From 2d79ed35fd906dc53fb7ac7695cfec92544dd7ac Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Wed, 19 Jul 2023 12:32:51 +1200 Subject: [PATCH v1 01/14] Provide vectored variants of FileRead() and FileWrite(). FileReadV() and FileWriteV() adapt preadv() and pwritev() for PostgreSQL's virtual file descriptors. The traditional FileRead() and FileWrite() functions are implemented in terms of the new functions. Author: Thomas Munro --- src/backend/storage/file/fd.c | 39 +++++++++++++++++++++++++++-------- src/include/storage/fd.h | 30 +++++++++++++++++++++++++-- 2 files changed, 58 insertions(+), 11 deletions(-) diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index b490a76ba7..ac5b981cce 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -2085,8 +2085,8 @@ FileWriteback(File file, off_t offset, off_t nbytes, uint32 wait_event_info) } int -FileRead(File file, void *buffer, size_t amount, off_t offset, - uint32 wait_event_info) +FileReadV(File file, const struct iovec *iov, int iovcnt, off_t offset, + uint32 wait_event_info) { int returnCode; Vfd *vfdP; @@ -2106,7 +2106,14 @@ FileRead(File file, void *buffer, size_t amount, off_t offset, retry: pgstat_report_wait_start(wait_event_info); - returnCode = pg_pread(vfdP->fd, buffer, amount, offset); + /* Avoid a slightly more expensive kernel call if there is no benefit. */ + if (iovcnt == 1) + returnCode = pg_pread(vfdP->fd, + iov[0].iov_base, + iov[0].iov_len, + offset); + else + returnCode = pg_preadv(vfdP->fd, iov, iovcnt, offset); pgstat_report_wait_end(); if (returnCode < 0) @@ -2141,8 +2148,8 @@ retry: } int -FileWrite(File file, const void *buffer, size_t amount, off_t offset, - uint32 wait_event_info) +FileWriteV(File file, const struct iovec *iov, int iovcnt, off_t offset, + uint32 wait_event_info) { int returnCode; Vfd *vfdP; @@ -2170,7 +2177,14 @@ FileWrite(File file, const void *buffer, size_t amount, off_t offset, */ if (temp_file_limit >= 0 && (vfdP->fdstate & FD_TEMP_FILE_LIMIT)) { - off_t past_write = offset + amount; + size_t size = 0; + off_t past_write; + + /* Compute the total transfer size. */ + for (int i = 0; i < iovcnt; ++i) + size += iov[i].iov_len; + + past_write = offset + size; if (past_write > vfdP->fileSize) { @@ -2188,11 +2202,18 @@ FileWrite(File file, const void *buffer, size_t amount, off_t offset, retry: errno = 0; pgstat_report_wait_start(wait_event_info); - returnCode = pg_pwrite(VfdCache[file].fd, buffer, amount, offset); + /* Avoid a slightly more expensive kernel call if there is no benefit. */ + if (iovcnt == 1) + returnCode = pg_pwrite(vfdP->fd, + iov[0].iov_base, + iov[0].iov_len, + offset); + else + returnCode = pg_pwritev(vfdP->fd, iov, iovcnt, offset); pgstat_report_wait_end(); /* if write didn't set errno, assume problem is no disk space */ - if (returnCode != amount && errno == 0) + if (returnCode < 0 && errno == 0) errno = ENOSPC; if (returnCode >= 0) @@ -2202,7 +2223,7 @@ retry: */ if (vfdP->fdstate & FD_TEMP_FILE_LIMIT) { - off_t past_write = offset + amount; + off_t past_write = offset + returnCode; if (past_write > vfdP->fileSize) { diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h index 6791a406fc..a354ae5a7f 100644 --- a/src/include/storage/fd.h +++ b/src/include/storage/fd.h @@ -43,6 +43,8 @@ #ifndef FD_H #define FD_H +#include "port/pg_iovec.h" + #include #include @@ -111,8 +113,8 @@ extern File PathNameOpenFilePerm(const char *fileName, int fileFlags, mode_t fil extern File OpenTemporaryFile(bool interXact); extern void FileClose(File file); extern int FilePrefetch(File file, off_t offset, off_t amount, uint32 wait_event_info); -extern int FileRead(File file, void *buffer, size_t amount, off_t offset, uint32 wait_event_info); -extern int FileWrite(File file, const void *buffer, size_t amount, off_t offset, uint32 wait_event_info); +extern int FileReadV(File file, const struct iovec *ioc, int iovcnt, off_t offset, uint32 wait_event_info); +extern int FileWriteV(File file, const struct iovec *ioc, int iovcnt, off_t offset, uint32 wait_event_info); extern int FileSync(File file, uint32 wait_event_info); extern int FileZero(File file, off_t offset, off_t amount, uint32 wait_event_info); extern int FileFallocate(File file, off_t offset, off_t amount, uint32 wait_event_info); @@ -195,6 +197,30 @@ extern int durable_unlink(const char *fname, int elevel); extern void SyncDataDirectory(void); extern int data_sync_elevel(int elevel); +static inline int +FileRead(File file, void *buffer, size_t amount, off_t offset, + uint32 wait_event_info) +{ + struct iovec iov = { + .iov_base = buffer, + .iov_len = amount + }; + + return FileReadV(file, &iov, 1, offset, wait_event_info); +} + +static inline int +FileWrite(File file, const void *buffer, size_t amount, off_t offset, + uint32 wait_event_info) +{ + struct iovec iov = { + .iov_base = unconstify(void *, buffer), + .iov_len = amount + }; + + return FileWriteV(file, &iov, 1, offset, wait_event_info); +} + /* Filename components */ #define PG_TEMP_FILES_DIR "pgsql_tmp" #define PG_TEMP_FILE_PREFIX "pgsql_tmp" -- 2.39.2