public inbox for [email protected]
help / color / mirror / Atom feedFrom: Alexander Korotkov <[email protected]>
To: Andrey Borodin <[email protected]>
Cc: Anastasia Lubennikova <[email protected]>
Cc: Daniel Gustafsson <[email protected]>
Cc: Kyotaro Horiguchi <[email protected]>
Cc: pgsql-hackers <[email protected]>
Subject: Re: MultiXact\SLRU buffers configuration
Date: Tue, 27 Oct 2020 20:23:26 +0300
Message-ID: <CAPpHfdsUtSGxRrKn65F_wrE66sNztNY4TpDGDHh2kvAZZDOMqA@mail.gmail.com> (raw)
In-Reply-To: <CAPpHfduT0Kb+8fMt4t0EF5G_3hig+wYgeRadQnNq20F4VxP7LA@mail.gmail.com>
References: <[email protected]>
<[email protected]>
<[email protected]>
<[email protected]>
<[email protected]>
<[email protected]>
<[email protected]>
<[email protected]>
<CAPpHfduekT=BrM3rLqvo4ajzKYmDk+6aCoYJrNHhK0Je+v2z=Q@mail.gmail.com>
<[email protected]>
<CAPpHfduT0Kb+8fMt4t0EF5G_3hig+wYgeRadQnNq20F4VxP7LA@mail.gmail.com>
On Tue, Oct 27, 2020 at 8:02 PM Alexander Korotkov <[email protected]> wrote:
> On Mon, Oct 26, 2020 at 6:45 PM Andrey Borodin <[email protected]> wrote:
> > Thanks for your review, Alexander!
> > +1 for avoiding double locking in SimpleLruReadPage_ReadOnly().
> > Other changes seem correct to me too.
> >
> >
> > I've tried to find optimal value for cache size and it seems to me that it affects multixact scalability much less than sizes of offsets\members buffers. I concur that patch 2 of the patchset does not seem documented enough.
>
> Thank you. I've made a few more minor adjustments to the patchset.
> I'm going to push 0001 and 0003 if there are no objections.
I get that patchset v5 doesn't pass the tests due to typo in assert.
The fixes version is attached.
------
Regards,
Alexander Korotkov
Attachments:
[application/octet-stream] v6-0001-Use-shared-lock-in-GetMultiXactIdMembers-for-offs.patch (12.9K, ../CAPpHfdsUtSGxRrKn65F_wrE66sNztNY4TpDGDHh2kvAZZDOMqA@mail.gmail.com/2-v6-0001-Use-shared-lock-in-GetMultiXactIdMembers-for-offs.patch)
download | inline diff:
From 9307192bbb9d1ee48aba5c335ae54cff7b34ffb7 Mon Sep 17 00:00:00 2001
From: Alexander Korotkov <[email protected]>
Date: Tue, 27 Oct 2020 19:29:56 +0300
Subject: [PATCH 1/3] Use shared lock in GetMultiXactIdMembers for offsets and
members
Previously the read of multixact required exclusive control locks for both
offsets and members SLRUs. This could lead to the excessive lock contention.
This commit we makes multixacts SLRU take advantage of SimpleLruReadPage_ReadOnly
similar to clog, commit_ts and subtrans.
In order to evade extra reacquiring of CLRU lock, we teach
SimpleLruReadPage_ReadOnly() to take into account the current lock mode and
report resulting lock mode back.
Discussion: https://postgr.es/m/a7f1c4e1-1015-92a4-2bd4-6736bd13d03e%40postgrespro.ru#c496c4e75fc0605094a0e1f763e6a6ec
Author: Andrey Borodin
Reviewed-by: Kyotaro Horiguchi, Daniel Gustafsson
Reviewed-by: Anastasia Lubennikova, Alexander Korotkov
---
src/backend/access/transam/clog.c | 4 +++-
src/backend/access/transam/commit_ts.c | 4 +++-
src/backend/access/transam/multixact.c | 22 +++++++++++++++-------
src/backend/access/transam/slru.c | 23 +++++++++++++++++------
src/backend/access/transam/subtrans.c | 4 +++-
src/backend/commands/async.c | 4 +++-
src/backend/storage/lmgr/lwlock.c | 3 +++
src/backend/storage/lmgr/predicate.c | 4 +++-
src/include/access/slru.h | 2 +-
src/include/storage/lwlock.h | 2 ++
10 files changed, 53 insertions(+), 19 deletions(-)
diff --git a/src/backend/access/transam/clog.c b/src/backend/access/transam/clog.c
index 034349aa7b9..4c372065dee 100644
--- a/src/backend/access/transam/clog.c
+++ b/src/backend/access/transam/clog.c
@@ -640,10 +640,11 @@ TransactionIdGetStatus(TransactionId xid, XLogRecPtr *lsn)
int lsnindex;
char *byteptr;
XidStatus status;
+ LWLockMode lockmode = LW_NONE;
/* lock is acquired by SimpleLruReadPage_ReadOnly */
- slotno = SimpleLruReadPage_ReadOnly(XactCtl, pageno, xid);
+ slotno = SimpleLruReadPage_ReadOnly(XactCtl, pageno, xid, &lockmode);
byteptr = XactCtl->shared->page_buffer[slotno] + byteno;
status = (*byteptr >> bshift) & CLOG_XACT_BITMASK;
@@ -651,6 +652,7 @@ TransactionIdGetStatus(TransactionId xid, XLogRecPtr *lsn)
lsnindex = GetLSNIndex(slotno, xid);
*lsn = XactCtl->shared->group_lsn[lsnindex];
+ Assert(lockmode != LW_NONE);
LWLockRelease(XactSLRULock);
return status;
diff --git a/src/backend/access/transam/commit_ts.c b/src/backend/access/transam/commit_ts.c
index cb8a9688018..c19b0b5399e 100644
--- a/src/backend/access/transam/commit_ts.c
+++ b/src/backend/access/transam/commit_ts.c
@@ -288,6 +288,7 @@ TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
CommitTimestampEntry entry;
TransactionId oldestCommitTsXid;
TransactionId newestCommitTsXid;
+ LWLockMode lockmode = LW_NONE;
if (!TransactionIdIsValid(xid))
ereport(ERROR,
@@ -342,7 +343,7 @@ TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
}
/* lock is acquired by SimpleLruReadPage_ReadOnly */
- slotno = SimpleLruReadPage_ReadOnly(CommitTsCtl, pageno, xid);
+ slotno = SimpleLruReadPage_ReadOnly(CommitTsCtl, pageno, xid, &lockmode);
memcpy(&entry,
CommitTsCtl->shared->page_buffer[slotno] +
SizeOfCommitTimestampEntry * entryno,
@@ -352,6 +353,7 @@ TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
if (nodeid)
*nodeid = entry.nodeid;
+ Assert(lockmode != LW_NONE);
LWLockRelease(CommitTsSLRULock);
return *ts != 0;
}
diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index 43653fe5721..ccbce90f0ea 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -1237,6 +1237,7 @@ GetMultiXactIdMembers(MultiXactId multi, MultiXactMember **members,
MultiXactId tmpMXact;
MultiXactOffset nextOffset;
MultiXactMember *ptr;
+ LWLockMode lockmode = LW_NONE;
debug_elog3(DEBUG2, "GetMembers: asked for %u", multi);
@@ -1340,12 +1341,13 @@ GetMultiXactIdMembers(MultiXactId multi, MultiXactMember **members,
* time on every multixact creation.
*/
retry:
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
pageno = MultiXactIdToOffsetPage(multi);
entryno = MultiXactIdToOffsetEntry(multi);
- slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, multi);
+ /* lock is acquired by SimpleLruReadPage_ReadOnly */
+ slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno,
+ multi, &lockmode);
offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
offptr += entryno;
offset = *offptr;
@@ -1377,7 +1379,8 @@ retry:
entryno = MultiXactIdToOffsetEntry(tmpMXact);
if (pageno != prev_pageno)
- slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, tmpMXact);
+ slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno,
+ tmpMXact, &lockmode);
offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
offptr += entryno;
@@ -1395,14 +1398,14 @@ retry:
length = nextMXOffset - offset;
}
+ Assert(lockmode != LW_NONE);
LWLockRelease(MultiXactOffsetSLRULock);
ptr = (MultiXactMember *) palloc(length * sizeof(MultiXactMember));
*members = ptr;
/* Now get the members themselves. */
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
-
+ lockmode = LW_NONE;
truelength = 0;
prev_pageno = -1;
for (i = 0; i < length; i++, offset++)
@@ -1418,7 +1421,8 @@ retry:
if (pageno != prev_pageno)
{
- slotno = SimpleLruReadPage(MultiXactMemberCtl, pageno, true, multi);
+ slotno = SimpleLruReadPage_ReadOnly(MultiXactMemberCtl, pageno,
+ multi, &lockmode);
prev_pageno = pageno;
}
@@ -1441,6 +1445,7 @@ retry:
truelength++;
}
+ Assert(lockmode != LW_NONE);
LWLockRelease(MultiXactMemberSLRULock);
/*
@@ -2733,6 +2738,7 @@ find_multixact_start(MultiXactId multi, MultiXactOffset *result)
int entryno;
int slotno;
MultiXactOffset *offptr;
+ LWLockMode lockmode = LW_NONE;
Assert(MultiXactState->finishedStartup);
@@ -2749,10 +2755,12 @@ find_multixact_start(MultiXactId multi, MultiXactOffset *result)
return false;
/* lock is acquired by SimpleLruReadPage_ReadOnly */
- slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno, multi);
+ slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno,
+ multi, &lockmode);
offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
offptr += entryno;
offset = *offptr;
+ Assert(lockmode != LW_NONE);
LWLockRelease(MultiXactOffsetSLRULock);
*result = offset;
diff --git a/src/backend/access/transam/slru.c b/src/backend/access/transam/slru.c
index 16a78986971..cf89006e131 100644
--- a/src/backend/access/transam/slru.c
+++ b/src/backend/access/transam/slru.c
@@ -487,17 +487,23 @@ SimpleLruReadPage(SlruCtl ctl, int pageno, bool write_ok,
* Return value is the shared-buffer slot number now holding the page.
* The buffer's LRU access info is updated.
*
- * Control lock must NOT be held at entry, but will be held at exit.
- * It is unspecified whether the lock will be shared or exclusive.
+ * Control lock must be held in *lock_mode mode, which may be LW_NONE. Control
+ * lock will be held at exit in at least shared mode. Resulting control lock
+ * mode is set to *lock_mode.
*/
int
-SimpleLruReadPage_ReadOnly(SlruCtl ctl, int pageno, TransactionId xid)
+SimpleLruReadPage_ReadOnly(SlruCtl ctl, int pageno, TransactionId xid,
+ LWLockMode *lock_mode)
{
SlruShared shared = ctl->shared;
int slotno;
/* Try to find the page while holding only shared lock */
- LWLockAcquire(shared->ControlLock, LW_SHARED);
+ if (*lock_mode == LW_NONE)
+ {
+ LWLockAcquire(shared->ControlLock, LW_SHARED);
+ *lock_mode = LW_SHARED;
+ }
/* See if page is already in a buffer */
for (slotno = 0; slotno < shared->num_slots; slotno++)
@@ -517,8 +523,13 @@ SimpleLruReadPage_ReadOnly(SlruCtl ctl, int pageno, TransactionId xid)
}
/* No luck, so switch to normal exclusive lock and do regular read */
- LWLockRelease(shared->ControlLock);
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ if (*lock_mode != LW_EXCLUSIVE)
+ {
+ Assert(*lock_mode != LW_NONE);
+ LWLockRelease(shared->ControlLock);
+ LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ *lock_mode = LW_EXCLUSIVE;
+ }
return SimpleLruReadPage(ctl, pageno, true, xid);
}
diff --git a/src/backend/access/transam/subtrans.c b/src/backend/access/transam/subtrans.c
index 0111e867c79..7bb15431893 100644
--- a/src/backend/access/transam/subtrans.c
+++ b/src/backend/access/transam/subtrans.c
@@ -113,6 +113,7 @@ SubTransGetParent(TransactionId xid)
int slotno;
TransactionId *ptr;
TransactionId parent;
+ LWLockMode lockmode = LW_NONE;
/* Can't ask about stuff that might not be around anymore */
Assert(TransactionIdFollowsOrEquals(xid, TransactionXmin));
@@ -123,12 +124,13 @@ SubTransGetParent(TransactionId xid)
/* lock is acquired by SimpleLruReadPage_ReadOnly */
- slotno = SimpleLruReadPage_ReadOnly(SubTransCtl, pageno, xid);
+ slotno = SimpleLruReadPage_ReadOnly(SubTransCtl, pageno, xid, &lockmode);
ptr = (TransactionId *) SubTransCtl->shared->page_buffer[slotno];
ptr += entryno;
parent = *ptr;
+ Assert(lockmode != LW_NONE);
LWLockRelease(SubtransSLRULock);
return parent;
diff --git a/src/backend/commands/async.c b/src/backend/commands/async.c
index 8dbcace3f93..8b419575590 100644
--- a/src/backend/commands/async.c
+++ b/src/backend/commands/async.c
@@ -2002,6 +2002,7 @@ asyncQueueReadAllNotifications(void)
int curoffset = QUEUE_POS_OFFSET(pos);
int slotno;
int copysize;
+ LWLockMode lockmode = LW_NONE;
/*
* We copy the data from SLRU into a local buffer, so as to avoid
@@ -2010,7 +2011,7 @@ asyncQueueReadAllNotifications(void)
* part of the page we will actually inspect.
*/
slotno = SimpleLruReadPage_ReadOnly(NotifyCtl, curpage,
- InvalidTransactionId);
+ InvalidTransactionId, &lockmode);
if (curpage == QUEUE_POS_PAGE(head))
{
/* we only want to read as far as head */
@@ -2027,6 +2028,7 @@ asyncQueueReadAllNotifications(void)
NotifyCtl->shared->page_buffer[slotno] + curoffset,
copysize);
/* Release lock that we got from SimpleLruReadPage_ReadOnly() */
+ Assert(lockmode != LW_NONE);
LWLockRelease(NotifySLRULock);
/*
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 2fa90cc0954..8a7726f11c0 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -1068,6 +1068,8 @@ LWLockWakeup(LWLock *lock)
static void
LWLockQueueSelf(LWLock *lock, LWLockMode mode)
{
+ Assert(mode != LW_NONE);
+
/*
* If we don't have a PGPROC structure, there's no way to wait. This
* should never occur, since MyProc should only be null during shared
@@ -1828,6 +1830,7 @@ LWLockRelease(LWLock *lock)
elog(ERROR, "lock %s is not held", T_NAME(lock));
mode = held_lwlocks[i].mode;
+ Assert(mode == LW_EXCLUSIVE || mode == LW_SHARED);
num_held_lwlocks--;
for (; i < num_held_lwlocks; i++)
diff --git a/src/backend/storage/lmgr/predicate.c b/src/backend/storage/lmgr/predicate.c
index 8a365b400c6..a4df90a8aeb 100644
--- a/src/backend/storage/lmgr/predicate.c
+++ b/src/backend/storage/lmgr/predicate.c
@@ -924,6 +924,7 @@ SerialGetMinConflictCommitSeqNo(TransactionId xid)
TransactionId tailXid;
SerCommitSeqNo val;
int slotno;
+ LWLockMode lockmode = LW_NONE;
Assert(TransactionIdIsValid(xid));
@@ -946,8 +947,9 @@ SerialGetMinConflictCommitSeqNo(TransactionId xid)
* but will return with that lock held, which must then be released.
*/
slotno = SimpleLruReadPage_ReadOnly(SerialSlruCtl,
- SerialPage(xid), xid);
+ SerialPage(xid), xid, &lockmode);
val = SerialValue(slotno, xid);
+ Assert(lockmode != LW_NONE);
LWLockRelease(SerialSLRULock);
return val;
}
diff --git a/src/include/access/slru.h b/src/include/access/slru.h
index b39b43504d8..4b66d3b592b 100644
--- a/src/include/access/slru.h
+++ b/src/include/access/slru.h
@@ -142,7 +142,7 @@ extern int SimpleLruZeroPage(SlruCtl ctl, int pageno);
extern int SimpleLruReadPage(SlruCtl ctl, int pageno, bool write_ok,
TransactionId xid);
extern int SimpleLruReadPage_ReadOnly(SlruCtl ctl, int pageno,
- TransactionId xid);
+ TransactionId xid, LWLockMode *lock_mode);
extern void SimpleLruWritePage(SlruCtl ctl, int slotno);
extern void SimpleLruWriteAll(SlruCtl ctl, bool allow_redirtied);
extern void SimpleLruTruncate(SlruCtl ctl, int cutoffPage);
diff --git a/src/include/storage/lwlock.h b/src/include/storage/lwlock.h
index af9b41795d2..e680c6397aa 100644
--- a/src/include/storage/lwlock.h
+++ b/src/include/storage/lwlock.h
@@ -129,6 +129,8 @@ extern PGDLLIMPORT int NamedLWLockTrancheRequests;
typedef enum LWLockMode
{
+ LW_NONE, /* Not a lock mode. Indicates that there is no
+ * lock. */
LW_EXCLUSIVE,
LW_SHARED,
LW_WAIT_UNTIL_FREE /* A special mode used in PGPROC->lwWaitMode,
--
2.14.3
[application/octet-stream] v6-0002-Make-MultiXact-local-cache-size-configurable.patch (3.7K, ../CAPpHfdsUtSGxRrKn65F_wrE66sNztNY4TpDGDHh2kvAZZDOMqA@mail.gmail.com/3-v6-0002-Make-MultiXact-local-cache-size-configurable.patch)
download | inline diff:
From 2c40a5878da97b18e7e64a775f5caa0641e2f39c Mon Sep 17 00:00:00 2001
From: Alexander Korotkov <[email protected]>
Date: Mon, 26 Oct 2020 03:44:50 +0300
Subject: [PATCH 2/3] Make MultiXact local cache size configurable
---
doc/src/sgml/config.sgml | 16 ++++++++++++++++
src/backend/access/transam/multixact.c | 2 +-
src/backend/utils/init/globals.c | 2 ++
src/backend/utils/misc/guc.c | 10 ++++++++++
src/include/miscadmin.h | 2 ++
5 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index f043433e318..fd4ca293476 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -1823,6 +1823,22 @@ include_dir 'conf.d'
</listitem>
</varlistentry>
+ <varlistentry id="guc-multixact-local-cache-entries" xreflabel="multixact_local-cache-entries">
+ <term><varname>multixact_local_cache_entries</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>multixact_local_cache_entries</varname> configuration parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the number cached MultiXact by backend. Any SLRU lookup is preceeded
+ by cache lookup. Higher numbers of cache size help to deduplicate lock sets, while
+ lower values make cache lookup faster.
+ It defaults to 256.
+ </para>
+ </listitem>
+ </varlistentry>
+
<varlistentry id="guc-max-stack-depth" xreflabel="max_stack_depth">
<term><varname>max_stack_depth</varname> (<type>integer</type>)
<indexterm>
diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index ccbce90f0ea..57be24c0cc1 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -1613,7 +1613,7 @@ mXactCachePut(MultiXactId multi, int nmembers, MultiXactMember *members)
qsort(entry->members, nmembers, sizeof(MultiXactMember), mxactMemberComparator);
dlist_push_head(&MXactCache, &entry->node);
- if (MXactCacheMembers++ >= MAX_CACHE_ENTRIES)
+ if (MXactCacheMembers++ >= multixact_local_cache_entries)
{
dlist_node *node;
mXactCacheEnt *entry;
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 6ab82168398..9ca71933dcc 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -149,3 +149,5 @@ int VacuumCostBalance = 0; /* working state for vacuum */
bool VacuumCostActive = false;
double vacuum_cleanup_index_scale_factor;
+
+int multixact_local_cache_entries = 256;
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index a62d64eaa47..d667578cc33 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -2257,6 +2257,16 @@ static struct config_int ConfigureNamesInt[] =
NULL, NULL, NULL
},
+ {
+ {"multixact_local_cache_entries", PGC_SUSET, RESOURCES_MEM,
+ gettext_noop("Sets the number of cached MultiXact by backend."),
+ NULL
+ },
+ &multixact_local_cache_entries,
+ 256, 2, INT_MAX / 2,
+ NULL, NULL, NULL
+ },
+
{
{"temp_buffers", PGC_USERSET, RESOURCES_MEM,
gettext_noop("Sets the maximum number of temporary buffers used by each session."),
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e33523984..01af61c963a 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -162,6 +162,8 @@ extern PGDLLIMPORT int MaxConnections;
extern PGDLLIMPORT int max_worker_processes;
extern PGDLLIMPORT int max_parallel_workers;
+extern PGDLLIMPORT int multixact_local_cache_entries;
+
extern PGDLLIMPORT int MyProcPid;
extern PGDLLIMPORT pg_time_t MyStartTime;
extern PGDLLIMPORT TimestampTz MyStartTimestamp;
--
2.14.3
[application/octet-stream] v6-0003-Add-conditional-variable-to-wait-for-next-MultXact.patch (4.4K, ../CAPpHfdsUtSGxRrKn65F_wrE66sNztNY4TpDGDHh2kvAZZDOMqA@mail.gmail.com/4-v6-0003-Add-conditional-variable-to-wait-for-next-MultXact.patch)
download | inline diff:
From da9cc973a4e7d568466b1c4de15479f707ad04f6 Mon Sep 17 00:00:00 2001
From: Alexander Korotkov <[email protected]>
Date: Mon, 26 Oct 2020 01:55:31 +0300
Subject: [PATCH 3/3] Add conditional variable to wait for next MultXact offset
in corner case
GetMultiXactIdMembers() has a corner case, when the next multixact offset is
not yet set. In this case GetMultiXactIdMembers() has to sleep till this offset
is set. Currently the sleeping is implemented in naive way using pg_sleep()
and retry. This commit implements sleeping with conditional variable, which
provides more efficient way for waiting till the event.
Discussion: https://postgr.es/m/a7f1c4e1-1015-92a4-2bd4-6736bd13d03e%40postgrespro.ru#c496c4e75fc0605094a0e1f763e6a6ec
Author: Andrey Borodin
Reviewed-by: Kyotaro Horiguchi, Daniel Gustafsson
Reviewed-by: Anastasia Lubennikova, Alexander Korotkov
---
src/backend/access/transam/multixact.c | 35 ++++++++++++++++++++++++++++++++--
src/backend/postmaster/pgstat.c | 2 ++
src/include/pgstat.h | 1 +
3 files changed, 36 insertions(+), 2 deletions(-)
diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index 57be24c0cc1..70d977cba33 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -82,6 +82,7 @@
#include "lib/ilist.h"
#include "miscadmin.h"
#include "pg_trace.h"
+#include "pgstat.h"
#include "postmaster/autovacuum.h"
#include "storage/lmgr.h"
#include "storage/pmsignal.h"
@@ -233,6 +234,13 @@ typedef struct MultiXactStateData
/* support for members anti-wraparound measures */
MultiXactOffset offsetStopLimit; /* known if oldestOffsetKnown */
+ /*
+ * Conditional variable for waiting till the filling of the next multixact
+ * will be finished. See GetMultiXactIdMembers() and RecordNewMultiXact()
+ * for details.
+ */
+ ConditionVariable nextoffCV;
+
/*
* Per-backend data starts here. We have two arrays stored in the area
* immediately following the MultiXactStateData struct. Each is indexed by
@@ -892,6 +900,14 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
/* Exchange our lock */
LWLockRelease(MultiXactOffsetSLRULock);
+ /*
+ * Let everybody know the offset of this mxid is recorded now. The
+ * waiters are waiting for the offset of the mxid next of the target to
+ * know the number of members of the target mxid, so we don't need to wait
+ * for members of this mxid are recorded.
+ */
+ ConditionVariableBroadcast(&MultiXactState->nextoffCV);
+
LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
prev_pageno = -1;
@@ -1389,9 +1405,23 @@ retry:
if (nextMXOffset == 0)
{
/* Corner case 2: next multixact is still being filled in */
+
+ /*
+ * The recorder of the next mxid is just before writing the
+ * offset. Wait for the offset to be written.
+ */
+ ConditionVariablePrepareToSleep(&MultiXactState->nextoffCV);
+
+ /*
+ * We don't have to recheck if multixact was filled in during
+ * ConditionVariablePrepareToSleep(), because we were holding
+ * MultiXactOffsetSLRULock.
+ */
LWLockRelease(MultiXactOffsetSLRULock);
- CHECK_FOR_INTERRUPTS();
- pg_usleep(1000L);
+
+ ConditionVariableSleep(&MultiXactState->nextoffCV,
+ WAIT_EVENT_WAIT_NEXT_MXMEMBERS);
+ ConditionVariableCancelSleep();
goto retry;
}
@@ -1873,6 +1903,7 @@ MultiXactShmemInit(void)
/* Make sure we zero out the per-backend state */
MemSet(MultiXactState, 0, SHARED_MULTIXACT_STATE_SIZE);
+ ConditionVariableInit(&MultiXactState->nextoffCV);
}
else
Assert(found);
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 822f0ebc628..b99398a97e9 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -4020,6 +4020,8 @@ pgstat_get_wait_ipc(WaitEventIPC w)
break;
case WAIT_EVENT_XACT_GROUP_UPDATE:
event_name = "XactGroupUpdate";
+ case WAIT_EVENT_WAIT_NEXT_MXMEMBERS:
+ event_name = "MultiXactWaitNextMembers";
break;
/* no default case, so that compiler will warn */
}
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index a821ff4f158..75ede141ab7 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -952,6 +952,7 @@ typedef enum
WAIT_EVENT_REPLICATION_SLOT_DROP,
WAIT_EVENT_SAFE_SNAPSHOT,
WAIT_EVENT_SYNC_REP,
+ WAIT_EVENT_WAIT_NEXT_MXMEMBERS,
WAIT_EVENT_XACT_GROUP_UPDATE
} WaitEventIPC;
--
2.14.3
view thread (81+ messages) latest in thread
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: [email protected]
Cc: [email protected], [email protected], [email protected], [email protected], [email protected]
Subject: Re: MultiXact\SLRU buffers configuration
In-Reply-To: <CAPpHfdsUtSGxRrKn65F_wrE66sNztNY4TpDGDHh2kvAZZDOMqA@mail.gmail.com>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox