postgresql/src/include/access/slru.h

165 lines
5.3 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* slru.h
* Simple LRU buffering for transaction status logfiles
*
2017-01-03 19:48:53 +01:00
* Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
2010-09-20 22:08:53 +02:00
* src/include/access/slru.h
*
*-------------------------------------------------------------------------
*/
#ifndef SLRU_H
#define SLRU_H
#include "access/xlogdefs.h"
#include "storage/lwlock.h"
/*
* Define SLRU segment size. A page is the same BLCKSZ as is used everywhere
* else in Postgres. The segment size can be chosen somewhat arbitrarily;
* we make it 32 pages by default, or 256Kb, i.e. 1M transactions for CLOG
* or 64K transactions for SUBTRANS.
*
* Note: because TransactionIds are 32 bits and wrap around at 0xFFFFFFFF,
* page numbering also wraps around at 0xFFFFFFFF/xxxx_XACTS_PER_PAGE (where
* xxxx is CLOG or SUBTRANS, respectively), and segment numbering at
* 0xFFFFFFFF/xxxx_XACTS_PER_PAGE/SLRU_PAGES_PER_SEGMENT. We need
* take no explicit notice of that fact in slru.c, except when comparing
* segment and page numbers in SimpleLruTruncate (see PagePrecedes()).
*/
#define SLRU_PAGES_PER_SEGMENT 32
/* Maximum length of an SLRU name */
#define SLRU_MAX_NAME_LENGTH 32
/*
* Page status codes. Note that these do not include the "dirty" bit.
* page_dirty can be TRUE only in the VALID or WRITE_IN_PROGRESS states;
* in the latter case it implies that the page has been re-dirtied since
* the write started.
*/
typedef enum
{
SLRU_PAGE_EMPTY, /* buffer is not in use */
SLRU_PAGE_READ_IN_PROGRESS, /* page is being read in */
SLRU_PAGE_VALID, /* page is valid and not being written */
SLRU_PAGE_WRITE_IN_PROGRESS /* page is being written out */
} SlruPageStatus;
/*
* Shared-memory state
*/
typedef struct SlruSharedData
{
LWLock *ControlLock;
/* Number of buffers managed by this SLRU structure */
int num_slots;
/*
* Arrays holding info for each buffer slot. Page number is undefined
* when status is EMPTY, as is page_lru_count.
*/
char **page_buffer;
SlruPageStatus *page_status;
bool *page_dirty;
int *page_number;
int *page_lru_count;
/*
* Optional array of WAL flush LSNs associated with entries in the SLRU
* pages. If not zero/NULL, we must flush WAL before writing pages (true
* for pg_xact, false for multixact, pg_subtrans, pg_notify). group_lsn[]
* has lsn_groups_per_page entries per buffer slot, each containing the
* highest LSN known for a contiguous group of SLRU entries on that slot's
* page.
*/
XLogRecPtr *group_lsn;
int lsn_groups_per_page;
/*----------
* We mark a page "most recently used" by setting
* page_lru_count[slotno] = ++cur_lru_count;
* The oldest page is therefore the one with the highest value of
* cur_lru_count - page_lru_count[slotno]
* The counts will eventually wrap around, but this calculation still
* works as long as no page's age exceeds INT_MAX counts.
*----------
*/
int cur_lru_count;
/*
2005-10-15 04:49:52 +02:00
* latest_page_number is the page number of the current end of the log;
* this is not critical data, since we use it only to avoid swapping out
* the latest page.
*/
int latest_page_number;
/* LWLocks */
int lwlock_tranche_id;
char lwlock_tranche_name[SLRU_MAX_NAME_LENGTH];
LWLockPadded *buffer_locks;
} SlruSharedData;
typedef SlruSharedData *SlruShared;
/*
* SlruCtlData is an unshared structure that points to the active information
* in shared memory.
*/
typedef struct SlruCtlData
{
SlruShared shared;
/*
* This flag tells whether to fsync writes (true for pg_xact and multixact
* stuff, false for pg_subtrans and pg_notify).
*/
bool do_fsync;
2003-08-04 02:43:34 +02:00
/*
2005-10-15 04:49:52 +02:00
* Decide which of two page numbers is "older" for truncation purposes. We
* need to use comparison of TransactionIds here in order to do the right
* thing with wraparound XID arithmetic.
*/
2003-08-04 02:43:34 +02:00
bool (*PagePrecedes) (int, int);
/*
2005-10-15 04:49:52 +02:00
* Dir is set during SimpleLruInit and does not change thereafter. Since
* it's always the same, it doesn't need to be in shared memory.
*/
char Dir[64];
} SlruCtlData;
typedef SlruCtlData *SlruCtl;
extern Size SimpleLruShmemSize(int nslots, int nlsns);
extern void SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int nlsns,
LWLock *ctllock, const char *subdir, int tranche_id);
extern int SimpleLruZeroPage(SlruCtl ctl, int pageno);
2007-11-15 22:14:46 +01:00
extern int SimpleLruReadPage(SlruCtl ctl, int pageno, bool write_ok,
TransactionId xid);
2006-10-04 02:30:14 +02:00
extern int SimpleLruReadPage_ReadOnly(SlruCtl ctl, int pageno,
TransactionId xid);
extern void SimpleLruWritePage(SlruCtl ctl, int slotno);
Rework the way multixact truncations work. The fact that multixact truncations are not WAL logged has caused a fair share of problems. Amongst others it requires to do computations during recovery while the database is not in a consistent state, delaying truncations till checkpoints, and handling members being truncated, but offset not. We tried to put bandaids on lots of these issues over the last years, but it seems time to change course. Thus this patch introduces WAL logging for multixact truncations. This allows: 1) to perform the truncation directly during VACUUM, instead of delaying it to the checkpoint. 2) to avoid looking at the offsets SLRU for truncation during recovery, we can just use the master's values. 3) simplify a fair amount of logic to keep in memory limits straight, this has gotten much easier During the course of fixing this a bunch of additional bugs had to be fixed: 1) Data was not purged from memory the member's SLRU before deleting segments. This happened to be hard or impossible to hit due to the interlock between checkpoints and truncation. 2) find_multixact_start() relied on SimpleLruDoesPhysicalPageExist - but that doesn't work for offsets that haven't yet been flushed to disk. Add code to flush the SLRUs to fix. Not pretty, but it feels slightly safer to only make decisions based on actual on-disk state. 3) find_multixact_start() could be called concurrently with a truncation and thus fail. Via SetOffsetVacuumLimit() that could lead to a round of emergency vacuuming. The problem remains in pg_get_multixact_members(), but that's quite harmless. For now this is going to only get applied to 9.5+, leaving the issues in the older branches in place. It is quite possible that we need to backpatch at a later point though. For the case this gets backpatched we need to handle that an updated standby may be replaying WAL from a not-yet upgraded primary. We have to recognize that situation and use "old style" truncation (i.e. looking at the SLRUs) during WAL replay. In contrast to before, this now happens in the startup process, when replaying a checkpoint record, instead of the checkpointer. Doing truncation in the restartpoint is incorrect, they can happen much later than the original checkpoint, thereby leading to wraparound. To avoid "multixact_redo: unknown op code 48" errors standbys would have to be upgraded before primaries. A later patch will bump the WAL page magic, and remove the legacy truncation codepaths. Legacy truncation support is just included to make a possible future backpatch easier. Discussion: 20150621192409.GA4797@alap3.anarazel.de Reviewed-By: Robert Haas, Alvaro Herrera, Thomas Munro Backpatch: 9.5 for now
2015-09-26 19:04:25 +02:00
extern void SimpleLruFlush(SlruCtl ctl, bool allow_redirtied);
extern void SimpleLruTruncate(SlruCtl ctl, int cutoffPage);
extern bool SimpleLruDoesPhysicalPageExist(SlruCtl ctl, int pageno);
typedef bool (*SlruScanCallback) (SlruCtl ctl, char *filename, int segpage,
2017-06-21 20:39:04 +02:00
void *data);
extern bool SlruScanDirectory(SlruCtl ctl, SlruScanCallback callback, void *data);
Rework the way multixact truncations work. The fact that multixact truncations are not WAL logged has caused a fair share of problems. Amongst others it requires to do computations during recovery while the database is not in a consistent state, delaying truncations till checkpoints, and handling members being truncated, but offset not. We tried to put bandaids on lots of these issues over the last years, but it seems time to change course. Thus this patch introduces WAL logging for multixact truncations. This allows: 1) to perform the truncation directly during VACUUM, instead of delaying it to the checkpoint. 2) to avoid looking at the offsets SLRU for truncation during recovery, we can just use the master's values. 3) simplify a fair amount of logic to keep in memory limits straight, this has gotten much easier During the course of fixing this a bunch of additional bugs had to be fixed: 1) Data was not purged from memory the member's SLRU before deleting segments. This happened to be hard or impossible to hit due to the interlock between checkpoints and truncation. 2) find_multixact_start() relied on SimpleLruDoesPhysicalPageExist - but that doesn't work for offsets that haven't yet been flushed to disk. Add code to flush the SLRUs to fix. Not pretty, but it feels slightly safer to only make decisions based on actual on-disk state. 3) find_multixact_start() could be called concurrently with a truncation and thus fail. Via SetOffsetVacuumLimit() that could lead to a round of emergency vacuuming. The problem remains in pg_get_multixact_members(), but that's quite harmless. For now this is going to only get applied to 9.5+, leaving the issues in the older branches in place. It is quite possible that we need to backpatch at a later point though. For the case this gets backpatched we need to handle that an updated standby may be replaying WAL from a not-yet upgraded primary. We have to recognize that situation and use "old style" truncation (i.e. looking at the SLRUs) during WAL replay. In contrast to before, this now happens in the startup process, when replaying a checkpoint record, instead of the checkpointer. Doing truncation in the restartpoint is incorrect, they can happen much later than the original checkpoint, thereby leading to wraparound. To avoid "multixact_redo: unknown op code 48" errors standbys would have to be upgraded before primaries. A later patch will bump the WAL page magic, and remove the legacy truncation codepaths. Legacy truncation support is just included to make a possible future backpatch easier. Discussion: 20150621192409.GA4797@alap3.anarazel.de Reviewed-By: Robert Haas, Alvaro Herrera, Thomas Munro Backpatch: 9.5 for now
2015-09-26 19:04:25 +02:00
extern void SlruDeleteSegment(SlruCtl ctl, int segno);
/* SlruScanDirectory public callbacks */
extern bool SlruScanDirCbReportPresence(SlruCtl ctl, char *filename,
int segpage, void *data);
extern bool SlruScanDirCbDeleteAll(SlruCtl ctl, char *filename, int segpage,
void *data);
Phase 2 of pgindent updates. Change pg_bsd_indent to follow upstream rules for placement of comments to the right of code, and remove pgindent hack that caused comments following #endif to not obey the general rule. Commit e3860ffa4dd0dad0dd9eea4be9cc1412373a8c89 wasn't actually using the published version of pg_bsd_indent, but a hacked-up version that tried to minimize the amount of movement of comments to the right of code. The situation of interest is where such a comment has to be moved to the right of its default placement at column 33 because there's code there. BSD indent has always moved right in units of tab stops in such cases --- but in the previous incarnation, indent was working in 8-space tab stops, while now it knows we use 4-space tabs. So the net result is that in about half the cases, such comments are placed one tab stop left of before. This is better all around: it leaves more room on the line for comment text, and it means that in such cases the comment uniformly starts at the next 4-space tab stop after the code, rather than sometimes one and sometimes two tabs after. Also, ensure that comments following #endif are indented the same as comments following other preprocessor commands such as #else. That inconsistency turns out to have been self-inflicted damage from a poorly-thought-through post-indent "fixup" in pgindent. This patch is much less interesting than the first round of indent changes, but also bulkier, so I thought it best to separate the effects. Discussion: https://postgr.es/m/E1dAmxK-0006EE-1r@gemulon.postgresql.org Discussion: https://postgr.es/m/30527.1495162840@sss.pgh.pa.us
2017-06-21 21:18:54 +02:00
#endif /* SLRU_H */