mirror of
https://github.com/postgres/postgres.git
synced 2025-11-26 23:43:30 +03:00
4d330a61bb
smgrzeroextend() uses FileFallocate() to efficiently extend files by multiple blocks. When extending by a small number of blocks, use FileZero() instead, as using posix_fallocate() for small numbers of blocks is inefficient for some file systems / operating systems. FileZero() is also used as the fallback for FileFallocate() on platforms / filesystems that don't support fallocate. A big advantage of using posix_fallocate() is that it typically won't cause dirty buffers in the kernel pagecache. So far the most common pattern in our code is that we smgrextend() a page full of zeroes and put the corresponding page into shared buffers, from where we later write out the actual contents of the page. If the kernel, e.g. due to memory pressure or elapsed time, already wrote back the all-zeroes page, this can lead to doubling the amount of writes reaching storage. There are no users of smgrzeroextend() as of this commit. That will follow in future commits. Reviewed-by: Melanie Plageman <melanieplageman@gmail.com> Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi> Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Reviewed-by: David Rowley <dgrowleyml@gmail.com> Reviewed-by: John Naylor <john.naylor@enterprisedb.com> Discussion: https://postgr.es/m/20221029025420.eplyow6k7tgu6he3@awork3.anarazel.de
114 lines
4.5 KiB
C
114 lines
4.5 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* smgr.h
|
|
* storage manager switch public interface declarations.
|
|
*
|
|
*
|
|
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
*
|
|
* src/include/storage/smgr.h
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#ifndef SMGR_H
|
|
#define SMGR_H
|
|
|
|
#include "lib/ilist.h"
|
|
#include "storage/block.h"
|
|
#include "storage/relfilelocator.h"
|
|
|
|
/*
|
|
* smgr.c maintains a table of SMgrRelation objects, which are essentially
|
|
* cached file handles. An SMgrRelation is created (if not already present)
|
|
* by smgropen(), and destroyed by smgrclose(). Note that neither of these
|
|
* operations imply I/O, they just create or destroy a hashtable entry.
|
|
* (But smgrclose() may release associated resources, such as OS-level file
|
|
* descriptors.)
|
|
*
|
|
* An SMgrRelation may have an "owner", which is just a pointer to it from
|
|
* somewhere else; smgr.c will clear this pointer if the SMgrRelation is
|
|
* closed. We use this to avoid dangling pointers from relcache to smgr
|
|
* without having to make the smgr explicitly aware of relcache. There
|
|
* can't be more than one "owner" pointer per SMgrRelation, but that's
|
|
* all we need.
|
|
*
|
|
* SMgrRelations that do not have an "owner" are considered to be transient,
|
|
* and are deleted at end of transaction.
|
|
*/
|
|
typedef struct SMgrRelationData
|
|
{
|
|
/* rlocator is the hashtable lookup key, so it must be first! */
|
|
RelFileLocatorBackend smgr_rlocator; /* relation physical identifier */
|
|
|
|
/* pointer to owning pointer, or NULL if none */
|
|
struct SMgrRelationData **smgr_owner;
|
|
|
|
/*
|
|
* The following fields are reset to InvalidBlockNumber upon a cache flush
|
|
* event, and hold the last known size for each fork. This information is
|
|
* currently only reliable during recovery, since there is no cache
|
|
* invalidation for fork extension.
|
|
*/
|
|
BlockNumber smgr_targblock; /* current insertion target block */
|
|
BlockNumber smgr_cached_nblocks[MAX_FORKNUM + 1]; /* last known size */
|
|
|
|
/* additional public fields may someday exist here */
|
|
|
|
/*
|
|
* Fields below here are intended to be private to smgr.c and its
|
|
* submodules. Do not touch them from elsewhere.
|
|
*/
|
|
int smgr_which; /* storage manager selector */
|
|
|
|
/*
|
|
* for md.c; per-fork arrays of the number of open segments
|
|
* (md_num_open_segs) and the segments themselves (md_seg_fds).
|
|
*/
|
|
int md_num_open_segs[MAX_FORKNUM + 1];
|
|
struct _MdfdVec *md_seg_fds[MAX_FORKNUM + 1];
|
|
|
|
/* if unowned, list link in list of all unowned SMgrRelations */
|
|
dlist_node node;
|
|
} SMgrRelationData;
|
|
|
|
typedef SMgrRelationData *SMgrRelation;
|
|
|
|
#define SmgrIsTemp(smgr) \
|
|
RelFileLocatorBackendIsTemp((smgr)->smgr_rlocator)
|
|
|
|
extern void smgrinit(void);
|
|
extern SMgrRelation smgropen(RelFileLocator rlocator, BackendId backend);
|
|
extern bool smgrexists(SMgrRelation reln, ForkNumber forknum);
|
|
extern void smgrsetowner(SMgrRelation *owner, SMgrRelation reln);
|
|
extern void smgrclearowner(SMgrRelation *owner, SMgrRelation reln);
|
|
extern void smgrclose(SMgrRelation reln);
|
|
extern void smgrcloseall(void);
|
|
extern void smgrcloserellocator(RelFileLocatorBackend rlocator);
|
|
extern void smgrrelease(SMgrRelation reln);
|
|
extern void smgrreleaseall(void);
|
|
extern void smgrcreate(SMgrRelation reln, ForkNumber forknum, bool isRedo);
|
|
extern void smgrdosyncall(SMgrRelation *rels, int nrels);
|
|
extern void smgrdounlinkall(SMgrRelation *rels, int nrels, bool isRedo);
|
|
extern void smgrextend(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, const void *buffer, bool skipFsync);
|
|
extern void smgrzeroextend(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, int nblocks, bool skipFsync);
|
|
extern bool smgrprefetch(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum);
|
|
extern void smgrread(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, void *buffer);
|
|
extern void smgrwrite(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, const void *buffer, bool skipFsync);
|
|
extern void smgrwriteback(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, BlockNumber nblocks);
|
|
extern BlockNumber smgrnblocks(SMgrRelation reln, ForkNumber forknum);
|
|
extern BlockNumber smgrnblocks_cached(SMgrRelation reln, ForkNumber forknum);
|
|
extern void smgrtruncate(SMgrRelation reln, ForkNumber *forknum,
|
|
int nforks, BlockNumber *nblocks);
|
|
extern void smgrimmedsync(SMgrRelation reln, ForkNumber forknum);
|
|
extern void AtEOXact_SMgr(void);
|
|
extern bool ProcessBarrierSmgrRelease(void);
|
|
|
|
#endif /* SMGR_H */
|