diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index 0b31f55..e4b411f 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -9117,7 +9117,7 @@ copy_relation_data(SMgrRelation src, SMgrRelation dst, /* If we got a cancel signal during the copy of the data, quit */ CHECK_FOR_INTERRUPTS(); - smgrread(src, forkNum, blkno, buf); + smgrread(src, forkNum, blkno, buf, BAS_BULKREAD); if (!PageIsVerified(page, blkno)) ereport(ERROR, diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c index f848391..488cdf1 100644 --- a/src/backend/storage/buffer/bufmgr.c +++ b/src/backend/storage/buffer/bufmgr.c @@ -41,6 +41,7 @@ #include "pg_trace.h" #include "pgstat.h" #include "postmaster/bgwriter.h" +#include "storage/buf.h" #include "storage/buf_internals.h" #include "storage/bufmgr.h" #include "storage/ipc.h" @@ -451,7 +452,7 @@ ReadBuffer_common(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, if (track_io_timing) INSTR_TIME_SET_CURRENT(io_start); - smgrread(smgr, forkNum, blockNum, (char *) bufBlock); + smgrread(smgr, forkNum, blockNum, (char *) bufBlock, strategy); if (track_io_timing) { diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index de4d902..8cda2f9 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -73,8 +73,10 @@ #include "catalog/pg_tablespace.h" #include "common/relpath.h" #include "pgstat.h" +#include "storage/buf.h" #include "storage/fd.h" #include "storage/ipc.h" +#include "storage/bufmgr.h" #include "utils/guc.h" #include "utils/resowner_private.h" @@ -383,6 +385,21 @@ pg_flush_data(int fd, off_t offset, off_t amount) return 0; } +/* + * pg_fadvise --- advise OS that the cache will need or not + * + * Not all platforms have posix_fadvise. If it does not support posix_fadvise, + * we do nothing about here. + */ +int +pg_fadvise(int fd, off_t offset, off_t amount, int advise) +{ +#if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED) && defined(POSIX_FADV_RANDOM) && defined(POSIX_FADV_SEQUENTIAL) + return posix_fadvise(fd, offset, amount, advise); +#else + return 0; +#endif +} /* * fsync_fname -- fsync a file or directory, handling errors properly @@ -1142,6 +1159,33 @@ OpenTemporaryFileInTablespace(Oid tblspcOid, bool rejectError) } /* + * Controling OS file cache using posix_fadvise() + */ +int +FileCacheAdvise(File file, off_t offset, off_t amount, int advise) +{ + return pg_fadvise(VfdCache[file].fd, offset, amount, advise); +} + +/* + * Select OS readahead strategy using buffer hint. If we select POSIX_FADV_SEQUENTIAL, + * readahead parameter becomes the maximum and can read more faster. On the other hand, + * if we select POSIX_FADV_RANDOM, readahead wasn't executed at all and file cache + * replace algorithm will be more smart. Because it can calculate correct number of accesses + * which are hot data. + */ +int +BufferHintIOAdvise(File file, off_t offset, off_t amount, char *strategy) +{ + if(strategy != NULL) + /* use maximum readahead setting in kernel, we can read more faster */ + return FileCacheAdvise(file, offset, amount, POSIX_FADV_SEQUENTIAL); + else + /* don't use readahead in kernel, so we can more effectively use OS file cache */ + return FileCacheAdvise(file, offset, amount, POSIX_FADV_RANDOM); +} + +/* * close a file when done with it */ void diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c index e629181..e8ff0b0 100644 --- a/src/backend/storage/smgr/md.c +++ b/src/backend/storage/smgr/md.c @@ -653,7 +653,7 @@ mdprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum) */ void mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, - char *buffer) + char *buffer, char *strategy) { off_t seekpos; int nbytes; @@ -677,6 +677,7 @@ mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, errmsg("could not seek to block %u in file \"%s\": %m", blocknum, FilePathName(v->mdfd_vfd)))); + BufferHintIOAdvise(v->mdfd_vfd, buffer, BLCKSZ, strategy); nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ); TRACE_POSTGRESQL_SMGR_MD_READ_DONE(forknum, blocknum, diff --git a/src/backend/storage/smgr/smgr.c b/src/backend/storage/smgr/smgr.c index f7f1437..7a38aec 100644 --- a/src/backend/storage/smgr/smgr.c +++ b/src/backend/storage/smgr/smgr.c @@ -50,7 +50,7 @@ typedef struct f_smgr void (*smgr_prefetch) (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum); void (*smgr_read) (SMgrRelation reln, ForkNumber forknum, - BlockNumber blocknum, char *buffer); + BlockNumber blocknum, char *buffer, char *strategy); void (*smgr_write) (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync); BlockNumber (*smgr_nblocks) (SMgrRelation reln, ForkNumber forknum); @@ -588,9 +588,9 @@ smgrprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum) */ void smgrread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, - char *buffer) + char *buffer, char *strategy) { - (*(smgrsw[reln->smgr_which].smgr_read)) (reln, forknum, blocknum, buffer); + (*(smgrsw[reln->smgr_which].smgr_read)) (reln, forknum, blocknum, buffer, strategy); } /* diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h index 6dc031e..ca9a16a 100644 --- a/src/include/storage/bufmgr.h +++ b/src/include/storage/bufmgr.h @@ -44,6 +44,8 @@ typedef enum /* in globals.c ... this duplicates miscadmin.h */ extern PGDLLIMPORT int NBuffers; + + /* in bufmgr.c */ extern bool zero_damaged_pages; extern int bgwriter_lru_maxpages; diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h index 2a60229..3922c0a 100644 --- a/src/include/storage/fd.h +++ b/src/include/storage/fd.h @@ -68,6 +68,7 @@ extern int max_safe_fds; extern File PathNameOpenFile(FileName fileName, int fileFlags, int fileMode); extern File OpenTemporaryFile(bool interXact); extern void FileClose(File file); +extern int FileCacheAdvise(File file, off_t offset, off_t amount, int advise); extern int FilePrefetch(File file, off_t offset, int amount); extern int FileRead(File file, char *buffer, int amount); extern int FileWrite(File file, char *buffer, int amount); @@ -75,6 +76,7 @@ extern int FileSync(File file); extern off_t FileSeek(File file, off_t offset, int whence); extern int FileTruncate(File file, off_t offset); extern char *FilePathName(File file); +extern int BufferHintIOAdvise(File file, off_t offset, off_t amount, char *strategy); /* Operations that allow use of regular stdio --- USE WITH CAUTION */ extern FILE *AllocateFile(const char *name, const char *mode); @@ -113,6 +115,7 @@ extern int pg_fsync_no_writethrough(int fd); extern int pg_fsync_writethrough(int fd); extern int pg_fdatasync(int fd); extern int pg_flush_data(int fd, off_t offset, off_t amount); +extern int pg_fadvise(int fd, off_t offset, off_t amount, int advise); extern void fsync_fname(char *fname, bool isdir); /* Filename components for OpenTemporaryFile */ diff --git a/src/include/storage/smgr.h b/src/include/storage/smgr.h index 98b6f13..0c4f14e 100644 --- a/src/include/storage/smgr.h +++ b/src/include/storage/smgr.h @@ -92,7 +92,7 @@ extern void smgrextend(SMgrRelation reln, ForkNumber forknum, extern void smgrprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum); extern void smgrread(SMgrRelation reln, ForkNumber forknum, - BlockNumber blocknum, char *buffer); + BlockNumber blocknum, char *buffer, char *strategy); extern void smgrwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync); extern BlockNumber smgrnblocks(SMgrRelation reln, ForkNumber forknum); @@ -118,7 +118,7 @@ extern void mdextend(SMgrRelation reln, ForkNumber forknum, extern void mdprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum); extern void mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, - char *buffer); + char *buffer, char *strategy); extern void mdwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync); extern BlockNumber mdnblocks(SMgrRelation reln, ForkNumber forknum);