrigger(cancelTriggerPath, true) || ! (waittime >= maxwaittime && maxwaittime > 0))) ! { ! triggered = true; ! if (debug && waittime >= maxwaittime && maxwaittime > 0) ! fprintf(stderr, "\nTimed out after %d seconds\n", waittime); ! } } ! /* ! * Action on exit ! */ ! if (triggered) ! exit(1); /* Normal exit, with non-zero */ ! ! /* ! * If "finish" trigger file exists, we try to restore the log soon. ! */ ! if (CheckForExternalTrigger(finishTriggerPath, false)) ! break; } } /* * Once we have restored this file successfully we can remove some prior * WAL files. If this restore fails we musn't remove any file because some * of them will be requested again immediately after the failed restore, Index: doc/src/sgml/pgstandby.sgml =================================================================== RCS file: /projects/cvsroot/pgsql/doc/src/sgml/pgstandby.sgml,v retrieving revision 2.7 diff -c -r2.7 pgstandby.sgml *** doc/src/sgml/pgstandby.sgml 27 Feb 2009 09:30:21 -0000 2.7 --- doc/src/sgml/pgstandby.sgml 25 Mar 2009 06:26:40 -0000 *************** *** 174,180 **** ! -t triggerfile none Specify a trigger file whose presence should cause recovery to end --- 174,180 ---- ! -t canceltrigger none Specify a trigger file whose presence should cause recovery to end *************** *** 182,188 **** It is recommended that you use a structured filename to avoid confusion as to which server is being triggered when multiple servers exist on the same system; for example ! /tmp/pgsql.trigger.5432. --- 182,201 ---- It is recommended that you use a structured filename to avoid confusion as to which server is being triggered when multiple servers exist on the same system; for example ! /tmp/pgsql.cancel.5442. ! Note that the trigger file doesn't exist after recovery. ! ! ! ! -T finishtrigger ! none ! ! Specify a trigger file whose presence should cause recovery to end ! after replaying all the available WAL files. ! It is recommended that you use a structured filename like -t. ! -T is ignored if the same trigger file as that of ! -t is specified. ! Note that the trigger file remains even after recovery. *************** *** 209,215 **** archive_command = 'cp %p .../archive/%f' ! restore_command = 'pg_standby -l -d -s 2 -t /tmp/pgsql.trigger.5442 .../archive %f %p %r 2>>standby.log' where the archive directory is physically located on the standby server, --- 222,228 ---- archive_command = 'cp %p .../archive/%f' ! restore_command = 'pg_standby -l -d -s 2 -t /tmp/pgsql.cancel.5442 -T /tmp/pgsql.finish.5442 .../archive %f %p %r 2>>standby.log' where the archive directory is physically located on the standby server, *************** *** 236,242 **** stop waiting only when a trigger file called ! /tmp/pgsql.trigger.5442 appears --- 249,263 ---- stop waiting only when a trigger file called ! /tmp/pgsql.cancel.5442 appears, ! then do nothing even if there are the available WAL files ! ! ! ! ! stop waiting only when a trigger file called ! /tmp/pgsql.finish.5442 appears, ! then restore the available WAL file if it exists *************** *** 251,257 **** archive_command = 'copy %p ...\\archive\\%f' ! restore_command = 'pg_standby -d -s 5 -t C:\pgsql.trigger.5442 ...\archive %f %p %r 2>>standby.log' Note that backslashes need to be doubled in the --- 272,278 ---- archive_command = 'copy %p ...\\archive\\%f' ! restore_command = 'pg_standby -d -s 5 -t C:\pgsql.cancel.5442 -T C:\pgsql.finish.5442 ...\archive %f %p %r 2>>standby.log' Note that backslashes need to be doubled in the *************** *** 277,283 **** stop waiting only when a trigger file called ! C:\pgsql.trigger.5442 appears --- 298,312 ---- stop waiting only when a trigger file called ! C:\pgsql.cancel.5442 appears, ! then do nothing even if there are the available WAL files ! ! ! ! ! stop waiting only when a trigger file called ! C:\pgsql.trigger.5442 appears, ! then restore the available WAL file if it exists