mirror of
https://git.postgresql.org/git/postgresql.git
synced 2026-02-14 18:37:03 +08:00
53c2a97a92
More precisely, what we do here is make the SLRU cache sizes configurable with new GUCs, so that sites with high concurrency and big ranges of transactions in flight (resp. multixacts/subtransactions) can benefit from bigger caches. In order for this to work with good performance, two additional changes are made: 1. the cache is divided in "banks" (to borrow terminology from CPU caches), and algorithms such as eviction buffer search only affect one specific bank. This forestalls the problem that linear searching for a specific buffer across the whole cache takes too long: we only have to search the specific bank, whose size is small. This work is authored by Andrey Borodin. 2. Change the locking regime for the SLRU banks, so that each bank uses a separate LWLock. This allows for increased scalability. This work is authored by Dilip Kumar. (A part of this was previously committed as d172b717c6f4.) Special care is taken so that the algorithms that can potentially traverse more than one bank release one bank's lock before acquiring the next. This should happen rarely, but particularly clog.c's group commit feature needed code adjustment to cope with this. I (Álvaro) also added lots of comments to make sure the design is sound. The new GUCs match the names introduced by bcdfa5f2e2f2 in the pg_stat_slru view. The default values for these parameters are similar to the previous sizes of each SLRU. commit_ts, clog and subtrans accept value 0, which means to adjust by dividing shared_buffers by 512 (so 2MB for every 1GB of shared_buffers), with a cap of 8MB. (A new slru.c function SimpleLruAutotuneBuffers() was added to support this.) The cap was previously 1MB for clog, so for sites with more than 512MB of shared memory the total memory used increases, which is likely a good tradeoff. However, other SLRUs (notably multixact ones) retain smaller sizes and don't support a configured value of 0. These values based on shared_buffers may need to be revisited, but that's an easy change. There was some resistance to adding these new GUCs: it would be better to adjust to memory pressure automatically somehow, for example by stealing memory from shared_buffers (where the caches can grow and shrink naturally). However, doing that seems to be a much larger project and one which has made virtually no progress in several years, and because this is such a pain point for so many users, here we take the pragmatic approach. Author: Andrey Borodin <x4mmm@yandex-team.ru> Author: Dilip Kumar <dilipbalaut@gmail.com> Reviewed-by: Amul Sul, Gilles Darold, Anastasia Lubennikova, Ivan Lazarev, Robert Haas, Thomas Munro, Tomas Vondra, Yura Sokolov, Васильев Дмитрий (Dmitry Vasiliev). Discussion: https://postgr.es/m/2BEC2B3F-9B61-4C1D-9FB5-5FAB0F05EF86@yandex-team.ru Discussion: https://postgr.es/m/CAFiTN-vzDvNz=ExGXz6gdyjtzGixKSqs0mKHMmaQ8sOSEFZ33A@mail.gmail.com
74 lines
2.2 KiB
C
74 lines
2.2 KiB
C
/*
|
|
* commit_ts.h
|
|
*
|
|
* PostgreSQL commit timestamp manager
|
|
*
|
|
* Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
*
|
|
* src/include/access/commit_ts.h
|
|
*/
|
|
#ifndef COMMIT_TS_H
|
|
#define COMMIT_TS_H
|
|
|
|
#include "access/xlog.h"
|
|
#include "datatype/timestamp.h"
|
|
#include "replication/origin.h"
|
|
#include "storage/sync.h"
|
|
|
|
|
|
extern PGDLLIMPORT bool track_commit_timestamp;
|
|
|
|
extern void TransactionTreeSetCommitTsData(TransactionId xid, int nsubxids,
|
|
TransactionId *subxids, TimestampTz timestamp,
|
|
RepOriginId nodeid);
|
|
extern bool TransactionIdGetCommitTsData(TransactionId xid,
|
|
TimestampTz *ts, RepOriginId *nodeid);
|
|
extern TransactionId GetLatestCommitTsData(TimestampTz *ts,
|
|
RepOriginId *nodeid);
|
|
|
|
extern Size CommitTsShmemSize(void);
|
|
extern void CommitTsShmemInit(void);
|
|
extern void BootStrapCommitTs(void);
|
|
extern void StartupCommitTs(void);
|
|
extern void CommitTsParameterChange(bool newvalue, bool oldvalue);
|
|
extern void CompleteCommitTsInitialization(void);
|
|
extern void CheckPointCommitTs(void);
|
|
extern void ExtendCommitTs(TransactionId newestXact);
|
|
extern void TruncateCommitTs(TransactionId oldestXact);
|
|
extern void SetCommitTsLimit(TransactionId oldestXact,
|
|
TransactionId newestXact);
|
|
extern void AdvanceOldestCommitTsXid(TransactionId oldestXact);
|
|
|
|
extern int committssyncfiletag(const FileTag *ftag, char *path);
|
|
|
|
/* XLOG stuff */
|
|
#define COMMIT_TS_ZEROPAGE 0x00
|
|
#define COMMIT_TS_TRUNCATE 0x10
|
|
|
|
typedef struct xl_commit_ts_set
|
|
{
|
|
TimestampTz timestamp;
|
|
RepOriginId nodeid;
|
|
TransactionId mainxid;
|
|
/* subxact Xids follow */
|
|
} xl_commit_ts_set;
|
|
|
|
#define SizeOfCommitTsSet (offsetof(xl_commit_ts_set, mainxid) + \
|
|
sizeof(TransactionId))
|
|
|
|
typedef struct xl_commit_ts_truncate
|
|
{
|
|
int64 pageno;
|
|
TransactionId oldestXid;
|
|
} xl_commit_ts_truncate;
|
|
|
|
#define SizeOfCommitTsTruncate (offsetof(xl_commit_ts_truncate, oldestXid) + \
|
|
sizeof(TransactionId))
|
|
|
|
extern void commit_ts_redo(XLogReaderState *record);
|
|
extern void commit_ts_desc(StringInfo buf, XLogReaderState *record);
|
|
extern const char *commit_ts_identify(uint8 info);
|
|
|
|
#endif /* COMMIT_TS_H */
|