postgresql/src/include/storage/smgr.h
Amit Kapila d6ad34f341 Optimize DropRelFileNodeBuffers() for recovery.
The recovery path of DropRelFileNodeBuffers() is optimized so that
scanning of the whole buffer pool can be avoided when the number of
blocks to be truncated in a relation is below a certain threshold. For
such cases, we find the buffers by doing lookups in BufMapping table.
This improves the performance by more than 100 times in many cases
when several small tables (tested with 1000 relations) are truncated
and where the server is configured with a large value of shared
buffers (greater than equal to 100GB).

This optimization helps cases (a) when vacuum or autovacuum truncated off
any of the empty pages at the end of a relation, or (b) when the relation is
truncated in the same transaction in which it was created.

This commit introduces a new API smgrnblocks_cached which returns a cached
value for the number of blocks in a relation fork. This helps us to determine
the exact size of relation which is required to apply this optimization. The
exact size is required to ensure that we don't leave any buffer for the
relation being dropped as otherwise the background writer or checkpointer
can lead to a PANIC error while flushing buffers corresponding to files that
don't exist.

Author: Kirk Jamison based on ideas by Amit Kapila
Reviewed-by: Kyotaro Horiguchi, Takayuki Tsunakawa, and Amit Kapila
Tested-By: Haiying Tang
Discussion: https://postgr.es/m/OSBPR01MB3207DCA7EC725FDD661B3EDAEF660@OSBPR01MB3207.jpnprd01.prod.outlook.com
2021-01-12 07:45:40 +05:30

108 lines
4.2 KiB
C

/*-------------------------------------------------------------------------
*
* smgr.h
* storage manager switch public interface declarations.
*
*
* Portions Copyright (c) 1996-2021, 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/relfilenode.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
{
/* rnode is the hashtable lookup key, so it must be first! */
RelFileNodeBackend smgr_rnode; /* 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) \
RelFileNodeBackendIsTemp((smgr)->smgr_rnode)
extern void smgrinit(void);
extern SMgrRelation smgropen(RelFileNode rnode, 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 smgrclosenode(RelFileNodeBackend rnode);
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, char *buffer, bool skipFsync);
extern bool smgrprefetch(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum);
extern void smgrread(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, char *buffer);
extern void smgrwrite(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, char *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);
#endif /* SMGR_H */