mirror of
https://github.com/postgres/postgres.git
synced 2025-09-02 04:21:28 +03:00
Refactor the fsync queue for wider use.
Previously, md.c and checkpointer.c were tightly integrated so that fsync calls could be handed off and processed in the background. Introduce a system of callbacks and file tags, so that other modules can hand off fsync work in the same way. For now only md.c uses the new interface, but other users are being proposed. Since there may be use cases that are not strictly SMGR implementations, use a new function table for sync handlers rather than extending the traditional SMGR one. Instead of using a bitmapset of segment numbers for each RelFileNode in the checkpointer's hash table, make the segment number part of the key. This requires sending explicit "forget" requests for every segment individually when relations are dropped, but suits the file layout schemes of proposed future users better (ie sparse or high segment numbers). Author: Shawn Debnath and Thomas Munro Reviewed-by: Thomas Munro, Andres Freund Discussion: https://postgr.es/m/CAEepm=2gTANm=e3ARnJT=n0h8hf88wqmaZxk0JYkxw+b21fNrw@mail.gmail.com
This commit is contained in:
Thomas Munro
@@ -17,6 +17,8 @@
|
||||
|
||||
#include "storage/block.h"
|
||||
#include "storage/relfilenode.h"
|
||||
#include "storage/smgr.h"
|
||||
#include "storage/sync.h"
|
||||
|
||||
|
||||
/* GUC options */
|
||||
@@ -31,9 +33,9 @@ extern void CheckpointerMain(void) pg_attribute_noreturn();
|
||||
extern void RequestCheckpoint(int flags);
|
||||
extern void CheckpointWriteDelay(int flags, double progress);
|
||||
|
||||
extern bool ForwardFsyncRequest(RelFileNode rnode, ForkNumber forknum,
|
||||
BlockNumber segno);
|
||||
extern void AbsorbFsyncRequests(void);
|
||||
extern bool ForwardSyncRequest(const FileTag *ftag, SyncRequestType type);
|
||||
|
||||
extern void AbsorbSyncRequests(void);
|
||||
|
||||
extern Size CheckpointerShmemSize(void);
|
||||
extern void CheckpointerShmemInit(void);
|
||||
|
||||
@@ -54,6 +54,18 @@ extern PGDLLIMPORT bool data_sync_retry;
|
||||
*/
|
||||
extern int max_safe_fds;
|
||||
|
||||
/*
|
||||
* On Windows, we have to interpret EACCES as possibly meaning the same as
|
||||
* ENOENT, because if a file is unlinked-but-not-yet-gone on that platform,
|
||||
* that's what you get. Ugh. This code is designed so that we don't
|
||||
* actually believe these cases are okay without further evidence (namely,
|
||||
* a pending fsync request getting canceled ... see ProcessSyncRequests).
|
||||
*/
|
||||
#ifndef WIN32
|
||||
#define FILE_POSSIBLY_DELETED(err) ((err) == ENOENT)
|
||||
#else
|
||||
#define FILE_POSSIBLY_DELETED(err) ((err) == ENOENT || (err) == EACCES)
|
||||
#endif
|
||||
|
||||
/*
|
||||
* prototypes for functions in fd.c
|
||||
|
||||
51
src/include/storage/md.h
Normal file
51
src/include/storage/md.h
Normal file
@@ -0,0 +1,51 @@
|
||||
/*-------------------------------------------------------------------------
|
||||
*
|
||||
* md.h
|
||||
* magnetic disk storage manager public interface declarations.
|
||||
*
|
||||
*
|
||||
* Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* src/include/storage/md.h
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
#ifndef MD_H
|
||||
#define MD_H
|
||||
|
||||
#include "storage/block.h"
|
||||
#include "storage/relfilenode.h"
|
||||
#include "storage/smgr.h"
|
||||
#include "storage/sync.h"
|
||||
|
||||
/* md storage manager functionality */
|
||||
extern void mdinit(void);
|
||||
extern void mdclose(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdcreate(SMgrRelation reln, ForkNumber forknum, bool isRedo);
|
||||
extern bool mdexists(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdunlink(RelFileNodeBackend rnode, ForkNumber forknum, bool isRedo);
|
||||
extern void mdextend(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum, char *buffer, bool skipFsync);
|
||||
extern void mdprefetch(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum);
|
||||
extern void mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
|
||||
char *buffer);
|
||||
extern void mdwrite(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum, char *buffer, bool skipFsync);
|
||||
extern void mdwriteback(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum, BlockNumber nblocks);
|
||||
extern BlockNumber mdnblocks(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdtruncate(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber nblocks);
|
||||
extern void mdimmedsync(SMgrRelation reln, ForkNumber forknum);
|
||||
|
||||
extern void ForgetDatabaseSyncRequests(Oid dbid);
|
||||
extern void DropRelationFiles(RelFileNode *delrels, int ndelrels, bool isRedo);
|
||||
|
||||
/* md sync callbacks */
|
||||
extern int mdsyncfiletag(const FileTag *ftag, char *path);
|
||||
extern int mdunlinkfiletag(const FileTag *ftag, char *path);
|
||||
extern bool mdfiletagmatches(const FileTag *ftag, const FileTag *candidate);
|
||||
|
||||
#endif /* MD_H */
|
||||
@@ -18,7 +18,6 @@
|
||||
#include "storage/block.h"
|
||||
#include "storage/relfilenode.h"
|
||||
|
||||
|
||||
/*
|
||||
* smgr.c maintains a table of SMgrRelation objects, which are essentially
|
||||
* cached file handles. An SMgrRelation is created (if not already present)
|
||||
@@ -106,43 +105,6 @@ extern BlockNumber smgrnblocks(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void smgrtruncate(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber nblocks);
|
||||
extern void smgrimmedsync(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void smgrpreckpt(void);
|
||||
extern void smgrsync(void);
|
||||
extern void smgrpostckpt(void);
|
||||
extern void AtEOXact_SMgr(void);
|
||||
|
||||
|
||||
/* internals: move me elsewhere -- ay 7/94 */
|
||||
|
||||
/* in md.c */
|
||||
extern void mdinit(void);
|
||||
extern void mdclose(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdcreate(SMgrRelation reln, ForkNumber forknum, bool isRedo);
|
||||
extern bool mdexists(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdunlink(RelFileNodeBackend rnode, ForkNumber forknum, bool isRedo);
|
||||
extern void mdextend(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum, char *buffer, bool skipFsync);
|
||||
extern void mdprefetch(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum);
|
||||
extern void mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
|
||||
char *buffer);
|
||||
extern void mdwrite(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum, char *buffer, bool skipFsync);
|
||||
extern void mdwriteback(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber blocknum, BlockNumber nblocks);
|
||||
extern BlockNumber mdnblocks(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdtruncate(SMgrRelation reln, ForkNumber forknum,
|
||||
BlockNumber nblocks);
|
||||
extern void mdimmedsync(SMgrRelation reln, ForkNumber forknum);
|
||||
extern void mdpreckpt(void);
|
||||
extern void mdsync(void);
|
||||
extern void mdpostckpt(void);
|
||||
|
||||
extern void SetForwardFsyncRequests(void);
|
||||
extern void RememberFsyncRequest(RelFileNode rnode, ForkNumber forknum,
|
||||
BlockNumber segno);
|
||||
extern void ForgetRelationFsyncRequests(RelFileNode rnode, ForkNumber forknum);
|
||||
extern void ForgetDatabaseFsyncRequests(Oid dbid);
|
||||
extern void DropRelationFiles(RelFileNode *delrels, int ndelrels, bool isRedo);
|
||||
|
||||
#endif /* SMGR_H */
|
||||
|
||||
62
src/include/storage/sync.h
Normal file
62
src/include/storage/sync.h
Normal file
@@ -0,0 +1,62 @@
|
||||
/*-------------------------------------------------------------------------
|
||||
*
|
||||
* sync.h
|
||||
* File synchronization management code.
|
||||
*
|
||||
* Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* src/include/storage/sync.h
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
#ifndef SYNC_H
|
||||
#define SYNC_H
|
||||
|
||||
#include "storage/relfilenode.h"
|
||||
|
||||
/*
|
||||
* Type of sync request. These are used to manage the set of pending
|
||||
* requests to call a sync handler's sync or unlink functions at the next
|
||||
* checkpoint.
|
||||
*/
|
||||
typedef enum SyncRequestType
|
||||
{
|
||||
SYNC_REQUEST, /* schedule a call of sync function */
|
||||
SYNC_UNLINK_REQUEST, /* schedule a call of unlink function */
|
||||
SYNC_FORGET_REQUEST, /* forget all calls for a tag */
|
||||
SYNC_FILTER_REQUEST /* forget all calls satisfying match fn */
|
||||
} SyncRequestType;
|
||||
|
||||
/*
|
||||
* Which set of functions to use to handle a given request. See the function
|
||||
* table in sync.c.
|
||||
*/
|
||||
typedef enum SyncRequestHandler
|
||||
{
|
||||
SYNC_HANDLER_MD = 0 /* md smgr */
|
||||
} SyncRequestHandler;
|
||||
|
||||
/*
|
||||
* A tag identifying a file. Currently it has the members required for md.c's
|
||||
* usage, but sync.c has no knowledge of the internal structure, and it is
|
||||
* liable to change as required by future handlers.
|
||||
*/
|
||||
typedef struct FileTag
|
||||
{
|
||||
int16 handler; /* SyncRequstHandler value, saving space */
|
||||
int16 forknum; /* ForkNumber, saving space */
|
||||
RelFileNode rnode;
|
||||
uint32 segno;
|
||||
} FileTag;
|
||||
|
||||
extern void InitSync(void);
|
||||
extern void SyncPreCheckpoint(void);
|
||||
extern void SyncPostCheckpoint(void);
|
||||
extern void ProcessSyncRequests(void);
|
||||
extern void RememberSyncRequest(const FileTag *ftag, SyncRequestType type);
|
||||
extern void EnableSyncRequestForwarding(void);
|
||||
extern bool RegisterSyncRequest(const FileTag *ftag, SyncRequestType type,
|
||||
bool retryOnError);
|
||||
|
||||
#endif /* SYNC_H */
|
||||
Reference in New Issue
Block a user