database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-24 01:29:19 +03:00
Code Activity

Improve concurrency of foreign key locking

Browse Source 
This patch introduces two additional lock modes for tuples: "SELECT FOR
KEY SHARE" and "SELECT FOR NO KEY UPDATE".  These don't block each
other, in contrast with already existing "SELECT FOR SHARE" and "SELECT
FOR UPDATE".  UPDATE commands that do not modify the values stored in
the columns that are part of the key of the tuple now grab a SELECT FOR
NO KEY UPDATE lock on the tuple, allowing them to proceed concurrently
with tuple locks of the FOR KEY SHARE variety.

Foreign key triggers now use FOR KEY SHARE instead of FOR SHARE; this
means the concurrency improvement applies to them, which is the whole
point of this patch.

The added tuple lock semantics require some rejiggering of the multixact
module, so that the locking level that each transaction is holding can
be stored alongside its Xid.  Also, multixacts now need to persist
across server restarts and crashes, because they can now represent not
only tuple locks, but also tuple updates.  This means we need more
careful tracking of lifetime of pg_multixact SLRU files; since they now
persist longer, we require more infrastructure to figure out when they
can be removed.  pg_upgrade also needs to be careful to copy
pg_multixact files over from the old server to the new, or at least part
of multixact.c state, depending on the versions of the old and new
servers.

Tuple time qualification rules (HeapTupleSatisfies routines) need to be
careful not to consider tuples with the "is multi" infomask bit set as
being only locked; they might need to look up MultiXact values (i.e.
possibly do pg_multixact I/O) to find out the Xid that updated a tuple,
whereas they previously were assured to only use information readily
available from the tuple header.  This is considered acceptable, because
the extra I/O would involve cases that would previously cause some
commands to block waiting for concurrent transactions to finish.

Another important change is the fact that locking tuples that have
previously been updated causes the future versions to be marked as
locked, too; this is essential for correctness of foreign key checks.
This causes additional WAL-logging, also (there was previously a single
WAL record for a locked tuple; now there are as many as updated copies
of the tuple there exist.)

With all this in place, contention related to tuples being checked by
foreign key rules should be much reduced.

As a bonus, the old behavior that a subtransaction grabbing a stronger
tuple lock than the parent (sub)transaction held on a given tuple and
later aborting caused the weaker lock to be lost, has been fixed.

Many new spec files were added for isolation tester framework, to ensure
overall behavior is sane.  There's probably room for several more tests.

There were several reviewers of this patch; in particular, Noah Misch
and Andres Freund spent considerable time in it.  Original idea for the
patch came from Simon Riggs, after a problem report by Joel Jacobson.
Most code is from me, with contributions from Marti Raudsepp, Alexander
Shulgin, Noah Misch and Andres Freund.

This patch was discussed in several pgsql-hackers threads; the most
important start at the following message-ids:
	AANLkTimo9XVcEzfiBR-ut3KVNDkjm2Vxh+t8kAmWjPuv@mail.gmail.com
	1290721684-sup-3951@alvh.no-ip.org
	1294953201-sup-2099@alvh.no-ip.org
	1320343602-sup-2290@alvh.no-ip.org
	1339690386-sup-8927@alvh.no-ip.org
	4FE5FF020200002500048A3D@gw.wicourts.gov
	4FEAB90A0200002500048B7D@gw.wicourts.gov
This commit is contained in:
Alvaro Herrera
2013-01-23 12:04:59 -03:00
parent f925c79b9f
commit 0ac5ad5134
106 changed files with 6019 additions and 1483 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
src/include/access/multixact.h
View File

@@ -13,8 +13,15 @@
#include "access/xlog.h"
/*
* The first two MultiXactId values are reserved to store the truncation Xid
* and epoch of the first segment, so we start assigning multixact values from
* 2.
*/
#define InvalidMultiXactId ((MultiXactId) 0)
#define FirstMultiXactId ((MultiXactId) 1)
#define MaxMultiXactId ((MultiXactId) 0xFFFFFFFF)
#define MultiXactIdIsValid(multi) ((multi) != InvalidMultiXactId)
@@ -22,6 +29,33 @@
#define NUM_MXACTOFFSET_BUFFERS 8
#define NUM_MXACTMEMBER_BUFFERS 16
/*
* Possible multixact lock modes ("status"). The first four modes are for
* tuple locks (FOR KEY SHARE, FOR SHARE, FOR NO KEY UPDATE, FOR UPDATE); the
* next two are used for update and delete modes.
*/
typedef enum
{
MultiXactStatusForKeyShare = 0x00,
MultiXactStatusForShare = 0x01,
MultiXactStatusForNoKeyUpdate = 0x02,
MultiXactStatusForUpdate = 0x03,
/* an update that doesn't touch "key" columns */
MultiXactStatusNoKeyUpdate = 0x04,
/* other updates, and delete */
MultiXactStatusUpdate = 0x05
} MultiXactStatus;
#define MaxMultiXactStatus MultiXactStatusUpdate
typedef struct MultiXactMember
{
TransactionId xid;
MultiXactStatus status;
} MultiXactMember;
/* ----------------
* multixact-related XLOG entries
* ----------------
@@ -35,21 +69,24 @@ typedef struct xl_multixact_create
{
MultiXactId mid; /* new MultiXact's ID */
MultiXactOffset moff; /* its starting offset in members file */
int32 nxids; /* number of member XIDs */
TransactionId xids[1]; /* VARIABLE LENGTH ARRAY */
int32 nmembers; /* number of member XIDs */
MultiXactMember members[FLEXIBLE_ARRAY_MEMBER];
} xl_multixact_create;
#define MinSizeOfMultiXactCreate offsetof(xl_multixact_create, xids)
#define SizeOfMultiXactCreate (offsetof(xl_multixact_create, members))
extern MultiXactId MultiXactIdCreate(TransactionId xid1, TransactionId xid2);
extern MultiXactId MultiXactIdExpand(MultiXactId multi, TransactionId xid);
extern MultiXactId MultiXactIdCreate(TransactionId xid1,
MultiXactStatus status1, TransactionId xid2,
MultiXactStatus status2);
extern MultiXactId MultiXactIdExpand(MultiXactId multi, TransactionId xid,
MultiXactStatus status);
extern MultiXactId ReadNextMultiXactId(void);
extern bool MultiXactIdIsRunning(MultiXactId multi);
extern bool MultiXactIdIsCurrent(MultiXactId multi);
extern void MultiXactIdWait(MultiXactId multi);
extern bool ConditionalMultiXactIdWait(MultiXactId multi);
extern void MultiXactIdSetOldestMember(void);
extern int GetMultiXactIdMembers(MultiXactId multi, TransactionId **xids);
extern int GetMultiXactIdMembers(MultiXactId multi, MultiXactMember **xids,
bool allow_old);
extern bool MultiXactIdPrecedes(MultiXactId multi1, MultiXactId multi2);
extern void AtEOXact_MultiXact(void);
extern void AtPrepare_MultiXact(void);
@@ -60,14 +97,21 @@ extern void MultiXactShmemInit(void);
extern void BootStrapMultiXact(void);
extern void StartupMultiXact(void);
extern void ShutdownMultiXact(void);
extern void SetMultiXactIdLimit(MultiXactId oldest_datminmxid,
Oid oldest_datoid);
extern void MultiXactGetCheckptMulti(bool is_shutdown,
MultiXactId *nextMulti,
MultiXactOffset *nextMultiOffset);
MultiXactOffset *nextMultiOffset,
MultiXactId *oldestMulti,
Oid *oldestMultiDB);
extern void CheckPointMultiXact(void);
extern MultiXactId GetOldestMultiXactId(void);
extern void TruncateMultiXact(MultiXactId cutoff_multi);
extern void MultiXactSetNextMXact(MultiXactId nextMulti,
MultiXactOffset nextMultiOffset);
extern void MultiXactAdvanceNextMXact(MultiXactId minMulti,
MultiXactOffset minMultiOffset);
extern void MultiXactAdvanceOldest(MultiXactId oldestMulti, Oid oldestMultiDB);
extern void multixact_twophase_recover(TransactionId xid, uint16 info,
void *recdata, uint32 len);
@@ -78,5 +122,7 @@ extern void multixact_twophase_postabort(TransactionId xid, uint16 info,
extern void multixact_redo(XLogRecPtr lsn, XLogRecord *record);
extern void multixact_desc(StringInfo buf, uint8 xl_info, char *rec);
extern char *mxid_to_string(MultiXactId multi, int nmembers,
MultiXactMember *members);
#endif /* MULTIXACT_H */