commit a94095576809948e61b1778d4fb99010b28c51bb Author: mithun Date: Mon Mar 13 18:32:15 2017 +0530 Work :: AutoPrewarm Author :: Mithun diff --git a/contrib/pg_prewarm/Makefile b/contrib/pg_prewarm/Makefile index 7ad941e..88580d1 100644 --- a/contrib/pg_prewarm/Makefile +++ b/contrib/pg_prewarm/Makefile @@ -1,10 +1,10 @@ # contrib/pg_prewarm/Makefile MODULE_big = pg_prewarm -OBJS = pg_prewarm.o $(WIN32RES) +OBJS = pg_prewarm.o autoprewarm.o $(WIN32RES) EXTENSION = pg_prewarm -DATA = pg_prewarm--1.1.sql pg_prewarm--1.0--1.1.sql +DATA = pg_prewarm--1.1--1.2.sql pg_prewarm--1.1.sql pg_prewarm--1.0--1.1.sql PGFILEDESC = "pg_prewarm - preload relation data into system buffer cache" ifdef USE_PGXS diff --git a/contrib/pg_prewarm/autoprewarm.c b/contrib/pg_prewarm/autoprewarm.c new file mode 100644 index 0000000..f4b34ca --- /dev/null +++ b/contrib/pg_prewarm/autoprewarm.c @@ -0,0 +1,1137 @@ +/*------------------------------------------------------------------------- + * + * autoprewarm.c + * + * -- Automatically prewarm the shared buffer pool when server restarts. + * + * Copyright (c) 2013-2017, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pg_prewarm.c/autoprewarm.c + *------------------------------------------------------------------------- + */ + +#include "postgres.h" +#include + +/* These are always necessary for a bgworker. */ +#include "miscadmin.h" +#include "postmaster/bgworker.h" +#include "storage/ipc.h" +#include "storage/latch.h" +#include "storage/lwlock.h" +#include "storage/proc.h" +#include "storage/shmem.h" + +/* These are necessary for prewarm utilities. */ +#include "pgstat.h" +#include "storage/buf_internals.h" +#include "storage/smgr.h" +#include "utils/memutils.h" +#include "utils/resowner.h" +#include "utils/guc.h" +#include "catalog/pg_class.h" +#include "catalog/pg_type.h" +#include "executor/spi.h" +#include "access/xact.h" +#include "utils/rel.h" +#include "port/atomics.h" + +/* + * autoprewarm : + * + * What is it? + * =========== + * A bgworker which automatically records information about blocks which were + * present in buffer pool before server shutdown and then prewarm the buffer + * pool upon server restart with those blocks. + * + * How does it work? + * ================= + * When the shared library "pg_prewarm" is preloaded, a + * bgworker "autoprewarm" is launched immediately after the server has reached + * consistent state. The bgworker will start loading blocks recorded in the + * format BlockInfoRecord + * <> in + * $PGDATA/AUTOPREWARM_FILE, until there is a free buffer left in the buffer + * pool. This way we do not replace any new blocks which were loaded either by + * the recovery process or the querying clients. + * + * Once the "autoprewarm" bgworker has completed its prewarm task, it will + * start a new task to periodically dump the BlockInfoRecords related to blocks + * which are currently in shared buffer pool. Upon next server restart, the + * bgworker will prewarm the buffer pool by loading those blocks. The GUC + * pg_prewarm.dump_interval will control the dumping activity of the bgworker. + */ + +PG_FUNCTION_INFO_V1(launch_autoprewarm_dump); +PG_FUNCTION_INFO_V1(autoprewarm_dump_now); + +#define AT_PWARM_OFF -1 +#define AT_PWARM_DUMP_AT_SHUTDOWN_ONLY 0 +#define AT_PWARM_DEFAULT_DUMP_INTERVAL 300 + +#define AUTOPREWARM_FILE "autoprewarm.blocks" + +/* Primary functions */ +void _PG_init(void); +void autoprewarm_main(Datum main_arg); +static void dump_block_info_periodically(void); +static pid_t autoprewarm_dump_launcher(void); +static void setup_autoprewarm(BackgroundWorker *autoprewarm, + const char *worker_name, + const char *worker_function, + Datum main_arg, int restart_time, + int extra_flags); +void load_one_database(Datum main_arg); + +/* + * ============================================================================ + * =========================== SIGNAL HANDLERS =========================== + * ============================================================================ + */ + +static void sigtermHandler(SIGNAL_ARGS); +static void sighupHandler(SIGNAL_ARGS); + +/* flags set by signal handlers */ +static volatile sig_atomic_t got_sigterm = false; +static volatile sig_atomic_t got_sighup = false; + +/* + * Signal handler for SIGTERM + * Set a flag to let the main loop to terminate, and set our latch to wake it + * up. + */ +static void +sigtermHandler(SIGNAL_ARGS) +{ + int save_errno = errno; + + got_sigterm = true; + + if (MyProc) + SetLatch(&MyProc->procLatch); + + errno = save_errno; +} + +/* + * Signal handler for SIGHUP + * Set a flag to tell the process to reread the config file, and set our + * latch to wake it up. + */ +static void +sighupHandler(SIGNAL_ARGS) +{ + int save_errno = errno; + + got_sighup = true; + + if (MyProc) + SetLatch(&MyProc->procLatch); + + errno = save_errno; +} + +/* + * Signal handler for SIGUSR1. + */ +static void +sigusr1Handler(SIGNAL_ARGS) +{ + int save_errno = errno; + + if (MyProc) + SetLatch(&MyProc->procLatch); + + errno = save_errno; +} + +/* ============================================================================ + * ============== types and variables used by autoprewam ============= + * ============================================================================ + */ + +/* + * Meta-data of each persistent block which is dumped and used to load. + */ +typedef struct BlockInfoRecord +{ + Oid database; /* database */ + Oid spcNode; /* tablespace */ + Oid filenode; /* relation's filenode. */ + ForkNumber forknum; /* fork number */ + BlockNumber blocknum; /* block number */ +} BlockInfoRecord; + +/* + * Tasks performed by autoprewarm workers. + */ +typedef enum +{ + TASK_PREWARM_BUFFERPOOL, /* prewarm the buffer pool. */ + TASK_DUMP_BUFFERPOOL_INFO, /* dump the buffer pool block info. */ + TASK_DUMP_IMMEDIATE_ONCE, /* dump the buffer pool block info immediately + * once. */ + TASK_END /* no more tasks to do. */ +} AutoPrewarmTask; + +/* + * Shared state information about the running autoprewarm bgworker. + */ +typedef struct AutoPrewarmSharedState +{ + pg_atomic_uint32 current_task; /* current tasks performed by + * autoprewarm workers. */ +} AutoPrewarmSharedState; + +static AutoPrewarmSharedState *state = NULL; + +/* + * Kind of BlockInfoRecord in AUTOPREWARM_FILE file. + */ +typedef enum +{ + BLKTYPE_NEW_DATABASE, /* first BlockInfoRecord of new database. */ + BLKTYPE_NEW_RELATION, /* first BlockInfoRecord of new relation. */ + BLKTYPE_NEW_FORK, /* first BlockInfoRecord of new fork file. */ + BLKTYPE_NEW_BLOCK, /* any next BlockInfoRecord. */ + BLKTYPE_END /* No More BlockInfoRecords available in dump + * file. */ +} BlkType; + +/* GUC variable which control the dump activity of autoprewarm. */ +static int dump_interval = 0; + +/* + * GUC variable which says to which database we have to connect when + * BlockInfoRecord belongs to global objects. + */ +static char *default_database; + +/* compare member elements to check if they are not equal. */ +#define cmp_member_elem(fld) \ +do { \ + if (a->fld < b->fld) \ + return -1; \ + else if (a->fld > b->fld) \ + return 1; \ +} while(0); + +/* + * sort_cmp_func - compare function used for qsort(). + */ +static int +sort_cmp_func(const void *p, const void *q) +{ + BlockInfoRecord *a = (BlockInfoRecord *) p; + BlockInfoRecord *b = (BlockInfoRecord *) q; + + cmp_member_elem(database); + cmp_member_elem(spcNode); + cmp_member_elem(filenode); + cmp_member_elem(forknum); + cmp_member_elem(blocknum); + return 0; +} + +/* ============================================================================ + * ===================== prewarm part of autoprewarm ======================= + * ============================================================================ + */ + +/* + * set_autoprewarm_task - get next task allowed and to be performed by the + * autoprewarm worker. + * + * It works like this if we are the first to allocate shared memory we can do + * what ever task we wanted to do. If TASK_PREWARM_BUFFERPOOL is running + * nothing else can go parallel. If TASK_DUMP_BUFFERPOOL_INFO is running then + * only TASK_DUMP_IMMEDIATE_ONCE can go further ahead. + */ +static AutoPrewarmTask +get_autoprewarm_task(AutoPrewarmTask todo_task) +{ + bool found; + + state = NULL; + + LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE); + state = ShmemInitStruct("autoprewarm", + sizeof(AutoPrewarmSharedState), + &found); + if (!found) + pg_atomic_write_u32(&(state->current_task), todo_task); + + LWLockRelease(AddinShmemInitLock); + + /* If found check if we can go ahead. */ + if (found) + { + if (pg_atomic_read_u32(&(state->current_task)) == + TASK_PREWARM_BUFFERPOOL) + { + if (todo_task == TASK_PREWARM_BUFFERPOOL) + { + /* + * we were prewarming and we are back to do same, time to + * abort prewarming and move to dumping. + */ + pg_atomic_write_u32(&(state->current_task), + TASK_DUMP_BUFFERPOOL_INFO); + return TASK_DUMP_BUFFERPOOL_INFO; + } + else + return TASK_END; /* rest all cannot proceed further. */ + } + else if (pg_atomic_read_u32(&(state->current_task)) == + TASK_DUMP_BUFFERPOOL_INFO) + { + /* + * only thing that can be done now is TASK_DUMP_IMMEDIATE_ONCE. + */ + if (todo_task == TASK_DUMP_IMMEDIATE_ONCE) + return TASK_DUMP_IMMEDIATE_ONCE; + else + return TASK_END; + } + else if (pg_atomic_read_u32(&(state->current_task)) == + TASK_DUMP_IMMEDIATE_ONCE) + { + uint32 current_state = TASK_DUMP_IMMEDIATE_ONCE; + + /* We cannot do a TASK_PREWARM_BUFFERPOOL but rest can go ahead */ + if (todo_task == TASK_DUMP_IMMEDIATE_ONCE) + return TASK_DUMP_IMMEDIATE_ONCE; + + if (todo_task == TASK_PREWARM_BUFFERPOOL) + todo_task = TASK_DUMP_BUFFERPOOL_INFO; /* skip to do dump only */ + + /* + * first guy who can atomically set the current_task get the + * opportunity to proceed further + */ + if (pg_atomic_compare_exchange_u32(&(state->current_task), + ¤t_state, + TASK_DUMP_BUFFERPOOL_INFO)) + { + /* Wow! We won the race proceed with the task. */ + return TASK_DUMP_BUFFERPOOL_INFO; + } + else + return TASK_END; + } + + return TASK_END; + } + + return todo_task; /* we were first we can do what we wanted. */ +} + +/* + * getnextblockinfo -- given a BlkType get its next BlockInfoRecord from the + * dump file. + */ +static BlkType +getnextblockinfo(FILE *file, BlockInfoRecord *currblkinfo, BlkType reqblock, + BlockInfoRecord *newblkinfo) +{ + BlkType nextblk; + + while (true) + { + /* get next block. */ + if (5 != fscanf(file, "%u,%u,%u,%u,%u\n", &(newblkinfo->database), + &(newblkinfo->spcNode), &(newblkinfo->filenode), + (uint32 *) &(newblkinfo->forknum), + &(newblkinfo->blocknum))) + return BLKTYPE_END; /* No more valid entry hence stop processing. */ + + if (!currblkinfo || newblkinfo->database != currblkinfo->database) + nextblk = BLKTYPE_NEW_DATABASE; + else if (newblkinfo->filenode != currblkinfo->filenode) + nextblk = BLKTYPE_NEW_RELATION; + else if (newblkinfo->forknum != currblkinfo->forknum) + nextblk = BLKTYPE_NEW_FORK; + else + nextblk = BLKTYPE_NEW_BLOCK; + + if (nextblk <= reqblock) + return nextblk; + } +} + +/* + * GetRelOid -- given a filenode get its relation oid. + */ +static Oid +get_reloid(Oid filenode) +{ + int ret; + Oid relationid; + bool isnull; + Datum value[1] = {ObjectIdGetDatum(filenode)}; + StringInfoData buf; + Oid ptype[1] = {OIDOID}; + + initStringInfo(&buf); + appendStringInfo(&buf, + "select oid from pg_class where pg_relation_filenode(oid) = $1"); + + ret = SPI_execute_with_args(buf.data, 1, (Oid *) &ptype, (Datum *) &value, + NULL, true, 1); + + if (ret != SPI_OK_SELECT) + ereport(FATAL, (errmsg("SPI_execute failed: error code %d", ret))); + + if (SPI_processed < 1) + return InvalidOid; + + relationid = DatumGetObjectId(SPI_getbinval(SPI_tuptable->vals[0], + SPI_tuptable->tupdesc, + 1, &isnull)); + if (isnull) + return InvalidOid; + + return relationid; +} + +/* + * connect_to_db -- connect to the given dbid. + * + * For global objects the dbid will be InvalidOid, connect to user given + * default_database and try to load those blocks. + */ +static void +connect_to_db(Oid dbid) +{ + if (!OidIsValid(dbid)) + BackgroundWorkerInitializeConnection(default_database, NULL); + else + BackgroundWorkerInitializeConnectionByOid(dbid, InvalidOid); + SetCurrentStatementStartTimestamp(); + StartTransactionCommand(); + SPI_connect(); + PushActiveSnapshot(GetTransactionSnapshot()); +} + +/* + * load_one_database -- start of prewarm sub-worker, this will try to load + * blocks of one database starting from block info position passed by main + * prewarm worker. + */ +void +load_one_database(Datum main_arg) +{ + off_t blockinfo_pos; + char dump_file_path[MAXPGPATH]; + FILE *file = NULL; + BlockInfoRecord prevblock, + toload_block; + Relation rel = NULL; + bool have_dbconnection = false; + BlkType loadblocktype; + BlockNumber nblocks = 0; + + /* Establish signal handlers before unblocking signals. */ + pqsignal(SIGTERM, sigtermHandler); + pqsignal(SIGHUP, sighupHandler); + pqsignal(SIGUSR1, sigusr1Handler); + + /* + * We're now ready to receive signals + */ + BackgroundWorkerUnblockSignals(); + + blockinfo_pos = DatumGetInt64(main_arg); + + /* + * Seek to the blockinfo_pos and get the database ID to which following + * block info's belong to. Connect to the that database and start loading + * the blocks which follows until we reach end of block infos that belongs + * to connected database. + */ + + /* check if file exists and open file in read mode. */ + snprintf(dump_file_path, sizeof(dump_file_path), "%s", AUTOPREWARM_FILE); + file = fopen(dump_file_path, PG_BINARY_R); + if (!file) + return; /* No file to load. */ + + if (fseeko(file, blockinfo_pos, SEEK_SET)) + { + fclose(file); + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: error reading from \"%s\" : %m", + dump_file_path))); + } + + loadblocktype = BLKTYPE_NEW_BLOCK; + loadblocktype = getnextblockinfo(file, NULL, loadblocktype, &toload_block); + + /* + * It should be a block info belonging to a new database. Or else dump + * file is corrupted better to end the loading of bocks now. + */ + if (loadblocktype != BLKTYPE_NEW_DATABASE) + goto end_load; /* should we raise a voice here? */ + + while (loadblocktype != BLKTYPE_END) + { + Buffer buf; + Oid reloid; + + /* + * Load the block only if there exist a free buffer. We do not want to + * replace a block already in buffer pool. + */ + if (!have_free_buffer()) + goto end_load; + + if (got_sigterm) + goto end_load; + + switch (loadblocktype) + { + case BLKTYPE_NEW_DATABASE: + + if (have_dbconnection) + goto end_load; /* blocks belong to a new database, + * lets end the loading process. */ + loadblocktype = BLKTYPE_NEW_DATABASE; + + /* + * connect to the database. + */ + connect_to_db(toload_block.database); + have_dbconnection = true; + + case BLKTYPE_NEW_RELATION: + + /* + * release lock on previous relation. + */ + if (rel) + { + relation_close(rel, AccessShareLock); + rel = NULL; + } + + loadblocktype = BLKTYPE_NEW_RELATION; + + /* + * lock new relation. + */ + reloid = get_reloid(toload_block.filenode); + + if (!OidIsValid(reloid)) + break; + + rel = try_relation_open(reloid, AccessShareLock); + if (!rel) + break; + RelationOpenSmgr(rel); + + case BLKTYPE_NEW_FORK: + + /* + * check if fork exists and if block is within the range + */ + loadblocktype = BLKTYPE_NEW_FORK; + if ( /* toload_block.forknum > InvalidForkNumber && + * toload_block.forknum <= MAX_FORKNUM && */ + !smgrexists(rel->rd_smgr, toload_block.forknum)) + break; + nblocks = RelationGetNumberOfBlocksInFork(rel, + toload_block.forknum); + case BLKTYPE_NEW_BLOCK: + + /* check if blocknum is valid and with in fork file size. */ + if (toload_block.blocknum >= nblocks) + { + /* move to next forknum. */ + loadblocktype = BLKTYPE_NEW_FORK; + break; + } + + buf = ReadBufferExtended(rel, toload_block.forknum, + toload_block.blocknum, RBM_NORMAL, + NULL); + if (BufferIsValid(buf)) + { + ReleaseBuffer(buf); + } + + loadblocktype = BLKTYPE_NEW_BLOCK; + break; + + case BLKTYPE_END: + Assert(0); /* Should not be here! */ + } + + memcpy(&prevblock, &toload_block, sizeof(BlockInfoRecord)); + memset(&toload_block, 0, sizeof(BlockInfoRecord)); + loadblocktype = getnextblockinfo(file, &prevblock, loadblocktype, + &toload_block); + } + +end_load: + + fclose(file); + /* release lock on previous relation. */ + if (rel) + { + relation_close(rel, AccessShareLock); + rel = NULL; + } + + if (have_dbconnection) + { + SPI_finish(); + PopActiveSnapshot(); + CommitTransactionCommand(); + } + return; +} + +/* + * launch_prewarm_subworker -- register a dynamic worker to load the blocks + * starting from next_db_pos. We wait until the worker has stopped. + */ +static void +launch_prewarm_subworker(off_t next_db_pos) +{ + BackgroundWorker worker; + BackgroundWorkerHandle *handle = NULL; + BgwHandleStatus status; + + setup_autoprewarm(&worker, "autoprewarm", "load_one_database", + Int64GetDatum(next_db_pos), BGW_NEVER_RESTART, + BGWORKER_BACKEND_DATABASE_CONNECTION); + /* set bgw_notify_pid so that we can use WaitForBackgroundWorkerShutdown */ + worker.bgw_notify_pid = MyProcPid; + + if (!RegisterDynamicBackgroundWorker(&worker, &handle)) + { + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_RESOURCES), + errmsg("registering dynamic bgworker autoprewarm failed"), + errhint("Consider increasing configuration parameter " + "\"max_worker_processes\"."))); + } + + status = WaitForBackgroundWorkerShutdown(handle); + if (status == BGWH_STOPPED) + return; + + if (status == BGWH_POSTMASTER_DIED) + { + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_RESOURCES), + errmsg("cannot start bgworker autoprewarm without postmaster"), + errhint("Kill all remaining database processes and restart" + " the database."))); + } + + Assert(0); +} + +/* + * prewarm_buffer_pool - the main routine which prewarm the buffer pool. + * + * The prewarm bgworker will first seek to database map table in + * $PGDATA/AUTOPREWARM_FILE. For each offset in the map table it launches a + * sub-worker to load the block info from that offset position until the end + * of that database's block info. All sub-workers will be launched in + * sequential order only after the previous sub-worker has finished its job. + * We try to load each blocknum read from $PGDATA/AUTOPREWARM_FILE until we + * have any free buffer left or SIGTERM is received. + */ +static void +prewarm_buffer_pool(void) +{ + char dump_file_path[MAXPGPATH]; + FILE *file = NULL; + off_t database_map_table, + next_db_pos; + + snprintf(dump_file_path, sizeof(dump_file_path), "%s", + AUTOPREWARM_FILE); + + file = fopen(dump_file_path, PG_BINARY_R); + if (!file) + return; /* No file to load. */ + + /* seek to start of database_map_table. */ + if (1 != fscanf(file, "%020jd\n", (intmax_t *) & database_map_table)) + return; + if (fseeko(file, database_map_table, SEEK_SET)) + { + fclose(file); + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm : error writing to \"%s\" : %m", + dump_file_path))); + } + + /* get next database's first block info's position. */ + while (!got_sigterm && + 1 == fscanf(file, "|%jd", (intmax_t *) & next_db_pos)) + { + /* + * Register a sub-worker to load new database's block. Wait until the + * sub-worker finish its job before launching next subworker. + */ + launch_prewarm_subworker(next_db_pos); + } + + ereport(LOG, (errmsg("autoprewarm load task ended"))); + + fclose(file); + + return; +} + +/* ============================================================================ + * ============= buffer pool info dump part of autoprewarm =============== + * ============================================================================ + */ + +/* This sub-module is for periodically dumping buffer pool's block info into + * a dump file AUTOPREWARM_FILE. + * Each entry of block info looks like this: + * and we shall call it + * as BlockInfoRecord. + * + * Contents of AUTOPREWARM_FILE has been formated such a way that + * blockInfoRecord of each database can be given to different prewarm workers. + * + * format of AUTOPREWAM_FILE + * ======================================= + * [offset position of database map table] + * [sorted BlockInfoRecords..............] + * [database map table] + * ======================================= + * + * The [database map table] is sequence of offset in file which will point to + * first BlockInfoRecords of each database in the dump. The prewarm worker + * will read this offset one by one in sequence and ask its subworker to seek + * to this position and then start loading the BlockInfoRecords one by one + * until it see a BlockInfoRecords of a different database than it is actually + * connected to. + * NOTE : We store off_t inside file so the dump file will not be portable to + * be used across systems where sizeof off_t is different from each other. + */ + +/* + * dump_now - the main routine which goes through each buffer header of buffer + * pool and dumps their meta data. We Sort these data and then dump them. + * Sorting is necessary as it facilitates sequential read during load. + */ +static uint32 +dump_now(void) +{ + static char dump_file_path[MAXPGPATH], + transient_dump_file_path[MAXPGPATH]; + uint32 i; + int ret; + uint32 num_blocks; + BlockInfoRecord *block_info_array; + BufferDesc *bufHdr; + FILE *file = NULL; + off_t *database_map_table, + database_map_table_pos; + size_t database_map_table_size; + uint32 num_db = 0; + Oid prev_database; + + block_info_array = + (BlockInfoRecord *) palloc(sizeof(BlockInfoRecord) * NBuffers); + database_map_table_size = 64; + database_map_table = + (off_t *) palloc(sizeof(off_t) * database_map_table_size); + + for (num_blocks = 0, i = 0; i < NBuffers; i++) + { + uint32 buf_state; + + bufHdr = GetBufferDescriptor(i); + + /* lock each buffer header before inspecting. */ + buf_state = LockBufHdr(bufHdr); + + if (buf_state & BM_TAG_VALID) + { + block_info_array[num_blocks].database = bufHdr->tag.rnode.dbNode; + block_info_array[num_blocks].spcNode = bufHdr->tag.rnode.spcNode; + block_info_array[num_blocks].filenode = bufHdr->tag.rnode.relNode; + block_info_array[num_blocks].forknum = bufHdr->tag.forkNum; + block_info_array[num_blocks].blocknum = bufHdr->tag.blockNum; + ++num_blocks; + } + + UnlockBufHdr(bufHdr, buf_state); + } + + /* sorting now only to avoid sorting while loading. */ + pg_qsort(block_info_array, num_blocks, sizeof(BlockInfoRecord), + sort_cmp_func); + + snprintf(transient_dump_file_path, sizeof(dump_file_path), + "%s.%d", AUTOPREWARM_FILE, MyProcPid); + file = fopen(transient_dump_file_path, "w"); + if (file == NULL) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: could not open \"%s\": %m", + dump_file_path))); + + snprintf(dump_file_path, sizeof(dump_file_path), + "%s", AUTOPREWARM_FILE); + ret = fprintf(file, "%020jd\n", (intmax_t) 0); + if (ret < 0) + { + fclose(file); + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: error writing to \"%s\" : %m", + dump_file_path))); + } + + database_map_table[num_db++] = ftello(file); + + for (i = 0; i < num_blocks; i++) + { + if (i > 0 && block_info_array[i].database != prev_database) + { + if (num_db == database_map_table_size) + { + database_map_table_size *= 2; /* double and repalloc. */ + database_map_table = + (off_t *) repalloc(database_map_table, + sizeof(off_t) * database_map_table_size); + } + fflush(file); + database_map_table[num_db++] = ftello(file); + } + + ret = fprintf(file, "%u,%u,%u,%u,%u\n", + block_info_array[i].database, + block_info_array[i].spcNode, + block_info_array[i].filenode, + (uint32) block_info_array[i].forknum, + block_info_array[i].blocknum); + if (ret < 0) + { + fclose(file); + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: error writing to \"%s\" : %m", + dump_file_path))); + } + + prev_database = block_info_array[i].database; + } + + pfree(block_info_array); + database_map_table_pos = ftello(file); + + for (i = 0; i < num_db; i++) + { + ret = fprintf(file, "|%jd", (intmax_t) database_map_table[i]); + if (ret < 0) + { + fclose(file); + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: error writing to \"%s\" : %m", + dump_file_path))); + } + } + + rewind(file); + ret = fprintf(file, "%020jd\n", (intmax_t) database_map_table_pos); + if (ret < 0) + { + fclose(file); + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: error writing to \"%s\" : %m", + dump_file_path))); + } + + /* + * rename transient_dump_file_path to dump_file_path to make things + * permanent. + */ + ret = fclose(file); + if (ret != 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("autoprewarm: error closing \"%s\" : %m", + transient_dump_file_path))); + (void) durable_rename(transient_dump_file_path, dump_file_path, LOG); + + ereport(LOG, (errmsg("autoprewarm: saved metadata info of %d blocks", + num_blocks))); + return num_blocks; +} + +/* + * dump_block_info_periodically - at regular intervals, which is defined by GUC + * dump_interval, dump the info of blocks which are present in buffer pool. + */ +void +dump_block_info_periodically() +{ + pg_time_t last_dump_time = (pg_time_t) time(NULL); + + while (!got_sigterm) + { + int rc; + pg_time_t now; + int elapsed_secs = 0, + timeout = AT_PWARM_DEFAULT_DUMP_INTERVAL; + + if (dump_interval > AT_PWARM_DUMP_AT_SHUTDOWN_ONLY) + { + now = (pg_time_t) time(NULL); + elapsed_secs = now - last_dump_time; + + if (elapsed_secs > dump_interval) + { + dump_now(); + if (got_sigterm) + return; /* got shutdown signal just after a dump. And, + * I think better to return now. */ + last_dump_time = (pg_time_t) time(NULL); + elapsed_secs = 0; + } + + timeout = dump_interval - elapsed_secs; + } + + /* Has been set not to dump. Nothing more to do. */ + if (dump_interval == AT_PWARM_OFF) + return; + + ResetLatch(&MyProc->procLatch); + rc = WaitLatch(&MyProc->procLatch, + WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, + timeout * 1000, PG_WAIT_EXTENSION); + + if (rc & WL_POSTMASTER_DEATH) + proc_exit(1); + + /* + * In case of a SIGHUP, just reload the configuration. + */ + if (got_sighup) + { + got_sighup = false; + ProcessConfigFile(PGC_SIGHUP); + } + } + + /* One last block meta info dump while postmaster shutdown. */ + if (dump_interval != AT_PWARM_OFF) + dump_now(); +} + +/* + * autoprewarm_main -- the main entry point of autoprewarm bgworker process. + */ +void +autoprewarm_main(Datum main_arg) +{ + AutoPrewarmTask next_task; + + /* Establish signal handlers before unblocking signals. */ + pqsignal(SIGTERM, sigtermHandler); + pqsignal(SIGHUP, sighupHandler); + pqsignal(SIGUSR1, sigusr1Handler); + + /* We're now ready to receive signals */ + BackgroundWorkerUnblockSignals(); + + next_task = get_autoprewarm_task(DatumGetInt32(main_arg)); + + ereport(LOG, (errmsg("autoprewarm has started"))); + + /* + * **** perform autoprewarm's next task **** + */ + if (next_task == TASK_PREWARM_BUFFERPOOL) + { + prewarm_buffer_pool(); + /* prewarm is done lets move to TASK_DUMP_BUFFERPOOL_INFO. */ + pg_atomic_write_u32(&(state->current_task), + TASK_DUMP_BUFFERPOOL_INFO); + next_task = TASK_DUMP_BUFFERPOOL_INFO; + } + + if (next_task == TASK_DUMP_BUFFERPOOL_INFO) + { + dump_block_info_periodically(); + + /* + * down grade to TASK_DUMP_IMMEDIATE_ONCE so others can start + * TASK_DUMP_BUFFERPOOL_INFO + */ + pg_atomic_write_u32(&(state->current_task), TASK_DUMP_IMMEDIATE_ONCE); + } + + ereport(LOG, (errmsg("autoprewarm shutting down"))); +} + +/* ============================================================================ + * ============= extension's entry functions/utilities =================== + * ============================================================================ + */ + +/* Register autoprewarm load bgworker. */ +static void +setup_autoprewarm(BackgroundWorker *autoprewarm, const char *worker_name, + const char *worker_function, Datum main_arg, int restart_time, + int extra_flags) +{ + MemSet(autoprewarm, 0, sizeof(BackgroundWorker)); + autoprewarm->bgw_flags = BGWORKER_SHMEM_ACCESS | extra_flags; + + /* Register the autoprewarm background worker */ + autoprewarm->bgw_start_time = BgWorkerStart_ConsistentState; + autoprewarm->bgw_restart_time = restart_time; + autoprewarm->bgw_main = NULL; + strcpy(autoprewarm->bgw_library_name, "pg_prewarm"); + strcpy(autoprewarm->bgw_function_name, worker_function); + strncpy(autoprewarm->bgw_name, worker_name, BGW_MAXLEN); + autoprewarm->bgw_main_arg = main_arg; +} + +/* Extension's entry point. */ +void +_PG_init(void) +{ + BackgroundWorker autoprewarm; + + /* Define custom GUC variables. */ + DefineCustomIntVariable("pg_prewarm.dump_interval", + "Sets the maximum time between two buffer pool dumps", + "If set to Zero, timer based dumping is disabled." + " If set to -1, stops the running autoprewarm.", + &dump_interval, + AT_PWARM_DEFAULT_DUMP_INTERVAL, + AT_PWARM_OFF, INT_MAX / 1000, + PGC_SIGHUP, + GUC_UNIT_S, + NULL, + NULL, + NULL); + + /* if not run as a preloaded library, nothing more to do here! */ + if (!process_shared_preload_libraries_in_progress) + return; + + DefineCustomStringVariable("pg_prewarm.default_database", + "default database to connect if dump has not recorded same.", + NULL, + &default_database, + "postgres", + PGC_POSTMASTER, + 0, + NULL, + NULL, + NULL); + /* Request additional shared resources */ + RequestAddinShmemSpace(MAXALIGN(sizeof(AutoPrewarmSharedState))); + + /* Has been set not to prewarm/dump. Nothing more to do. */ + if (dump_interval == AT_PWARM_OFF) + return; + + /* Register autoprewarm load. */ + setup_autoprewarm(&autoprewarm, "autoprewarm", "autoprewarm_main", + Int32GetDatum(TASK_PREWARM_BUFFERPOOL), 0, 0); + RegisterBackgroundWorker(&autoprewarm); +} + +/* + * Dynamically launch an autoprewarm dump worker. + */ +static pid_t +autoprewarm_dump_launcher(void) +{ + BackgroundWorker worker; + BackgroundWorkerHandle *handle; + BgwHandleStatus status; + pid_t pid; + + setup_autoprewarm(&worker, "autoprewarm", "autoprewarm_main", + Int32GetDatum(TASK_DUMP_BUFFERPOOL_INFO), 0, 0); + + /* set bgw_notify_pid so that we can use WaitForBackgroundWorkerStartup */ + worker.bgw_notify_pid = MyProcPid; + + if (!RegisterDynamicBackgroundWorker(&worker, &handle)) + { + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_RESOURCES), + errmsg("registering dynamic bgworker \"autoprewarm\" failed"), + errhint("Consider increasing configuration parameter " + "\"max_worker_processes\"."))); + } + + status = WaitForBackgroundWorkerStartup(handle, &pid); + if (status == BGWH_STOPPED) + { + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_RESOURCES), + errmsg("could not start autoprewarm dump bgworker"), + errhint("More details may be available in the server log."))); + } + + if (status == BGWH_POSTMASTER_DIED) + { + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_RESOURCES), + errmsg("cannot start bgworker autoprewarm without postmaster"), + errhint("Kill all remaining database processes and restart" + " the database."))); + } + + Assert(status == BGWH_STARTED); + return pid; +} + +/* + * The C-Language entry function to launch autoprewarm dump bgworker. + */ +Datum +launch_autoprewarm_dump(PG_FUNCTION_ARGS) +{ + pid_t pid; + + /* Has been set not to prewarm/dump. Nothing more to do. */ + if (dump_interval == AT_PWARM_OFF) + PG_RETURN_NULL(); + + pid = autoprewarm_dump_launcher(); + PG_RETURN_INT32(pid); +} + +/* + * The C-Language entry function to dump immediately. + */ +Datum +autoprewarm_dump_now(PG_FUNCTION_ARGS) +{ + AutoPrewarmTask next_task; + + /* dump only if prewarm is not in progress. */ + next_task = get_autoprewarm_task(TASK_DUMP_IMMEDIATE_ONCE); + if (next_task == TASK_DUMP_IMMEDIATE_ONCE) + PG_RETURN_INT64(dump_now()); + PG_RETURN_NULL(); +} diff --git a/contrib/pg_prewarm/pg_prewarm--1.1--1.2.sql b/contrib/pg_prewarm/pg_prewarm--1.1--1.2.sql new file mode 100644 index 0000000..6c35fb7 --- /dev/null +++ b/contrib/pg_prewarm/pg_prewarm--1.1--1.2.sql @@ -0,0 +1,14 @@ +/* contrib/pg_prewarm/pg_prewarm--1.0--1.1.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pg_prewarm UPDATE TO '1.2'" to load this file. \quit + +CREATE FUNCTION launch_autoprewarm_dump() +RETURNS pg_catalog.int4 STRICT +AS 'MODULE_PATHNAME', 'launch_autoprewarm_dump' +LANGUAGE C; + +CREATE FUNCTION autoprewarm_dump_now() +RETURNS pg_catalog.int8 STRICT +AS 'MODULE_PATHNAME', 'autoprewarm_dump_now' +LANGUAGE C; diff --git a/contrib/pg_prewarm/pg_prewarm.control b/contrib/pg_prewarm/pg_prewarm.control index cf2fb92..40e3add 100644 --- a/contrib/pg_prewarm/pg_prewarm.control +++ b/contrib/pg_prewarm/pg_prewarm.control @@ -1,5 +1,5 @@ # pg_prewarm extension comment = 'prewarm relation data' -default_version = '1.1' +default_version = '1.2' module_pathname = '$libdir/pg_prewarm' relocatable = true diff --git a/doc/src/sgml/pgprewarm.sgml b/doc/src/sgml/pgprewarm.sgml index c090401..1538446 100644 --- a/doc/src/sgml/pgprewarm.sgml +++ b/doc/src/sgml/pgprewarm.sgml @@ -10,7 +10,9 @@ The pg_prewarm module provides a convenient way to load relation data into either the operating system buffer cache - or the PostgreSQL buffer cache. + or the PostgreSQL buffer cache. Additionally, an + automatic prewarming of the server buffers is supported whenever the server + restarts. @@ -55,6 +57,102 @@ pg_prewarm(regclass, mode text default 'buffer', fork text default 'main', cache. For these reasons, prewarming is typically most useful at startup, when caches are largely empty. + + +launch_autoprewarm_dump() RETURNS int4 + + + + This is a SQL callable function to launch the autoprewarm + worker to dump the buffer pool information at regular interval. In a server, + we can only run one autoprewarm worker so if worker sees + another existing worker it will exit immediately. The return value is pid of + the worker which has been launched. + + + +autoprewarm_dump_now() RETURNS int8 + + + + This is a SQL callable function to dump buffer pool information immediately + once by a backend. This can work in parallel + with the autoprewarm worker while it is dumping. + The return value is the number of blocks info dumped. + + + + + autoprewarm + + + A bgworker which automatically records information about blocks which were + present in buffer pool before server shutdown and then prewarm the buffer + pool upon server restart with those blocks. + + + + When the shared library pg_prewarm is preloaded via + in postgresql.conf, + a bgworker autoprewarm is launched immediately after the + server has reached a consistent state. The bgworker will start loading blocks + recorded in $PGDATA/autoprewarm.blocks until there is a + free buffer left in the buffer pool. This way we do not replace any new + blocks which were loaded either by the recovery process or the querying + clients. + + + + Once the autoprewarm bgworker has completed its prewarm + task, it will start a new task to periodically dump the information about + blocks which are currently in shared buffer pool. Upon next server restart, + the bgworker will prewarm the buffer pool by loading those blocks. The GUC + pg_prewarm.dump_interval will control the dumping activity + of the bgworker. + + + + + Configuration Parameters + + + + + pg_prewarm.dump_interval (int) + + pg_prewarm.dump_interval configuration parameter + + + + + This is valid only for autoprewarm. The minimum number + of seconds between two buffer pool's block information dump. The default + is 300 seconds. It also takes special values. If set to 0 then timer + based dump is disabled, it dumps only while the server is shutting down. + If set to -1, the running autoprewarm will be stopped. + + + + + + + + + pg_prewarm.default_database (string) + + pg_prewarm.default_database configuration parameter + + + + + This is valid only for autoprewarm. The blocks of + global objects will not have a database associated with them. The + default_database will be used to connect and preload + such blocks. + + + + diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c index 5d0a636..06a34a7 100644 --- a/src/backend/storage/buffer/freelist.c +++ b/src/backend/storage/buffer/freelist.c @@ -169,6 +169,23 @@ ClockSweepTick(void) } /* + * have_free_buffer -- a lockless check to see if there is a free buffer in + * buffer pool. + * + * If the result is true that will become stale once free buffers are moved out + * by other operations, so the caller who strictly want to use a free buffer + * should not call this. + */ +bool +have_free_buffer() +{ + if (StrategyControl->firstFreeBuffer >= 0) + return true; + else + return false; +} + +/* * StrategyGetBuffer * * Called by the bufmgr to get the next candidate buffer to use in diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index d117b66..58d4871 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -317,6 +317,7 @@ extern void StrategyNotifyBgWriter(int bgwprocno); extern Size StrategyShmemSize(void); extern void StrategyInitialize(bool init); +extern bool have_free_buffer(void); /* buf_table.c */ extern Size BufTableShmemSize(int size); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 9f876ae..4e7ea86 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -133,6 +133,8 @@ AttrDefault AttrNumber AttributeOpts AuthRequest +AutoPrewarmSharedState +AutoPrewarmTask AutoVacOpts AutoVacuumShmemStruct AuxProcType @@ -206,10 +208,12 @@ BitmapOr BitmapOrPath BitmapOrState Bitmapset +BlkType BlobInfo Block BlockId BlockIdData +BlockInfoRecord BlockNumber BlockSampler BlockSamplerData