[prev in list] [next in list] [prev in thread] [next in thread]
List: pgsql-hackers
Subject: Re: SLRU optimization - configurable buffer pool and partitioning the SLRU lock
From: Alvaro Herrera <alvherre () alvh ! no-ip ! org>
Date: 2024-01-31 23:31:34
Message-ID: 202401312331.dozxsouzpsvd () alvherre ! pgsql
[Download RAW message or body]
On 2024-Jan-29, Dilip Kumar wrote:
> Thank you for working on this. There is one thing that I feel is
> problematic. We have kept the allowed values for these GUCs to be in
> multiple of SLRU_BANK_SIZE i.e. 16 and that's the reason the min
> values were changed to 16 but in this refactoring patch for some of
> the buffers you have changed that to 8 so I think that's not good.
Oh, absolutely, you're right. Restored the minimum to 16.
So, here's the patchset as two pieces. 0001 converts
SlruSharedData->latest_page_number to use atomics. I don't see any
reason to mix this in with the rest of the patch, and though it likely
won't have any performance advantage by itself (since the lock
acquisition is pretty much the same), it seems better to get it in ahead
of the rest -- I think that simplifies matters for the second patch,
which is large enough.
So, 0002 introduces the rest of the feature. I removed use of banklocks
in a different amount as banks, and I made commit_ts use a longer
lwlock acquisition at truncation time, rather than forcing all-lwlock
acquisition.
The more I look at 0002, the more I notice that some comments need badly
updated, so please don't read too much into it yet. But I wanted to
post it anyway for archives and cfbot purposes.
--
Álvaro Herrera PostgreSQL Developer — https://www.EnterpriseDB.com/
["0001-Use-atomics-for-SlruSharedData-latest_page_number.patch" (text/x-diff)]
From 464a996b85c333ffc781086263c2e491758b248f Mon Sep 17 00:00:00 2001
From: Alvaro Herrera <alvherre@alvh.no-ip.org>
Date: Wed, 31 Jan 2024 12:27:51 +0100
Subject: [PATCH 1/2] Use atomics for SlruSharedData->latest_page_number
---
src/backend/access/transam/clog.c | 7 ++----
src/backend/access/transam/commit_ts.c | 7 +++---
src/backend/access/transam/multixact.c | 30 ++++++++++++++++----------
src/backend/access/transam/slru.c | 19 ++++++++++------
src/include/access/slru.h | 5 ++++-
5 files changed, 41 insertions(+), 27 deletions(-)
diff --git a/src/backend/access/transam/clog.c b/src/backend/access/transam/clog.c
index f6e7da7ffc..245fd21c8d 100644
--- a/src/backend/access/transam/clog.c
+++ b/src/backend/access/transam/clog.c
@@ -766,14 +766,11 @@ StartupCLOG(void)
TransactionId xid = XidFromFullTransactionId(TransamVariables->nextXid);
int64 pageno = TransactionIdToPage(xid);
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
-
/*
* Initialize our idea of the latest page number.
*/
- XactCtl->shared->latest_page_number = pageno;
-
- LWLockRelease(XactSLRULock);
+ pg_atomic_init_u64(&XactCtl->shared->latest_page_number, pageno);
+ pg_write_barrier();
}
/*
diff --git a/src/backend/access/transam/commit_ts.c b/src/backend/access/transam/commit_ts.c
index 61b82385f3..f68705989d 100644
--- a/src/backend/access/transam/commit_ts.c
+++ b/src/backend/access/transam/commit_ts.c
@@ -689,9 +689,7 @@ ActivateCommitTs(void)
/*
* Re-Initialize our idea of the latest page number.
*/
- LWLockAcquire(CommitTsSLRULock, LW_EXCLUSIVE);
- CommitTsCtl->shared->latest_page_number = pageno;
- LWLockRelease(CommitTsSLRULock);
+ pg_atomic_init_u64(&CommitTsCtl->shared->latest_page_number, pageno);
/*
* If CommitTs is enabled, but it wasn't in the previous server run, we
@@ -1006,7 +1004,8 @@ commit_ts_redo(XLogReaderState *record)
* During XLOG replay, latest_page_number isn't set up yet; insert a
* suitable value to bypass the sanity test in SimpleLruTruncate.
*/
- CommitTsCtl->shared->latest_page_number = trunc->pageno;
+ pg_atomic_write_u64(&CommitTsCtl->shared->latest_page_number,
+ trunc->pageno);
SimpleLruTruncate(CommitTsCtl, trunc->pageno);
}
diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index 59523be901..a886c29892 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -2017,13 +2017,17 @@ StartupMultiXact(void)
* Initialize offset's idea of the latest page number.
*/
pageno = MultiXactIdToOffsetPage(multi);
- MultiXactOffsetCtl->shared->latest_page_number = pageno;
+ pg_atomic_init_u64(&MultiXactOffsetCtl->shared->latest_page_number,
+ pageno);
/*
* Initialize member's idea of the latest page number.
*/
pageno = MXOffsetToMemberPage(offset);
- MultiXactMemberCtl->shared->latest_page_number = pageno;
+ pg_atomic_init_u64(&MultiXactMemberCtl->shared->latest_page_number,
+ pageno);
+
+ pg_write_barrier();
}
/*
@@ -2047,14 +2051,15 @@ TrimMultiXact(void)
oldestMXactDB = MultiXactState->oldestMultiXactDB;
LWLockRelease(MultiXactGenLock);
- /* Clean up offsets state */
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
-
/*
* (Re-)Initialize our idea of the latest page number for offsets.
*/
pageno = MultiXactIdToOffsetPage(nextMXact);
- MultiXactOffsetCtl->shared->latest_page_number = pageno;
+ pg_atomic_write_u64(&MultiXactOffsetCtl->shared->latest_page_number,
+ pageno);
+
+ /* Clean up offsets state */
+ LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
/*
* Zero out the remainder of the current offsets page. See notes in
@@ -2081,14 +2086,16 @@ TrimMultiXact(void)
LWLockRelease(MultiXactOffsetSLRULock);
- /* And the same for members */
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
-
/*
+ * And the same for members.
+ *
* (Re-)Initialize our idea of the latest page number for members.
*/
pageno = MXOffsetToMemberPage(offset);
- MultiXactMemberCtl->shared->latest_page_number = pageno;
+ pg_atomic_write_u64(&MultiXactMemberCtl->shared->latest_page_number,
+ pageno);
+
+ LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
/*
* Zero out the remainder of the current members page. See notes in
@@ -3333,7 +3340,8 @@ multixact_redo(XLogReaderState *record)
* SimpleLruTruncate.
*/
pageno = MultiXactIdToOffsetPage(xlrec.endTruncOff);
- MultiXactOffsetCtl->shared->latest_page_number = pageno;
+ pg_atomic_write_u64(&MultiXactOffsetCtl->shared->latest_page_number,
+ pageno);
PerformOffsetsTruncation(xlrec.startTruncOff, xlrec.endTruncOff);
LWLockRelease(MultiXactTruncationLock);
diff --git a/src/backend/access/transam/slru.c b/src/backend/access/transam/slru.c
index 9ac4790f16..57949fbab4 100644
--- a/src/backend/access/transam/slru.c
+++ b/src/backend/access/transam/slru.c
@@ -17,7 +17,8 @@
* per-buffer LWLocks that synchronize I/O for each buffer. The control lock
* must be held to examine or modify any shared state. A process that is
* reading in or writing out a page buffer does not hold the control lock,
- * only the per-buffer lock for the buffer it is working on.
+ * only the per-buffer lock for the buffer it is working on. One exception
+ * is latest_page_number, which is read and written using atomic ops.
*
* "Holding the control lock" means exclusive lock in all cases except for
* SimpleLruReadPage_ReadOnly(); see comments for SlruRecentlyUsed() for
@@ -330,7 +331,8 @@ SimpleLruZeroPage(SlruCtl ctl, int64 pageno)
SimpleLruZeroLSNs(ctl, slotno);
/* Assume this page is now the latest active page */
- shared->latest_page_number = pageno;
+ pg_atomic_write_u64(&shared->latest_page_number, pageno);
+ pg_write_barrier();
/* update the stats counter of zeroed pages */
pgstat_count_slru_page_zeroed(shared->slru_stats_idx);
@@ -1113,8 +1115,11 @@ SlruSelectLRUPage(SlruCtl ctl, int64 pageno)
shared->page_lru_count[slotno] = cur_count;
this_delta = 0;
}
+
this_page_number = shared->page_number[slotno];
- if (this_page_number == shared->latest_page_number)
+ pg_read_barrier();
+ if (this_page_number ==
+ pg_atomic_read_u64(&shared->latest_page_number))
continue;
if (shared->page_status[slotno] == SLRU_PAGE_VALID)
{
@@ -1270,10 +1275,12 @@ SimpleLruTruncate(SlruCtl ctl, int64 cutoffPage)
restart:
/*
- * While we are holding the lock, make an important safety check: the
- * current endpoint page must not be eligible for removal.
+ * An important safety check: the current endpoint page must not be
+ * eligible for removal.
*/
- if (ctl->PagePrecedes(shared->latest_page_number, cutoffPage))
+ pg_read_barrier();
+ if (ctl->PagePrecedes(pg_atomic_read_u64(&shared->latest_page_number),
+ cutoffPage))
{
LWLockRelease(shared->ControlLock);
ereport(LOG,
diff --git a/src/include/access/slru.h b/src/include/access/slru.h
index b05f6bc71d..2109488654 100644
--- a/src/include/access/slru.h
+++ b/src/include/access/slru.h
@@ -49,6 +49,9 @@ typedef enum
/*
* Shared-memory state
+ *
+ * ControlLock is used to protect access to the other fields, except
+ * latest_page_number, which uses atomics; see comment in slru.c.
*/
typedef struct SlruSharedData
{
@@ -95,7 +98,7 @@ typedef struct SlruSharedData
* this is not critical data, since we use it only to avoid swapping out
* the latest page.
*/
- int64 latest_page_number;
+ pg_atomic_uint64 latest_page_number;
/* SLRU's index for statistics purposes (might not be unique) */
int slru_stats_idx;
--
2.39.2
["0002-Enlarge-SLRU-buffer-caches-and-improve-concurrency.patch" (text/x-diff)]
From 1b7c1f628a5f67260eded1b4b22930913d61f43f Mon Sep 17 00:00:00 2001
From: Alvaro Herrera <alvherre@alvh.no-ip.org>
Date: Wed, 31 Jan 2024 17:06:19 +0100
Subject: [PATCH 2/2] Enlarge SLRU buffer caches and improve concurrency
---
doc/src/sgml/config.sgml | 139 ++++++++++
src/backend/access/transam/clog.c | 224 +++++++++++----
src/backend/access/transam/commit_ts.c | 88 ++++--
src/backend/access/transam/multixact.c | 190 +++++++++----
src/backend/access/transam/slru.c | 257 +++++++++++++-----
src/backend/access/transam/subtrans.c | 103 +++++--
src/backend/commands/async.c | 61 +++--
src/backend/storage/lmgr/lwlock.c | 9 +-
src/backend/storage/lmgr/lwlocknames.txt | 14 +-
src/backend/storage/lmgr/predicate.c | 38 ++-
.../utils/activity/wait_event_names.txt | 15 +-
src/backend/utils/init/globals.c | 9 +
src/backend/utils/misc/guc_tables.c | 78 ++++++
src/backend/utils/misc/postgresql.conf.sample | 9 +
src/include/access/clog.h | 1 -
src/include/access/commit_ts.h | 1 -
src/include/access/multixact.h | 4 -
src/include/access/slru.h | 81 +++++-
src/include/access/subtrans.h | 3 -
src/include/commands/async.h | 5 -
src/include/miscadmin.h | 8 +
src/include/storage/lwlock.h | 7 +
src/include/storage/predicate.h | 4 -
src/include/utils/guc_hooks.h | 11 +
src/test/modules/test_slru/test_slru.c | 35 +--
25 files changed, 1088 insertions(+), 306 deletions(-)
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 61038472c5..3e3119865a 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -2006,6 +2006,145 @@ include_dir 'conf.d'
</listitem>
</varlistentry>
+ <varlistentry id="guc-commit-timestamp-buffers" \
xreflabel="commit_timestamp_buffers"> + \
<term><varname>commit_timestamp_buffers</varname> (<type>integer</type>) + \
<indexterm> + <primary><varname>commit_timestamp_buffers</varname> \
configuration parameter</primary> + </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of memory to use to cache the contents of
+ <literal>pg_commit_ts</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>0</literal>, which requests
+ <varname>shared_buffers</varname>/512 up to 1024 blocks,
+ but not fewer than 16 blocks.
+ This parameter can only be set at server start.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry id="guc-multixact-members-buffers" \
xreflabel="multixact_members_buffers"> + \
<term><varname>multixact_members_buffers</varname> (<type>integer</type>) + \
<indexterm> + <primary><varname>multixact_members_buffers</varname> \
configuration parameter</primary> + </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of shared memory to use to cache the contents
+ of <literal>pg_multixact/members</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>32</literal>.
+ This parameter can only be set at server start.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry id="guc-multixact-offsets-buffers" \
xreflabel="multixact_offsets_buffers"> + \
<term><varname>multixact_offsets_buffers</varname> (<type>integer</type>) + \
<indexterm> + <primary><varname>multixact_offsets_buffers</varname> \
configuration parameter</primary> + </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of shared memory to use to cache the contents
+ of <literal>pg_multixact/offsets</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>16</literal>.
+ This parameter can only be set at server start.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry id="guc-notify-buffers" xreflabel="notify_buffers">
+ <term><varname>notify_buffers</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>notify_buffers</varname> configuration parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of shared memory to use to cache the contents
+ of <literal>pg_notify</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>16</literal>.
+ This parameter can only be set at server start.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry id="guc-serializable-buffers" xreflabel="serializable_buffers">
+ <term><varname>serializable_buffers</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>serializable_buffers</varname> configuration \
parameter</primary> + </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of shared memory to use to cache the contents
+ of <literal>pg_serial</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>32</literal>.
+ This parameter can only be set at server start.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry id="guc-subtransaction-buffers" \
xreflabel="subtransaction_buffers"> + \
<term><varname>subtransaction_buffers</varname> (<type>integer</type>) + \
<indexterm> + <primary><varname>subtransaction_buffers</varname> configuration \
parameter</primary> + </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of shared memory to use to cache the contents
+ of <literal>pg_subtrans</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>0</literal>, which requests
+ <varname>shared_buffers</varname>/512 up to 1024 blocks,
+ but not fewer than 16 blocks.
+ This parameter can only be set at server start.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry id="guc-transaction-buffers" xreflabel="transaction_buffers">
+ <term><varname>transaction_buffers</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>transaction_buffers</varname> configuration \
parameter</primary> + </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the amount of shared memory to use to cache the contents
+ of <literal>pg_xact</literal> (see
+ <xref linkend="pgdata-contents-table"/>).
+ If this value is specified without units, it is taken as blocks,
+ that is <symbol>BLCKSZ</symbol> bytes, typically 8kB.
+ The default value is <literal>0</literal>, which requests
+ <varname>shared_buffers</varname>/512 up to 1024 blocks,
+ but not fewer than 16 blocks.
+ This parameter can only be set at server start.
+ </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/clog.c b/src/backend/access/transam/clog.c
index 245fd21c8d..01e153ee14 100644
--- a/src/backend/access/transam/clog.c
+++ b/src/backend/access/transam/clog.c
@@ -43,6 +43,7 @@
#include "pgstat.h"
#include "storage/proc.h"
#include "storage/sync.h"
+#include "utils/guc_hooks.h"
/*
* Defines for CLOG page sizes. A page is the same BLCKSZ as is used
@@ -62,6 +63,15 @@
#define CLOG_XACTS_PER_PAGE (BLCKSZ * CLOG_XACTS_PER_BYTE)
#define CLOG_XACT_BITMASK ((1 << CLOG_BITS_PER_XACT) - 1)
+/*
+ * Because space used in CLOG by each transaction is so small, we place a
+ * smaller limit on the number of CLOG buffers than SLRU allows. No other
+ * SLRU needs this.
+ */
+#define CLOG_MAX_ALLOWED_BUFFERS \
+ Min(SLRU_MAX_ALLOWED_BUFFERS, \
+ (((MaxTransactionId / 2) + (CLOG_XACTS_PER_PAGE - 1)) / CLOG_XACTS_PER_PAGE))
+
/*
* Although we return an int64 the actual value can't currently exceed
@@ -284,15 +294,20 @@ TransactionIdSetPageStatus(TransactionId xid, int nsubxids,
XLogRecPtr lsn, int64 pageno,
bool all_xact_same_page)
{
+ LWLock *lock;
+
/* Can't use group update when PGPROC overflows. */
StaticAssertDecl(THRESHOLD_SUBTRANS_CLOG_OPT <= PGPROC_MAX_CACHED_SUBXIDS,
"group clog threshold less than PGPROC cached subxids");
+ /* Get the SLRU bank lock for the page we are going to access. */
+ lock = SimpleLruGetBankLock(XactCtl, pageno);
+
/*
- * When there is contention on XactSLRULock, we try to group multiple
- * updates; a single leader process will perform transaction status
- * updates for multiple backends so that the number of times XactSLRULock
- * needs to be acquired is reduced.
+ * When there is contention on the SLRU bank lock we need, we try to group
+ * multiple updates; a single leader process will perform transaction
+ * status updates for multiple backends so that the number of times the
+ * bank lock needs to be acquired is reduced.
*
* For this optimization to be safe, the XID and subxids in MyProc must be
* the same as the ones for which we're setting the status. Check that
@@ -310,17 +325,17 @@ TransactionIdSetPageStatus(TransactionId xid, int nsubxids,
nsubxids * sizeof(TransactionId)) == 0))
{
/*
- * If we can immediately acquire XactSLRULock, we update the status of
- * our own XID and release the lock. If not, try use group XID
- * update. If that doesn't work out, fall back to waiting for the
- * lock to perform an update for this transaction only.
+ * If we can immediately acquire the lock, we update the status of our
+ * own XID and release the lock. If not, try use group XID update. If
+ * that doesn't work out, fall back to waiting for the lock to perform
+ * an update for this transaction only.
*/
- if (LWLockConditionalAcquire(XactSLRULock, LW_EXCLUSIVE))
+ if (LWLockConditionalAcquire(lock, LW_EXCLUSIVE))
{
/* Got the lock without waiting! Do the update. */
TransactionIdSetPageStatusInternal(xid, nsubxids, subxids, status,
lsn, pageno);
- LWLockRelease(XactSLRULock);
+ LWLockRelease(lock);
return;
}
else if (TransactionGroupUpdateXidStatus(xid, status, lsn, pageno))
@@ -333,10 +348,10 @@ TransactionIdSetPageStatus(TransactionId xid, int nsubxids,
}
/* Group update not applicable, or couldn't accept this page number. */
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
TransactionIdSetPageStatusInternal(xid, nsubxids, subxids, status,
lsn, pageno);
- LWLockRelease(XactSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -355,7 +370,8 @@ TransactionIdSetPageStatusInternal(TransactionId xid, int \
nsubxids, Assert(status == TRANSACTION_STATUS_COMMITTED ||
status == TRANSACTION_STATUS_ABORTED ||
(status == TRANSACTION_STATUS_SUB_COMMITTED && !TransactionIdIsValid(xid)));
- Assert(LWLockHeldByMeInMode(XactSLRULock, LW_EXCLUSIVE));
+ Assert(LWLockHeldByMeInMode(SimpleLruGetBankLock(XactCtl, pageno),
+ LW_EXCLUSIVE));
/*
* If we're doing an async commit (ie, lsn is valid), then we must wait
@@ -406,14 +422,15 @@ TransactionIdSetPageStatusInternal(TransactionId xid, int \
nsubxids, }
/*
- * When we cannot immediately acquire XactSLRULock in exclusive mode at
+ * Subroutine for TransactionIdSetPageStatus, q.v.
+ *
+ * When we cannot immediately acquire the SLRU bank lock in exclusive mode at
* commit time, add ourselves to a list of processes that need their XIDs
* status update. The first process to add itself to the list will acquire
- * XactSLRULock in exclusive mode and set transaction status as required
- * on behalf of all group members. This avoids a great deal of contention
- * around XactSLRULock when many processes are trying to commit at once,
- * since the lock need not be repeatedly handed off from one committing
- * process to the next.
+ * the lock in exclusive mode and set transaction status as required on behalf
+ * of all group members. This avoids a great deal of contention when many
+ * processes are trying to commit at once, since the lock need not be
+ * repeatedly handed off from one committing process to the next.
*
* Returns true when transaction status has been updated in clog; returns
* false if we decided against applying the optimization because the page
@@ -427,13 +444,15 @@ TransactionGroupUpdateXidStatus(TransactionId xid, XidStatus \
status, PGPROC *proc = MyProc;
uint32 nextidx;
uint32 wakeidx;
+ int prevpageno;
+ LWLock *prevlock = NULL;
/* We should definitely have an XID whose status needs to be updated. */
Assert(TransactionIdIsValid(xid));
/*
- * Add ourselves to the list of processes needing a group XID status
- * update.
+ * Prepare to add ourselves to the list of processes needing a group XID
+ * status update.
*/
proc->clogGroupMember = true;
proc->clogGroupMemberXid = xid;
@@ -441,6 +460,41 @@ TransactionGroupUpdateXidStatus(TransactionId xid, XidStatus \
status, proc->clogGroupMemberPage = pageno;
proc->clogGroupMemberLsn = lsn;
+ /*
+ * The underlying SLRU is using bank-wise lock so it is possible that here
+ * we might get requesters who are contending on different SLRU-bank
+ * locks. But in the group, we try to only add the requesters who want to
+ * update the same page i.e. they would be requesting for the same
+ * SLRU-bank lock as well. The main reason for now allowing requesters of
+ * different pages together is 1) Once the leader acquires the lock they
+ * don't need to fetch multiple pages and do multiple I/O under the same
+ * lock 2) The leader need not switch the SLRU-bank lock if the different
+ * pages are from different SLRU banks 3) And the most important reason is
+ * that most of the time the contention will occur in high concurrent OLTP
+ * workload is going on and at that time most of the transactions would be
+ * generated during the same time and most of them would fall in same clog
+ * page as each page can hold status of 32k transactions. However, there
+ * is an exception where in some extreme conditions we might get different
+ * page requests added in the same group but we have handled that by
+ * switching the bank lock, although that is not the most performant way
+ * that's not the common case either so we are fine with that.
+ *
+ * Also to be noted that unless the leader of the current group does not
+ * get the lock we don't clear the 'procglobal->clogGroupFirst' that means
+ * concurrently if we get the requesters for different SLRU pages then
+ * those will have to go for the normal update instead of group update and
+ * that's fine as that is not the common case. As soon as the leader of
+ * the current group gets the lock for the required bank that time we
+ * clear this value and now other requesters (which might want to update a
+ * different page and that might fall into the different bank as well) are
+ * allowed to form a new group as the first group is now detached. So if
+ * the new group has a request for a different SLRU-bank lock then the
+ * group leader of this group might also get the lock while the first
+ * group is performing the update and these two groups can perform the
+ * group update concurrently but it is completely safe as these two
+ * leaders are operating on completely different SLRU pages and they both
+ * are holding their respective SLRU locks.
+ */
nextidx = pg_atomic_read_u32(&procglobal->clogGroupFirst);
while (true)
@@ -507,8 +561,17 @@ TransactionGroupUpdateXidStatus(TransactionId xid, XidStatus \
status, return true;
}
- /* We are the leader. Acquire the lock on behalf of everyone. */
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
+ /*
+ * Acquire the SLRU bank lock for the first page in the group before we
+ * close this group by setting procglobal->clogGroupFirst as
+ * INVALID_PGPROCNO so that we do not close the new entries to the group
+ * even before getting the lock and losing whole purpose of the group
+ * update.
+ */
+ nextidx = pg_atomic_read_u32(&procglobal->clogGroupFirst);
+ prevpageno = ProcGlobal->allProcs[nextidx].clogGroupMemberPage;
+ prevlock = SimpleLruGetBankLock(XactCtl, prevpageno);
+ LWLockAcquire(prevlock, LW_EXCLUSIVE);
/*
* Now that we've got the lock, clear the list of processes waiting for
@@ -525,6 +588,37 @@ TransactionGroupUpdateXidStatus(TransactionId xid, XidStatus \
status, while (nextidx != INVALID_PGPROCNO)
{
PGPROC *nextproc = &ProcGlobal->allProcs[nextidx];
+ int thispageno = nextproc->clogGroupMemberPage;
+
+ /*
+ * If the SLRU bank lock for the current page is not the same as that
+ * of the last page then we need to release the lock on the previous
+ * bank and acquire the lock on the bank for the page we are going to
+ * update now.
+ *
+ * Although on the best effort basis we try that all the requests
+ * within a group are for the same clog page there are some
+ * possibilities that there are request for more than one page in the
+ * same group (for details refer to the comment in the previous while
+ * loop). That scenario might not be very performant because while
+ * switching the lock the group leader might need to wait on the new
+ * lock if the pages are from different SLRU bank but it is safe
+ * because a) we are releasing the old lock before acquiring the new
+ * lock so there is should not be any deadlock situation b) and, we
+ * are always modifying the page under the correct SLRU lock.
+ */
+ if (thispageno != prevpageno)
+ {
+ LWLock *lock = SimpleLruGetBankLock(XactCtl, thispageno);
+
+ if (prevlock != lock)
+ {
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ }
+ prevlock = lock;
+ prevpageno = thispageno;
+ }
/*
* Transactions with more than THRESHOLD_SUBTRANS_CLOG_OPT sub-XIDs
@@ -544,7 +638,8 @@ TransactionGroupUpdateXidStatus(TransactionId xid, XidStatus \
status, }
/* We're done with the lock now. */
- LWLockRelease(XactSLRULock);
+ if (prevlock != NULL)
+ LWLockRelease(prevlock);
/*
* Now that we've released the lock, go back and wake everybody up. We
@@ -573,7 +668,7 @@ TransactionGroupUpdateXidStatus(TransactionId xid, XidStatus \
status, /*
* Sets the commit status of a single transaction.
*
- * Must be called with XactSLRULock held
+ * Caller must hold the corresponding SLRU bank lock, will be held at exit.
*/
static void
TransactionIdSetStatusBit(TransactionId xid, XidStatus status, XLogRecPtr lsn, int \
slotno) @@ -584,6 +679,11 @@ TransactionIdSetStatusBit(TransactionId xid, XidStatus \
status, XLogRecPtr lsn, i char byteval;
char curval;
+ Assert(XactCtl->shared->page_number[slotno] == TransactionIdToPage(xid));
+ Assert(LWLockHeldByMeInMode(SimpleLruGetBankLock(XactCtl,
+ XactCtl->shared->page_number[slotno]),
+ LW_EXCLUSIVE));
+
byteptr = XactCtl->shared->page_buffer[slotno] + byteno;
curval = (*byteptr >> bshift) & CLOG_XACT_BITMASK;
@@ -665,7 +765,7 @@ TransactionIdGetStatus(TransactionId xid, XLogRecPtr *lsn)
lsnindex = GetLSNIndex(slotno, xid);
*lsn = XactCtl->shared->group_lsn[lsnindex];
- LWLockRelease(XactSLRULock);
+ LWLockRelease(SimpleLruGetBankLock(XactCtl, pageno));
return status;
}
@@ -673,23 +773,18 @@ TransactionIdGetStatus(TransactionId xid, XLogRecPtr *lsn)
/*
* Number of shared CLOG buffers.
*
- * On larger multi-processor systems, it is possible to have many CLOG page
- * requests in flight at one time which could lead to disk access for CLOG
- * page if the required page is not found in memory. Testing revealed that we
- * can get the best performance by having 128 CLOG buffers, more than that it
- * doesn't improve performance.
- *
- * Unconditionally keeping the number of CLOG buffers to 128 did not seem like
- * a good idea, because it would increase the minimum amount of shared memory
- * required to start, which could be a problem for people running very small
- * configurations. The following formula seems to represent a reasonable
- * compromise: people with very low values for shared_buffers will get fewer
- * CLOG buffers as well, and everyone else will get 128.
+ * If asked to autotune, we use 2MB for every 1GB of shared buffers, up to 8MB,
+ * but always at least 16 buffers. Otherwise just cap the configured amount to
+ * be between 16 and the maximum allowed.
*/
-Size
+static int
CLOGShmemBuffers(void)
{
- return Min(128, Max(4, NBuffers / 512));
+ /* auto-tune based on shared buffers */
+ if (transaction_buffers == 0)
+ return Min(1024, Max(16, NBuffers / 512));
+
+ return Min(Max(16, transaction_buffers), CLOG_MAX_ALLOWED_BUFFERS);
}
/*
@@ -704,13 +799,36 @@ CLOGShmemSize(void)
void
CLOGShmemInit(void)
{
+ /* If auto-tuning is requested, now is the time to do it */
+ if (transaction_buffers == 0)
+ {
+ char buf[32];
+
+ snprintf(buf, sizeof(buf), "%d", CLOGShmemBuffers());
+ SetConfigOption("transaction_buffers", buf, PGC_POSTMASTER,
+ PGC_S_DYNAMIC_DEFAULT);
+ if (transaction_buffers == 0) /* failed to apply it? */
+ SetConfigOption("transaction_buffers", buf, PGC_POSTMASTER,
+ PGC_S_OVERRIDE);
+ }
+ Assert(transaction_buffers != 0);
+
XactCtl->PagePrecedes = CLOGPagePrecedes;
SimpleLruInit(XactCtl, "Xact", CLOGShmemBuffers(), CLOG_LSNS_PER_PAGE,
- XactSLRULock, "pg_xact", LWTRANCHE_XACT_BUFFER,
- SYNC_HANDLER_CLOG, false);
+ "pg_xact", LWTRANCHE_XACT_BUFFER,
+ LWTRANCHE_XACT_SLRU, SYNC_HANDLER_CLOG, false);
SlruPagePrecedesUnitTests(XactCtl, CLOG_XACTS_PER_PAGE);
}
+/*
+ * GUC check_hook for transaction_buffers
+ */
+bool
+check_transaction_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("transaction_buffers", newval);
+}
+
/*
* This func must be called ONCE on system install. It creates
* the initial CLOG segment. (The CLOG directory is assumed to
@@ -721,8 +839,9 @@ void
BootStrapCLOG(void)
{
int slotno;
+ LWLock *lock = SimpleLruGetBankLock(XactCtl, 0);
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Create and zero the first page of the commit log */
slotno = ZeroCLOGPage(0, false);
@@ -731,7 +850,7 @@ BootStrapCLOG(void)
SimpleLruWritePage(XactCtl, slotno);
Assert(!XactCtl->shared->page_dirty[slotno]);
- LWLockRelease(XactSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -781,8 +900,9 @@ TrimCLOG(void)
{
TransactionId xid = XidFromFullTransactionId(TransamVariables->nextXid);
int64 pageno = TransactionIdToPage(xid);
+ LWLock *lock = SimpleLruGetBankLock(XactCtl, pageno);
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/*
* Zero out the remainder of the current clog page. Under normal
@@ -814,7 +934,7 @@ TrimCLOG(void)
XactCtl->shared->page_dirty[slotno] = true;
}
- LWLockRelease(XactSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -846,6 +966,7 @@ void
ExtendCLOG(TransactionId newestXact)
{
int64 pageno;
+ LWLock *lock;
/*
* No work except at first XID of a page. But beware: just after
@@ -856,13 +977,14 @@ ExtendCLOG(TransactionId newestXact)
return;
pageno = TransactionIdToPage(newestXact);
+ lock = SimpleLruGetBankLock(XactCtl, pageno);
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Zero the page and make an XLOG entry about it */
ZeroCLOGPage(pageno, true);
- LWLockRelease(XactSLRULock);
+ LWLockRelease(lock);
}
@@ -1000,16 +1122,18 @@ clog_redo(XLogReaderState *record)
{
int64 pageno;
int slotno;
+ LWLock *lock;
memcpy(&pageno, XLogRecGetData(record), sizeof(pageno));
- LWLockAcquire(XactSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(XactCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = ZeroCLOGPage(pageno, false);
SimpleLruWritePage(XactCtl, slotno);
Assert(!XactCtl->shared->page_dirty[slotno]);
- LWLockRelease(XactSLRULock);
+ LWLockRelease(lock);
}
else if (info == CLOG_TRUNCATE)
{
diff --git a/src/backend/access/transam/commit_ts.c \
b/src/backend/access/transam/commit_ts.c index f68705989d..9590aa3ea0 100644
--- a/src/backend/access/transam/commit_ts.c
+++ b/src/backend/access/transam/commit_ts.c
@@ -33,6 +33,7 @@
#include "pg_trace.h"
#include "storage/shmem.h"
#include "utils/builtins.h"
+#include "utils/guc_hooks.h"
#include "utils/snapmgr.h"
#include "utils/timestamp.h"
@@ -225,10 +226,11 @@ SetXidCommitTsInPage(TransactionId xid, int nsubxids,
TransactionId *subxids, TimestampTz ts,
RepOriginId nodeid, int64 pageno)
{
+ LWLock *lock = SimpleLruGetBankLock(CommitTsCtl, pageno);
int slotno;
int i;
- LWLockAcquire(CommitTsSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = SimpleLruReadPage(CommitTsCtl, pageno, true, xid);
@@ -238,22 +240,25 @@ SetXidCommitTsInPage(TransactionId xid, int nsubxids,
CommitTsCtl->shared->page_dirty[slotno] = true;
- LWLockRelease(CommitTsSLRULock);
+ LWLockRelease(lock);
}
/*
* Sets the commit timestamp of a single transaction.
*
- * Must be called with CommitTsSLRULock held
+ * Caller must hold the correct SLRU bank lock, will be held at exit
*/
static void
TransactionIdSetCommitTs(TransactionId xid, TimestampTz ts,
RepOriginId nodeid, int slotno)
{
- int entryno = TransactionIdToCTsEntry(xid);
+ int entryno;
CommitTimestampEntry entry;
- Assert(TransactionIdIsNormal(xid));
+ if (!TransactionIdIsNormal(xid))
+ return;
+
+ entryno = TransactionIdToCTsEntry(xid);
entry.time = ts;
entry.nodeid = nodeid;
@@ -345,7 +350,7 @@ TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
if (nodeid)
*nodeid = entry.nodeid;
- LWLockRelease(CommitTsSLRULock);
+ LWLockRelease(SimpleLruGetBankLock(CommitTsCtl, pageno));
return *ts != 0;
}
@@ -499,14 +504,18 @@ pg_xact_commit_timestamp_origin(PG_FUNCTION_ARGS)
/*
* Number of shared CommitTS buffers.
*
- * We use a very similar logic as for the number of CLOG buffers (except we
- * scale up twice as fast with shared buffers, and the maximum is twice as
- * high); see comments in CLOGShmemBuffers.
+ * If asked to autotune, we use 2MB for every 1GB of shared buffers, up to 8MB,
+ * but always at least 16 buffers. Otherwise just cap the configured amount to
+ * be between 16 and the maximum allowed.
*/
-Size
+static int
CommitTsShmemBuffers(void)
{
- return Min(256, Max(4, NBuffers / 256));
+ /* auto-tune based on shared buffers */
+ if (commit_timestamp_buffers == 0)
+ return Min(1024, Max(16, NBuffers / 512));
+
+ return Min(Max(16, commit_timestamp_buffers), SLRU_MAX_ALLOWED_BUFFERS);
}
/*
@@ -528,10 +537,24 @@ CommitTsShmemInit(void)
{
bool found;
+ /* If auto-tuning is requested, now is the time to do it */
+ if (commit_timestamp_buffers == 0)
+ {
+ char buf[32];
+
+ snprintf(buf, sizeof(buf), "%d", CommitTsShmemBuffers());
+ SetConfigOption("commit_timestamp_buffers", buf, PGC_POSTMASTER,
+ PGC_S_DYNAMIC_DEFAULT);
+ if (commit_timestamp_buffers == 0) /* failed to apply it? */
+ SetConfigOption("commit_timestamp_buffers", buf, PGC_POSTMASTER,
+ PGC_S_OVERRIDE);
+ }
+ Assert(commit_timestamp_buffers != 0);
+
CommitTsCtl->PagePrecedes = CommitTsPagePrecedes;
SimpleLruInit(CommitTsCtl, "CommitTs", CommitTsShmemBuffers(), 0,
- CommitTsSLRULock, "pg_commit_ts",
- LWTRANCHE_COMMITTS_BUFFER,
+ "pg_commit_ts", LWTRANCHE_COMMITTS_BUFFER,
+ LWTRANCHE_COMMITTS_SLRU,
SYNC_HANDLER_COMMIT_TS,
false);
SlruPagePrecedesUnitTests(CommitTsCtl, COMMIT_TS_XACTS_PER_PAGE);
@@ -553,6 +576,15 @@ CommitTsShmemInit(void)
Assert(found);
}
+/*
+ * GUC check_hook for commit_timestamp_buffers
+ */
+bool
+check_commit_ts_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("commit_timestamp_buffers", newval);
+}
+
/*
* This function must be called ONCE on system install.
*
@@ -715,13 +747,14 @@ ActivateCommitTs(void)
/* Create the current segment file, if necessary */
if (!SimpleLruDoesPhysicalPageExist(CommitTsCtl, pageno))
{
+ LWLock *lock = SimpleLruGetBankLock(CommitTsCtl, pageno);
int slotno;
- LWLockAcquire(CommitTsSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = ZeroCommitTsPage(pageno, false);
SimpleLruWritePage(CommitTsCtl, slotno);
Assert(!CommitTsCtl->shared->page_dirty[slotno]);
- LWLockRelease(CommitTsSLRULock);
+ LWLockRelease(lock);
}
/* Change the activation status in shared memory. */
@@ -760,8 +793,6 @@ DeactivateCommitTs(void)
TransamVariables->oldestCommitTsXid = InvalidTransactionId;
TransamVariables->newestCommitTsXid = InvalidTransactionId;
- LWLockRelease(CommitTsLock);
-
/*
* Remove *all* files. This is necessary so that there are no leftover
* files; in the case where this feature is later enabled after running
@@ -769,10 +800,16 @@ DeactivateCommitTs(void)
* (We can probably tolerate out-of-sequence files, as they are going to
* be overwritten anyway when we wrap around, but it seems better to be
* tidy.)
+ *
+ * Note that we do this with CommitTsLock acquired in exclusive mode.
+ * This is very heavy-handed, but since this routine can only be called
+ * in the replica and should happen very rarely, we don't worry too much
+ * about it. Note also that no process should be consulting this SLRU
+ * if we have just deactivated it.
*/
- LWLockAcquire(CommitTsSLRULock, LW_EXCLUSIVE);
(void) SlruScanDirectory(CommitTsCtl, SlruScanDirCbDeleteAll, NULL);
- LWLockRelease(CommitTsSLRULock);
+
+ LWLockRelease(CommitTsLock);
}
/*
@@ -804,6 +841,7 @@ void
ExtendCommitTs(TransactionId newestXact)
{
int64 pageno;
+ LWLock *lock;
/*
* Nothing to do if module not enabled. Note we do an unlocked read of
@@ -824,12 +862,14 @@ ExtendCommitTs(TransactionId newestXact)
pageno = TransactionIdToCTsPage(newestXact);
- LWLockAcquire(CommitTsSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(CommitTsCtl, pageno);
+
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Zero the page and make an XLOG entry about it */
ZeroCommitTsPage(pageno, !InRecovery);
- LWLockRelease(CommitTsSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -983,16 +1023,18 @@ commit_ts_redo(XLogReaderState *record)
{
int64 pageno;
int slotno;
+ LWLock *lock;
memcpy(&pageno, XLogRecGetData(record), sizeof(pageno));
- LWLockAcquire(CommitTsSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(CommitTsCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = ZeroCommitTsPage(pageno, false);
SimpleLruWritePage(CommitTsCtl, slotno);
Assert(!CommitTsCtl->shared->page_dirty[slotno]);
- LWLockRelease(CommitTsSLRULock);
+ LWLockRelease(lock);
}
else if (info == COMMIT_TS_TRUNCATE)
{
diff --git a/src/backend/access/transam/multixact.c \
b/src/backend/access/transam/multixact.c index a886c29892..6143fdaaab 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -88,6 +88,7 @@
#include "storage/proc.h"
#include "storage/procarray.h"
#include "utils/builtins.h"
+#include "utils/guc_hooks.h"
#include "utils/memutils.h"
#include "utils/snapmgr.h"
@@ -192,10 +193,10 @@ static SlruCtlData MultiXactMemberCtlData;
/*
* MultiXact state shared across all backends. All this state is protected
- * by MultiXactGenLock. (We also use MultiXactOffsetSLRULock and
- * MultiXactMemberSLRULock to guard accesses to the two sets of SLRU
- * buffers. For concurrency's sake, we avoid holding more than one of these
- * locks at a time.)
+ * by MultiXactGenLock. (We also use SLRU bank's lock of MultiXactOffset and
+ * MultiXactMember to guard accesses to the two sets of SLRU buffers. For
+ * concurrency's sake, we avoid holding more than one of these locks at a
+ * time.)
*/
typedef struct MultiXactStateData
{
@@ -870,12 +871,15 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
int slotno;
MultiXactOffset *offptr;
int i;
-
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
+ LWLock *lock;
+ LWLock *prevlock = NULL;
pageno = MultiXactIdToOffsetPage(multi);
entryno = MultiXactIdToOffsetEntry(multi);
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+
/*
* Note: we pass the MultiXactId to SimpleLruReadPage as the "transaction"
* to complain about if there's any I/O error. This is kinda bogus, but
@@ -891,10 +895,8 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
MultiXactOffsetCtl->shared->page_dirty[slotno] = true;
- /* Exchange our lock */
- LWLockRelease(MultiXactOffsetSLRULock);
-
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
+ /* Release MultiXactOffset SLRU lock. */
+ LWLockRelease(lock);
prev_pageno = -1;
@@ -916,6 +918,20 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
if (pageno != prev_pageno)
{
+ /*
+ * MultiXactMember SLRU page is changed so check if this new page
+ * fall into the different SLRU bank then release the old bank's
+ * lock and acquire lock on the new bank.
+ */
+ lock = SimpleLruGetBankLock(MultiXactMemberCtl, pageno);
+ if (lock != prevlock)
+ {
+ if (prevlock != NULL)
+ LWLockRelease(prevlock);
+
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ prevlock = lock;
+ }
slotno = SimpleLruReadPage(MultiXactMemberCtl, pageno, true, multi);
prev_pageno = pageno;
}
@@ -936,7 +952,8 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
MultiXactMemberCtl->shared->page_dirty[slotno] = true;
}
- LWLockRelease(MultiXactMemberSLRULock);
+ if (prevlock != NULL)
+ LWLockRelease(prevlock);
}
/*
@@ -1239,6 +1256,8 @@ GetMultiXactIdMembers(MultiXactId multi, MultiXactMember \
**members, MultiXactId tmpMXact;
MultiXactOffset nextOffset;
MultiXactMember *ptr;
+ LWLock *lock;
+ LWLock *prevlock = NULL;
debug_elog3(DEBUG2, "GetMembers: asked for %u", multi);
@@ -1342,11 +1361,22 @@ GetMultiXactIdMembers(MultiXactId multi, MultiXactMember \
**members,
* time on every multixact creation.
*/
retry:
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
-
pageno = MultiXactIdToOffsetPage(multi);
entryno = MultiXactIdToOffsetEntry(multi);
+ /*
+ * If this page falls under a different bank, release the old bank's lock
+ * and acquire the lock of the new bank.
+ */
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
+ if (lock != prevlock)
+ {
+ if (prevlock != NULL)
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ prevlock = lock;
+ }
+
slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, multi);
offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
offptr += entryno;
@@ -1379,7 +1409,21 @@ retry:
entryno = MultiXactIdToOffsetEntry(tmpMXact);
if (pageno != prev_pageno)
+ {
+ /*
+ * Since we're going to access a different SLRU page, if this page
+ * falls under a different bank, release the old bank's lock and
+ * acquire the lock of the new bank.
+ */
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
+ if (prevlock != lock)
+ {
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ prevlock = lock;
+ }
slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, tmpMXact);
+ }
offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
offptr += entryno;
@@ -1388,7 +1432,8 @@ retry:
if (nextMXOffset == 0)
{
/* Corner case 2: next multixact is still being filled in */
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(prevlock);
+ prevlock = NULL;
CHECK_FOR_INTERRUPTS();
pg_usleep(1000L);
goto retry;
@@ -1397,13 +1442,11 @@ retry:
length = nextMXOffset - offset;
}
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(prevlock);
+ prevlock = NULL;
ptr = (MultiXactMember *) palloc(length * sizeof(MultiXactMember));
- /* Now get the members themselves. */
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
-
truelength = 0;
prev_pageno = -1;
for (i = 0; i < length; i++, offset++)
@@ -1419,6 +1462,20 @@ retry:
if (pageno != prev_pageno)
{
+ /*
+ * Since we're going to access a different SLRU page, if this page
+ * falls under a different bank, release the old bank's lock and
+ * acquire the lock of the new bank.
+ */
+ lock = SimpleLruGetBankLock(MultiXactMemberCtl, pageno);
+ if (lock != prevlock)
+ {
+ if (prevlock)
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ prevlock = lock;
+ }
+
slotno = SimpleLruReadPage(MultiXactMemberCtl, pageno, true, multi);
prev_pageno = pageno;
}
@@ -1442,7 +1499,8 @@ retry:
truelength++;
}
- LWLockRelease(MultiXactMemberSLRULock);
+ if (prevlock)
+ LWLockRelease(prevlock);
/* A multixid with zero members should not happen */
Assert(truelength > 0);
@@ -1834,8 +1892,8 @@ MultiXactShmemSize(void)
mul_size(sizeof(MultiXactId) * 2, MaxOldestSlot))
size = SHARED_MULTIXACT_STATE_SIZE;
- size = add_size(size, SimpleLruShmemSize(NUM_MULTIXACTOFFSET_BUFFERS, 0));
- size = add_size(size, SimpleLruShmemSize(NUM_MULTIXACTMEMBER_BUFFERS, 0));
+ size = add_size(size, SimpleLruShmemSize(multixact_offsets_buffers, 0));
+ size = add_size(size, SimpleLruShmemSize(multixact_members_buffers, 0));
return size;
}
@@ -1851,16 +1909,16 @@ MultiXactShmemInit(void)
MultiXactMemberCtl->PagePrecedes = MultiXactMemberPagePrecedes;
SimpleLruInit(MultiXactOffsetCtl,
- "MultiXactOffset", NUM_MULTIXACTOFFSET_BUFFERS, 0,
- MultiXactOffsetSLRULock, "pg_multixact/offsets",
- LWTRANCHE_MULTIXACTOFFSET_BUFFER,
+ "MultiXactOffset", multixact_offsets_buffers, 0,
+ "pg_multixact/offsets", LWTRANCHE_MULTIXACTOFFSET_BUFFER,
+ LWTRANCHE_MULTIXACTOFFSET_SLRU,
SYNC_HANDLER_MULTIXACT_OFFSET,
false);
SlruPagePrecedesUnitTests(MultiXactOffsetCtl, MULTIXACT_OFFSETS_PER_PAGE);
SimpleLruInit(MultiXactMemberCtl,
- "MultiXactMember", NUM_MULTIXACTMEMBER_BUFFERS, 0,
- MultiXactMemberSLRULock, "pg_multixact/members",
- LWTRANCHE_MULTIXACTMEMBER_BUFFER,
+ "MultiXactMember", multixact_members_buffers, 0,
+ "pg_multixact/members", LWTRANCHE_MULTIXACTMEMBER_BUFFER,
+ LWTRANCHE_MULTIXACTMEMBER_SLRU,
SYNC_HANDLER_MULTIXACT_MEMBER,
false);
/* doesn't call SimpleLruTruncate() or meet criteria for unit tests */
@@ -1887,6 +1945,24 @@ MultiXactShmemInit(void)
OldestVisibleMXactId = OldestMemberMXactId + MaxOldestSlot;
}
+/*
+ * GUC check_hook for multixact_offsets_buffers
+ */
+bool
+check_multixact_offsets_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("multixact_offsets_buffers", newval);
+}
+
+/*
+ * GUC check_hook for multixact_members_buffers
+ */
+bool
+check_multixact_members_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("multixact_members_buffers", newval);
+}
+
/*
* This func must be called ONCE on system install. It creates the initial
* MultiXact segments. (The MultiXacts directories are assumed to have been
@@ -1896,8 +1972,10 @@ void
BootStrapMultiXact(void)
{
int slotno;
+ LWLock *lock;
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, 0);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Create and zero the first page of the offsets log */
slotno = ZeroMultiXactOffsetPage(0, false);
@@ -1906,9 +1984,10 @@ BootStrapMultiXact(void)
SimpleLruWritePage(MultiXactOffsetCtl, slotno);
Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]);
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(lock);
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(MultiXactMemberCtl, 0);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Create and zero the first page of the members log */
slotno = ZeroMultiXactMemberPage(0, false);
@@ -1917,7 +1996,7 @@ BootStrapMultiXact(void)
SimpleLruWritePage(MultiXactMemberCtl, slotno);
Assert(!MultiXactMemberCtl->shared->page_dirty[slotno]);
- LWLockRelease(MultiXactMemberSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -1977,10 +2056,12 @@ static void
MaybeExtendOffsetSlru(void)
{
int64 pageno;
+ LWLock *lock;
pageno = MultiXactIdToOffsetPage(MultiXactState->nextMXact);
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
if (!SimpleLruDoesPhysicalPageExist(MultiXactOffsetCtl, pageno))
{
@@ -1995,7 +2076,7 @@ MaybeExtendOffsetSlru(void)
SimpleLruWritePage(MultiXactOffsetCtl, slotno);
}
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -2051,6 +2132,8 @@ TrimMultiXact(void)
oldestMXactDB = MultiXactState->oldestMultiXactDB;
LWLockRelease(MultiXactGenLock);
+ /* Clean up offsets state */
+
/*
* (Re-)Initialize our idea of the latest page number for offsets.
*/
@@ -2058,9 +2141,6 @@ TrimMultiXact(void)
pg_atomic_write_u64(&MultiXactOffsetCtl->shared->latest_page_number,
pageno);
- /* Clean up offsets state */
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
-
/*
* Zero out the remainder of the current offsets page. See notes in
* TrimCLOG() for background. Unlike CLOG, some WAL record covers every
@@ -2074,7 +2154,9 @@ TrimMultiXact(void)
{
int slotno;
MultiXactOffset *offptr;
+ LWLock *lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, nextMXact);
offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
offptr += entryno;
@@ -2082,10 +2164,9 @@ TrimMultiXact(void)
MemSet(offptr, 0, BLCKSZ - (entryno * sizeof(MultiXactOffset)));
MultiXactOffsetCtl->shared->page_dirty[slotno] = true;
+ LWLockRelease(lock);
}
- LWLockRelease(MultiXactOffsetSLRULock);
-
/*
* And the same for members.
*
@@ -2095,8 +2176,6 @@ TrimMultiXact(void)
pg_atomic_write_u64(&MultiXactMemberCtl->shared->latest_page_number,
pageno);
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
-
/*
* Zero out the remainder of the current members page. See notes in
* TrimCLOG() for motivation.
@@ -2107,7 +2186,9 @@ TrimMultiXact(void)
int slotno;
TransactionId *xidptr;
int memberoff;
+ LWLock *lock = SimpleLruGetBankLock(MultiXactMemberCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
memberoff = MXOffsetToMemberOffset(offset);
slotno = SimpleLruReadPage(MultiXactMemberCtl, pageno, true, offset);
xidptr = (TransactionId *)
@@ -2122,10 +2203,9 @@ TrimMultiXact(void)
*/
MultiXactMemberCtl->shared->page_dirty[slotno] = true;
+ LWLockRelease(lock);
}
- LWLockRelease(MultiXactMemberSLRULock);
-
/* signal that we're officially up */
LWLockAcquire(MultiXactGenLock, LW_EXCLUSIVE);
MultiXactState->finishedStartup = true;
@@ -2413,6 +2493,7 @@ static void
ExtendMultiXactOffset(MultiXactId multi)
{
int64 pageno;
+ LWLock *lock;
/*
* No work except at first MultiXactId of a page. But beware: just after
@@ -2423,13 +2504,14 @@ ExtendMultiXactOffset(MultiXactId multi)
return;
pageno = MultiXactIdToOffsetPage(multi);
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Zero the page and make an XLOG entry about it */
ZeroMultiXactOffsetPage(pageno, true);
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -2462,15 +2544,17 @@ ExtendMultiXactMember(MultiXactOffset offset, int nmembers)
if (flagsoff == 0 && flagsbit == 0)
{
int64 pageno;
+ LWLock *lock;
pageno = MXOffsetToMemberPage(offset);
+ lock = SimpleLruGetBankLock(MultiXactMemberCtl, pageno);
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Zero the page and make an XLOG entry about it */
ZeroMultiXactMemberPage(pageno, true);
- LWLockRelease(MultiXactMemberSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -2768,7 +2852,7 @@ find_multixact_start(MultiXactId multi, MultiXactOffset \
*result) offptr = (MultiXactOffset *) \
MultiXactOffsetCtl->shared->page_buffer[slotno]; offptr += entryno;
offset = *offptr;
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(SimpleLruGetBankLock(MultiXactOffsetCtl, pageno));
*result = offset;
return true;
@@ -3250,31 +3334,35 @@ multixact_redo(XLogReaderState *record)
{
int64 pageno;
int slotno;
+ LWLock *lock;
memcpy(&pageno, XLogRecGetData(record), sizeof(pageno));
- LWLockAcquire(MultiXactOffsetSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(MultiXactOffsetCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = ZeroMultiXactOffsetPage(pageno, false);
SimpleLruWritePage(MultiXactOffsetCtl, slotno);
Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]);
- LWLockRelease(MultiXactOffsetSLRULock);
+ LWLockRelease(lock);
}
else if (info == XLOG_MULTIXACT_ZERO_MEM_PAGE)
{
int64 pageno;
int slotno;
+ LWLock *lock;
memcpy(&pageno, XLogRecGetData(record), sizeof(pageno));
- LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(MultiXactMemberCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = ZeroMultiXactMemberPage(pageno, false);
SimpleLruWritePage(MultiXactMemberCtl, slotno);
Assert(!MultiXactMemberCtl->shared->page_dirty[slotno]);
- LWLockRelease(MultiXactMemberSLRULock);
+ LWLockRelease(lock);
}
else if (info == XLOG_MULTIXACT_CREATE_ID)
{
diff --git a/src/backend/access/transam/slru.c b/src/backend/access/transam/slru.c
index 57949fbab4..7974d904ec 100644
--- a/src/backend/access/transam/slru.c
+++ b/src/backend/access/transam/slru.c
@@ -60,6 +60,7 @@
#include "pgstat.h"
#include "storage/fd.h"
#include "storage/shmem.h"
+#include "utils/guc_hooks.h"
static inline int
SlruFileName(SlruCtl ctl, char *path, int64 segno)
@@ -106,6 +107,12 @@ typedef struct SlruWriteAllData
typedef struct SlruWriteAllData *SlruWriteAll;
+/*
+ * Macro to get the lock index that protects the given slot.
+ */
+#define SLRU_SLOTNO_GET_BANKLOCKNO(slotno) \
+ ((slotno) / SLRU_BANK_SIZE)
+
/*
* Populate a file tag describing a segment file. We only use the segment
* number, since we can derive everything else we need by having separate
@@ -118,34 +125,6 @@ typedef struct SlruWriteAllData *SlruWriteAll;
(a).segno = (xx_segno) \
)
-/*
- * Macro to mark a buffer slot "most recently used". Note multiple evaluation
- * of arguments!
- *
- * The reason for the if-test is that there are often many consecutive
- * accesses to the same page (particularly the latest page). By suppressing
- * useless increments of cur_lru_count, we reduce the probability that old
- * pages' counts will "wrap around" and make them appear recently used.
- *
- * We allow this code to be executed concurrently by multiple processes within
- * SimpleLruReadPage_ReadOnly(). As long as int reads and writes are atomic,
- * this should not cause any completely-bogus values to enter the computation.
- * However, it is possible for either cur_lru_count or individual
- * page_lru_count entries to be "reset" to lower values than they should have,
- * in case a process is delayed while it executes this macro. With care in
- * SlruSelectLRUPage(), this does little harm, and in any case the absolute
- * worst possible consequence is a nonoptimal choice of page to evict. The
- * gain from allowing concurrent reads of SLRU pages seems worth it.
- */
-#define SlruRecentlyUsed(shared, slotno) \
- do { \
- int new_lru_count = (shared)->cur_lru_count; \
- if (new_lru_count != (shared)->page_lru_count[slotno]) { \
- (shared)->cur_lru_count = ++new_lru_count; \
- (shared)->page_lru_count[slotno] = new_lru_count; \
- } \
- } while (0)
-
/* Saved info for SlruReportIOError */
typedef enum
{
@@ -173,6 +152,7 @@ static int SlruSelectLRUPage(SlruCtl ctl, int64 pageno);
static bool SlruScanDirCbDeleteCutoff(SlruCtl ctl, char *filename,
int64 segpage, void *data);
static void SlruInternalDeleteSegment(SlruCtl ctl, int64 segno);
+static inline void SlruRecentlyUsed(SlruShared shared, int slotno);
/*
@@ -182,8 +162,11 @@ static void SlruInternalDeleteSegment(SlruCtl ctl, int64 segno);
Size
SimpleLruShmemSize(int nslots, int nlsns)
{
+ int nbanks = nslots / SLRU_BANK_SIZE;
Size sz;
+ Assert(nslots <= SLRU_MAX_ALLOWED_BUFFERS);
+
/* we assume nslots isn't so large as to risk overflow */
sz = MAXALIGN(sizeof(SlruSharedData));
sz += MAXALIGN(nslots * sizeof(char *)); /* page_buffer[] */
@@ -192,6 +175,8 @@ SimpleLruShmemSize(int nslots, int nlsns)
sz += MAXALIGN(nslots * sizeof(int64)); /* page_number[] */
sz += MAXALIGN(nslots * sizeof(int)); /* page_lru_count[] */
sz += MAXALIGN(nslots * sizeof(LWLockPadded)); /* buffer_locks[] */
+ sz += MAXALIGN(nbanks * sizeof(LWLockPadded)); /* bank_locks[] */
+ sz += MAXALIGN(nbanks * sizeof(int)); /* bank_cur_lru_count[] */
if (nlsns > 0)
sz += MAXALIGN(nslots * nlsns * sizeof(XLogRecPtr)); /* group_lsn[] */
@@ -208,16 +193,20 @@ SimpleLruShmemSize(int nslots, int nlsns)
* nlsns: number of LSN groups per page (set to zero if not relevant).
* ctllock: LWLock to use to control access to the shared control structure.
* subdir: PGDATA-relative subdirectory that will contain the files.
- * tranche_id: LWLock tranche ID to use for the SLRU's per-buffer LWLocks.
+ * buffer_tranche_id: tranche ID to use for the SLRU's per-buffer LWLocks.
+ * bank_tranche_id: tranche ID to use for the bank LWLocks.
* sync_handler: which set of functions to use to handle sync requests
*/
void
SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int nlsns,
- LWLock *ctllock, const char *subdir, int tranche_id,
+ const char *subdir, int buffer_tranche_id, int bank_tranche_id,
SyncRequestHandler sync_handler, bool long_segment_names)
{
SlruShared shared;
bool found;
+ int nbanks = nslots / SLRU_BANK_SIZE;
+
+ Assert(nslots <= SLRU_MAX_ALLOWED_BUFFERS);
shared = (SlruShared) ShmemInitStruct(name,
SimpleLruShmemSize(nslots, nlsns),
@@ -228,19 +217,14 @@ SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int \
nlsns, /* Initialize locks and shared memory area */
char *ptr;
Size offset;
- int slotno;
Assert(!found);
memset(shared, 0, sizeof(SlruSharedData));
- shared->ControlLock = ctllock;
-
shared->num_slots = nslots;
shared->lsn_groups_per_page = nlsns;
- shared->cur_lru_count = 0;
-
/* shared->latest_page_number will be set later */
shared->slru_stats_idx = pgstat_get_slru_index(name);
@@ -261,6 +245,10 @@ SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int \
nlsns, /* Initialize LWLocks */
shared->buffer_locks = (LWLockPadded *) (ptr + offset);
offset += MAXALIGN(nslots * sizeof(LWLockPadded));
+ shared->bank_locks = (LWLockPadded *) (ptr + offset);
+ offset += MAXALIGN(nbanks * sizeof(LWLockPadded));
+ shared->bank_cur_lru_count = (int *) (ptr + offset);
+ offset += MAXALIGN(nbanks * sizeof(int));
if (nlsns > 0)
{
@@ -269,10 +257,10 @@ SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int \
nlsns, }
ptr += BUFFERALIGN(offset);
- for (slotno = 0; slotno < nslots; slotno++)
+ for (int slotno = 0; slotno < nslots; slotno++)
{
LWLockInitialize(&shared->buffer_locks[slotno].lock,
- tranche_id);
+ buffer_tranche_id);
shared->page_buffer[slotno] = ptr;
shared->page_status[slotno] = SLRU_PAGE_EMPTY;
@@ -281,11 +269,23 @@ SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int \
nlsns, ptr += BLCKSZ;
}
+ /* Initialize the bank locks. */
+ for (int banklockno = 0; banklockno < nbanks; banklockno++)
+ LWLockInitialize(&shared->bank_locks[banklockno].lock,
+ bank_tranche_id);
+
+ /* Initialize the bank lru counters. */
+ for (int bankno = 0; bankno < nbanks; bankno++)
+ shared->bank_cur_lru_count[bankno] = 0;
+
/* Should fit to estimated shmem size */
Assert(ptr - (char *) shared <= SimpleLruShmemSize(nslots, nlsns));
}
else
+ {
Assert(found);
+ Assert(shared->num_slots == nslots);
+ }
/*
* Initialize the unshared control struct, including directory path. We
@@ -294,6 +294,7 @@ SimpleLruInit(SlruCtl ctl, const char *name, int nslots, int \
nlsns, ctl->shared = shared;
ctl->sync_handler = sync_handler;
ctl->long_segment_names = long_segment_names;
+ ctl->bank_mask = (nslots / SLRU_BANK_SIZE) - 1;
strlcpy(ctl->Dir, subdir, sizeof(ctl->Dir));
}
@@ -371,12 +372,13 @@ static void
SimpleLruWaitIO(SlruCtl ctl, int slotno)
{
SlruShared shared = ctl->shared;
+ int banklockno = SLRU_SLOTNO_GET_BANKLOCKNO(slotno);
/* See notes at top of file */
- LWLockRelease(shared->ControlLock);
+ LWLockRelease(&shared->bank_locks[banklockno].lock);
LWLockAcquire(&shared->buffer_locks[slotno].lock, LW_SHARED);
LWLockRelease(&shared->buffer_locks[slotno].lock);
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ LWLockAcquire(&shared->bank_locks[banklockno].lock, LW_EXCLUSIVE);
/*
* If the slot is still in an io-in-progress state, then either someone
@@ -419,7 +421,7 @@ SimpleLruWaitIO(SlruCtl ctl, int slotno)
* Return value is the shared-buffer slot number now holding the page.
* The buffer's LRU access info is updated.
*
- * Control lock must be held at entry, and will be held at exit.
+ * The correct bank lock must be held at entry, and will be held at exit.
*/
int
SimpleLruReadPage(SlruCtl ctl, int64 pageno, bool write_ok,
@@ -427,10 +429,14 @@ SimpleLruReadPage(SlruCtl ctl, int64 pageno, bool write_ok,
{
SlruShared shared = ctl->shared;
+ /* Caller must hold the bank lock for the input page. */
+ Assert(LWLockHeldByMe(SimpleLruGetBankLock(ctl, pageno)));
+
/* Outer loop handles restart if we must wait for someone else's I/O */
for (;;)
{
int slotno;
+ int banklockno;
bool ok;
/* See if page already is in memory; if not, pick victim slot */
@@ -473,9 +479,10 @@ SimpleLruReadPage(SlruCtl ctl, int64 pageno, bool write_ok,
/* Acquire per-buffer lock (cannot deadlock, see notes at top) */
LWLockAcquire(&shared->buffer_locks[slotno].lock, LW_EXCLUSIVE);
+ banklockno = SLRU_SLOTNO_GET_BANKLOCKNO(slotno);
/* Release control lock while doing I/O */
- LWLockRelease(shared->ControlLock);
+ LWLockRelease(&shared->bank_locks[banklockno].lock);
/* Do the read */
ok = SlruPhysicalReadPage(ctl, pageno, slotno);
@@ -484,7 +491,7 @@ SimpleLruReadPage(SlruCtl ctl, int64 pageno, bool write_ok,
SimpleLruZeroLSNs(ctl, slotno);
/* Re-acquire control lock and update page state */
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ LWLockAcquire(&shared->bank_locks[banklockno].lock, LW_EXCLUSIVE);
Assert(shared->page_number[slotno] == pageno &&
shared->page_status[slotno] == SLRU_PAGE_READ_IN_PROGRESS &&
@@ -526,12 +533,19 @@ SimpleLruReadPage_ReadOnly(SlruCtl ctl, int64 pageno, \
TransactionId xid) {
SlruShared shared = ctl->shared;
int slotno;
+ int bankstart = (pageno & ctl->bank_mask) * SLRU_BANK_SIZE;
+ int bankend = bankstart + SLRU_BANK_SIZE;
+ int banklockno = SLRU_SLOTNO_GET_BANKLOCKNO(bankstart);
/* Try to find the page while holding only shared lock */
- LWLockAcquire(shared->ControlLock, LW_SHARED);
+ LWLockAcquire(&shared->bank_locks[banklockno].lock, LW_SHARED);
- /* See if page is already in a buffer */
- for (slotno = 0; slotno < shared->num_slots; slotno++)
+ /*
+ * See if the page is already in a buffer pool. The buffer pool is
+ * divided into banks of buffers and each pageno may reside only in one
+ * bank so limit the search within the bank.
+ */
+ for (slotno = bankstart; slotno < bankend; slotno++)
{
if (shared->page_number[slotno] == pageno &&
shared->page_status[slotno] != SLRU_PAGE_EMPTY &&
@@ -548,8 +562,8 @@ SimpleLruReadPage_ReadOnly(SlruCtl ctl, int64 pageno, \
TransactionId xid) }
/* No luck, so switch to normal exclusive lock and do regular read */
- LWLockRelease(shared->ControlLock);
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ LWLockRelease(&shared->bank_locks[banklockno].lock);
+ LWLockAcquire(&shared->bank_locks[banklockno].lock, LW_EXCLUSIVE);
return SimpleLruReadPage(ctl, pageno, true, xid);
}
@@ -571,6 +585,7 @@ SlruInternalWritePage(SlruCtl ctl, int slotno, SlruWriteAll \
fdata) SlruShared shared = ctl->shared;
int64 pageno = shared->page_number[slotno];
bool ok;
+ int banklockno = SLRU_SLOTNO_GET_BANKLOCKNO(slotno);
/* If a write is in progress, wait for it to finish */
while (shared->page_status[slotno] == SLRU_PAGE_WRITE_IN_PROGRESS &&
@@ -599,7 +614,7 @@ SlruInternalWritePage(SlruCtl ctl, int slotno, SlruWriteAll \
fdata) LWLockAcquire(&shared->buffer_locks[slotno].lock, LW_EXCLUSIVE);
/* Release control lock while doing I/O */
- LWLockRelease(shared->ControlLock);
+ LWLockRelease(&shared->bank_locks[banklockno].lock);
/* Do the write */
ok = SlruPhysicalWritePage(ctl, pageno, slotno, fdata);
@@ -614,7 +629,7 @@ SlruInternalWritePage(SlruCtl ctl, int slotno, SlruWriteAll \
fdata) }
/* Re-acquire control lock and update page state */
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ LWLockAcquire(&shared->bank_locks[banklockno].lock, LW_EXCLUSIVE);
Assert(shared->page_number[slotno] == pageno &&
shared->page_status[slotno] == SLRU_PAGE_WRITE_IN_PROGRESS);
@@ -1030,17 +1045,17 @@ SlruReportIOError(SlruCtl ctl, int64 pageno, TransactionId \
xid) }
/*
- * Select the slot to re-use when we need a free slot.
+ * Select the slot to re-use when we need a free slot for the given page.
*
- * The target page number is passed because we need to consider the
- * possibility that some other process reads in the target page while
- * we are doing I/O to free a slot. Hence, check or recheck to see if
- * any slot already holds the target page, and return that slot if so.
- * Thus, the returned slot is *either* a slot already holding the pageno
- * (could be any state except EMPTY), *or* a freeable slot (state EMPTY
- * or CLEAN).
+ * The target page number is passed not only because we need to know the
+ * correct bank to use, but also because we need to consider the possibility
+ * that some other process reads in the target page while we are doing I/O to
+ * free a slot. Hence, check or recheck to see if any slot already holds the
+ * target page, and return that slot if so. Thus, the returned slot is
+ * *either* a slot already holding the pageno (could be any state except
+ * EMPTY), *or* a freeable slot (state EMPTY or CLEAN).
*
- * Control lock must be held at entry, and will be held at exit.
+ * The correct bank lock must be held at entry, and will be held at exit.
*/
static int
SlruSelectLRUPage(SlruCtl ctl, int64 pageno)
@@ -1058,9 +1073,18 @@ SlruSelectLRUPage(SlruCtl ctl, int64 pageno)
int bestinvalidslot = 0; /* keep compiler quiet */
int best_invalid_delta = -1;
int64 best_invalid_page_number = 0; /* keep compiler quiet */
+ int bankno = pageno & ctl->bank_mask;
+ int bankstart = bankno * SLRU_BANK_SIZE;
+ int bankend = bankstart + SLRU_BANK_SIZE;
- /* See if page already has a buffer assigned */
- for (slotno = 0; slotno < shared->num_slots; slotno++)
+ Assert(LWLockHeldByMe(&shared->bank_locks[bankno].lock));
+
+ /*
+ * See if the page is already in a buffer pool. The buffer pool is
+ * divided into banks of buffers and each pageno may reside only in
+ * one bank so limit the search within the bank.
+ */
+ for (slotno = bankstart; slotno < bankend; slotno++)
{
if (shared->page_number[slotno] == pageno &&
shared->page_status[slotno] != SLRU_PAGE_EMPTY)
@@ -1094,8 +1118,8 @@ SlruSelectLRUPage(SlruCtl ctl, int64 pageno)
* That gets us back on the path to having good data when there are
* multiple pages with the same lru_count.
*/
- cur_count = (shared->cur_lru_count)++;
- for (slotno = 0; slotno < shared->num_slots; slotno++)
+ cur_count = (shared->bank_cur_lru_count[bankno])++;
+ for (slotno = bankstart; slotno < bankend; slotno++)
{
int this_delta;
int64 this_page_number;
@@ -1117,6 +1141,7 @@ SlruSelectLRUPage(SlruCtl ctl, int64 pageno)
}
this_page_number = shared->page_number[slotno];
+
pg_read_barrier();
if (this_page_number ==
pg_atomic_read_u64(&shared->latest_page_number))
@@ -1193,6 +1218,7 @@ SimpleLruWriteAll(SlruCtl ctl, bool allow_redirtied)
int slotno;
int64 pageno = 0;
int i;
+ int prevlockno = SLRU_SLOTNO_GET_BANKLOCKNO(0);
bool ok;
/* update the stats counter of flushes */
@@ -1203,10 +1229,23 @@ SimpleLruWriteAll(SlruCtl ctl, bool allow_redirtied)
*/
fdata.num_files = 0;
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ LWLockAcquire(&shared->bank_locks[prevlockno].lock, LW_EXCLUSIVE);
for (slotno = 0; slotno < shared->num_slots; slotno++)
{
+ int curlockno = SLRU_SLOTNO_GET_BANKLOCKNO(slotno);
+
+ /*
+ * If the current bank lock is not same as the previous bank lock then
+ * release the previous lock and acquire the new lock.
+ */
+ if (curlockno != prevlockno)
+ {
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
+ LWLockAcquire(&shared->bank_locks[curlockno].lock, LW_EXCLUSIVE);
+ prevlockno = curlockno;
+ }
+
SlruInternalWritePage(ctl, slotno, &fdata);
/*
@@ -1220,7 +1259,7 @@ SimpleLruWriteAll(SlruCtl ctl, bool allow_redirtied)
!shared->page_dirty[slotno]));
}
- LWLockRelease(shared->ControlLock);
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
/*
* Now close any files that were open
@@ -1260,6 +1299,7 @@ SimpleLruTruncate(SlruCtl ctl, int64 cutoffPage)
{
SlruShared shared = ctl->shared;
int slotno;
+ int prevlockno;
/* update the stats counter of truncates */
pgstat_count_slru_truncate(shared->slru_stats_idx);
@@ -1270,8 +1310,6 @@ SimpleLruTruncate(SlruCtl ctl, int64 cutoffPage)
* or just after a checkpoint, any dirty pages should have been flushed
* already ... we're just being extra careful here.)
*/
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
-
restart:
/*
@@ -1282,15 +1320,29 @@ restart:
if (ctl->PagePrecedes(pg_atomic_read_u64(&shared->latest_page_number),
cutoffPage))
{
- LWLockRelease(shared->ControlLock);
ereport(LOG,
(errmsg("could not truncate directory \"%s\": apparent wraparound",
ctl->Dir)));
return;
}
+ prevlockno = SLRU_SLOTNO_GET_BANKLOCKNO(0);
+ LWLockAcquire(&shared->bank_locks[prevlockno].lock, LW_EXCLUSIVE);
for (slotno = 0; slotno < shared->num_slots; slotno++)
{
+ int curlockno = SLRU_SLOTNO_GET_BANKLOCKNO(slotno);
+
+ /*
+ * If the current bank lock is not same as the previous bank lock then
+ * release the previous lock and acquire the new lock.
+ */
+ if (curlockno != prevlockno)
+ {
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
+ LWLockAcquire(&shared->bank_locks[curlockno].lock, LW_EXCLUSIVE);
+ prevlockno = curlockno;
+ }
+
if (shared->page_status[slotno] == SLRU_PAGE_EMPTY)
continue;
if (!ctl->PagePrecedes(shared->page_number[slotno], cutoffPage))
@@ -1320,10 +1372,12 @@ restart:
SlruInternalWritePage(ctl, slotno, NULL);
else
SimpleLruWaitIO(ctl, slotno);
+
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
goto restart;
}
- LWLockRelease(shared->ControlLock);
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
/* Now we can remove the old segment(s) */
(void) SlruScanDirectory(ctl, SlruScanDirCbDeleteCutoff, &cutoffPage);
@@ -1364,15 +1418,29 @@ SlruDeleteSegment(SlruCtl ctl, int64 segno)
SlruShared shared = ctl->shared;
int slotno;
bool did_write;
+ int prevlockno = SLRU_SLOTNO_GET_BANKLOCKNO(0);
/* Clean out any possibly existing references to the segment. */
- LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);
+ LWLockAcquire(&shared->bank_locks[prevlockno].lock, LW_EXCLUSIVE);
restart:
did_write = false;
for (slotno = 0; slotno < shared->num_slots; slotno++)
{
- int pagesegno = shared->page_number[slotno] / SLRU_PAGES_PER_SEGMENT;
+ int pagesegno;
+ int curlockno = SLRU_SLOTNO_GET_BANKLOCKNO(slotno);
+ /*
+ * If the current bank lock is not same as the previous bank lock then
+ * release the previous lock and acquire the new lock.
+ */
+ if (curlockno != prevlockno)
+ {
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
+ LWLockAcquire(&shared->bank_locks[curlockno].lock, LW_EXCLUSIVE);
+ prevlockno = curlockno;
+ }
+
+ pagesegno = shared->page_number[slotno] / SLRU_PAGES_PER_SEGMENT;
if (shared->page_status[slotno] == SLRU_PAGE_EMPTY)
continue;
@@ -1406,7 +1474,7 @@ restart:
SlruInternalDeleteSegment(ctl, segno);
- LWLockRelease(shared->ControlLock);
+ LWLockRelease(&shared->bank_locks[prevlockno].lock);
}
/*
@@ -1673,3 +1741,50 @@ SlruSyncFileTag(SlruCtl ctl, const FileTag *ftag, char *path)
errno = save_errno;
return result;
}
+
+/*
+ * Function to mark a buffer slot "most recently used".
+ *
+ * The reason for the if-test is that there are often many consecutive
+ * accesses to the same page (particularly the latest page). By suppressing
+ * useless increments of bank_cur_lru_count, we reduce the probability that old
+ * pages' counts will "wrap around" and make them appear recently used.
+ *
+ * We allow this code to be executed concurrently by multiple processes within
+ * SimpleLruReadPage_ReadOnly(). As long as int reads and writes are atomic,
+ * this should not cause any completely-bogus values to enter the computation.
+ * However, it is possible for either bank_cur_lru_count or individual
+ * page_lru_count entries to be "reset" to lower values than they should have,
+ * in case a process is delayed while it executes this function. With care in
+ * SlruSelectLRUPage(), this does little harm, and in any case the absolute
+ * worst possible consequence is a nonoptimal choice of page to evict. The
+ * gain from allowing concurrent reads of SLRU pages seems worth it.
+ */
+static inline void
+SlruRecentlyUsed(SlruShared shared, int slotno)
+{
+ int bankno = slotno / SLRU_BANK_SIZE;
+ int new_lru_count = shared->bank_cur_lru_count[bankno];
+
+ if (new_lru_count != shared->page_lru_count[slotno])
+ {
+ shared->bank_cur_lru_count[bankno] = ++new_lru_count;
+ shared->page_lru_count[slotno] = new_lru_count;
+ }
+}
+
+/*
+ * Helper function for GUC check_hook to check whether slru buffers are in
+ * multiples of SLRU_BANK_SIZE.
+ */
+bool
+check_slru_buffers(const char *name, int *newval)
+{
+ /* Valid values are multiples of SLRU_BANK_SIZE */
+ if (*newval % SLRU_BANK_SIZE == 0)
+ return true;
+
+ GUC_check_errdetail("\"%s\" must be a multiple of %d", name,
+ SLRU_BANK_SIZE);
+ return false;
+}
diff --git a/src/backend/access/transam/subtrans.c \
b/src/backend/access/transam/subtrans.c index b2ed82ac56..cee850c9f8 100644
--- a/src/backend/access/transam/subtrans.c
+++ b/src/backend/access/transam/subtrans.c
@@ -31,7 +31,9 @@
#include "access/slru.h"
#include "access/subtrans.h"
#include "access/transam.h"
+#include "miscadmin.h"
#include "pg_trace.h"
+#include "utils/guc_hooks.h"
#include "utils/snapmgr.h"
@@ -85,12 +87,14 @@ SubTransSetParent(TransactionId xid, TransactionId parent)
int64 pageno = TransactionIdToPage(xid);
int entryno = TransactionIdToEntry(xid);
int slotno;
+ LWLock *lock;
TransactionId *ptr;
Assert(TransactionIdIsValid(parent));
Assert(TransactionIdFollows(xid, parent));
- LWLockAcquire(SubtransSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(SubTransCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = SimpleLruReadPage(SubTransCtl, pageno, true, xid);
ptr = (TransactionId *) SubTransCtl->shared->page_buffer[slotno];
@@ -108,7 +112,7 @@ SubTransSetParent(TransactionId xid, TransactionId parent)
SubTransCtl->shared->page_dirty[slotno] = true;
}
- LWLockRelease(SubtransSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -138,7 +142,7 @@ SubTransGetParent(TransactionId xid)
parent = *ptr;
- LWLockRelease(SubtransSLRULock);
+ LWLockRelease(SimpleLruGetBankLock(SubTransCtl, pageno));
return parent;
}
@@ -186,6 +190,22 @@ SubTransGetTopmostTransaction(TransactionId xid)
return previousXid;
}
+/*
+ * Number of shared SUBTRANS buffers.
+ *
+ * If asked to autotune, we use 2MB for every 1GB of shared buffers, up to 8MB,
+ * but always at least 16 buffers. Otherwise just cap the configured amount to
+ * be between 16 and the maximum allowed.
+ */
+static int
+SUBTRANSShmemBuffers(void)
+{
+ /* auto-tune based on shared buffers */
+ if (subtransaction_buffers == 0)
+ return Min(1024, Max(16, NBuffers / 512));
+
+ return Min(Max(16, subtransaction_buffers), SLRU_MAX_ALLOWED_BUFFERS);
+}
/*
* Initialization of shared memory for SUBTRANS
@@ -193,20 +213,42 @@ SubTransGetTopmostTransaction(TransactionId xid)
Size
SUBTRANSShmemSize(void)
{
- return SimpleLruShmemSize(NUM_SUBTRANS_BUFFERS, 0);
+ return SimpleLruShmemSize(SUBTRANSShmemBuffers(), 0);
}
void
SUBTRANSShmemInit(void)
{
+ /* If auto-tuning is requested, now is the time to do it */
+ if (subtransaction_buffers == 0)
+ {
+ char buf[32];
+
+ snprintf(buf, sizeof(buf), "%d", SUBTRANSShmemBuffers());
+ SetConfigOption("subtransaction_buffers", buf, PGC_POSTMASTER,
+ PGC_S_DYNAMIC_DEFAULT);
+ if (subtransaction_buffers == 0) /* failed to apply it? */
+ SetConfigOption("subtransaction_buffers", buf, PGC_POSTMASTER,
+ PGC_S_OVERRIDE);
+ }
+ Assert(subtransaction_buffers != 0);
+
SubTransCtl->PagePrecedes = SubTransPagePrecedes;
- SimpleLruInit(SubTransCtl, "Subtrans", NUM_SUBTRANS_BUFFERS, 0,
- SubtransSLRULock, "pg_subtrans",
- LWTRANCHE_SUBTRANS_BUFFER, SYNC_HANDLER_NONE,
- false);
+ SimpleLruInit(SubTransCtl, "Subtrans", SUBTRANSShmemBuffers(), 0,
+ "pg_subtrans", LWTRANCHE_SUBTRANS_BUFFER,
+ LWTRANCHE_SUBTRANS_SLRU, SYNC_HANDLER_NONE, false);
SlruPagePrecedesUnitTests(SubTransCtl, SUBTRANS_XACTS_PER_PAGE);
}
+/*
+ * GUC check_hook for subtransaction_buffers
+ */
+bool
+check_subtrans_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("subtransaction_buffers", newval);
+}
+
/*
* This func must be called ONCE on system install. It creates
* the initial SUBTRANS segment. (The SUBTRANS directory is assumed to
@@ -221,8 +263,9 @@ void
BootStrapSUBTRANS(void)
{
int slotno;
+ LWLock *lock = SimpleLruGetBankLock(SubTransCtl, 0);
- LWLockAcquire(SubtransSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Create and zero the first page of the subtrans log */
slotno = ZeroSUBTRANSPage(0);
@@ -231,7 +274,7 @@ BootStrapSUBTRANS(void)
SimpleLruWritePage(SubTransCtl, slotno);
Assert(!SubTransCtl->shared->page_dirty[slotno]);
- LWLockRelease(SubtransSLRULock);
+ LWLockRelease(lock);
}
/*
@@ -261,6 +304,8 @@ StartupSUBTRANS(TransactionId oldestActiveXID)
FullTransactionId nextXid;
int64 startPage;
int64 endPage;
+ LWLock *prevlock;
+ LWLock *lock;
/*
* Since we don't expect pg_subtrans to be valid across crashes, we
@@ -268,23 +313,47 @@ StartupSUBTRANS(TransactionId oldestActiveXID)
* Whenever we advance into a new page, ExtendSUBTRANS will likewise zero
* the new page without regard to whatever was previously on disk.
*/
- LWLockAcquire(SubtransSLRULock, LW_EXCLUSIVE);
-
startPage = TransactionIdToPage(oldestActiveXID);
nextXid = TransamVariables->nextXid;
endPage = TransactionIdToPage(XidFromFullTransactionId(nextXid));
+ prevlock = SimpleLruGetBankLock(SubTransCtl, startPage);
+ LWLockAcquire(prevlock, LW_EXCLUSIVE);
while (startPage != endPage)
{
+ lock = SimpleLruGetBankLock(SubTransCtl, startPage);
+
+ /*
+ * Check if we need to acquire the lock on the new bank then release
+ * the lock on the old bank and acquire on the new bank.
+ */
+ if (prevlock != lock)
+ {
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ prevlock = lock;
+ }
+
(void) ZeroSUBTRANSPage(startPage);
startPage++;
/* must account for wraparound */
if (startPage > TransactionIdToPage(MaxTransactionId))
startPage = 0;
}
- (void) ZeroSUBTRANSPage(startPage);
- LWLockRelease(SubtransSLRULock);
+ lock = SimpleLruGetBankLock(SubTransCtl, startPage);
+
+ /*
+ * Check if we need to acquire the lock on the new bank then release the
+ * lock on the old bank and acquire on the new bank.
+ */
+ if (prevlock != lock)
+ {
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ }
+ (void) ZeroSUBTRANSPage(startPage);
+ LWLockRelease(lock);
}
/*
@@ -318,6 +387,7 @@ void
ExtendSUBTRANS(TransactionId newestXact)
{
int64 pageno;
+ LWLock *lock;
/*
* No work except at first XID of a page. But beware: just after
@@ -329,12 +399,13 @@ ExtendSUBTRANS(TransactionId newestXact)
pageno = TransactionIdToPage(newestXact);
- LWLockAcquire(SubtransSLRULock, LW_EXCLUSIVE);
+ lock = SimpleLruGetBankLock(SubTransCtl, pageno);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
/* Zero the page */
ZeroSUBTRANSPage(pageno);
- LWLockRelease(SubtransSLRULock);
+ LWLockRelease(lock);
}
diff --git a/src/backend/commands/async.c b/src/backend/commands/async.c
index 8b24b22293..0c2ac60946 100644
--- a/src/backend/commands/async.c
+++ b/src/backend/commands/async.c
@@ -116,7 +116,7 @@
* frontend during startup.) The above design guarantees that notifies from
* other backends will never be missed by ignoring self-notifies.
*
- * The amount of shared memory used for notify management (NUM_NOTIFY_BUFFERS)
+ * The amount of shared memory used for notify management (notify_buffers)
* can be varied without affecting anything but performance. The maximum
* amount of notification data that can be queued at one time is determined
* by max_notify_queue_pages GUC.
@@ -148,6 +148,7 @@
#include "storage/sinval.h"
#include "tcop/tcopprot.h"
#include "utils/builtins.h"
+#include "utils/guc_hooks.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/snapmgr.h"
@@ -234,7 +235,7 @@ typedef struct QueuePosition
*
* Resist the temptation to make this really large. While that would save
* work in some places, it would add cost in others. In particular, this
- * should likely be less than NUM_NOTIFY_BUFFERS, to ensure that backends
+ * should likely be less than notify_buffers, to ensure that backends
* catch up before the pages they'll need to read fall out of SLRU cache.
*/
#define QUEUE_CLEANUP_DELAY 4
@@ -266,9 +267,10 @@ typedef struct QueueBackendStatus
* both NotifyQueueLock and NotifyQueueTailLock in EXCLUSIVE mode, backends
* can change the tail pointers.
*
- * NotifySLRULock is used as the control lock for the pg_notify SLRU buffers.
+ * SLRU buffer pool is divided in banks and bank wise SLRU lock is used as
+ * the control lock for the pg_notify SLRU buffers.
* In order to avoid deadlocks, whenever we need multiple locks, we first get
- * NotifyQueueTailLock, then NotifyQueueLock, and lastly NotifySLRULock.
+ * NotifyQueueTailLock, then NotifyQueueLock, and lastly SLRU bank lock.
*
* Each backend uses the backend[] array entry with index equal to its
* BackendId (which can range from 1 to MaxBackends). We rely on this to make
@@ -492,7 +494,7 @@ AsyncShmemSize(void)
size = mul_size(MaxBackends + 1, sizeof(QueueBackendStatus));
size = add_size(size, offsetof(AsyncQueueControl, backend));
- size = add_size(size, SimpleLruShmemSize(NUM_NOTIFY_BUFFERS, 0));
+ size = add_size(size, SimpleLruShmemSize(notify_buffers, 0));
return size;
}
@@ -541,8 +543,8 @@ AsyncShmemInit(void)
* names are used in order to avoid wraparound.
*/
NotifyCtl->PagePrecedes = asyncQueuePagePrecedes;
- SimpleLruInit(NotifyCtl, "Notify", NUM_NOTIFY_BUFFERS, 0,
- NotifySLRULock, "pg_notify", LWTRANCHE_NOTIFY_BUFFER,
+ SimpleLruInit(NotifyCtl, "Notify", notify_buffers, 0,
+ "pg_notify", LWTRANCHE_NOTIFY_BUFFER, LWTRANCHE_NOTIFY_SLRU,
SYNC_HANDLER_NONE, true);
if (!found)
@@ -1356,7 +1358,7 @@ asyncQueueNotificationToEntry(Notification *n, AsyncQueueEntry \
*qe)
* Eventually we will return NULL indicating all is done.
*
* We are holding NotifyQueueLock already from the caller and grab
- * NotifySLRULock locally in this function.
+ * page specific SLRU bank lock locally in this function.
*/
static ListCell *
asyncQueueAddEntries(ListCell *nextNotify)
@@ -1366,9 +1368,7 @@ asyncQueueAddEntries(ListCell *nextNotify)
int64 pageno;
int offset;
int slotno;
-
- /* We hold both NotifyQueueLock and NotifySLRULock during this operation */
- LWLockAcquire(NotifySLRULock, LW_EXCLUSIVE);
+ LWLock *prevlock;
/*
* We work with a local copy of QUEUE_HEAD, which we write back to shared
@@ -1389,6 +1389,11 @@ asyncQueueAddEntries(ListCell *nextNotify)
* page should be initialized already, so just fetch it.
*/
pageno = QUEUE_POS_PAGE(queue_head);
+ prevlock = SimpleLruGetBankLock(NotifyCtl, pageno);
+
+ /* We hold both NotifyQueueLock and SLRU bank lock during this operation */
+ LWLockAcquire(prevlock, LW_EXCLUSIVE);
+
if (QUEUE_POS_IS_ZERO(queue_head))
slotno = SimpleLruZeroPage(NotifyCtl, pageno);
else
@@ -1434,6 +1439,17 @@ asyncQueueAddEntries(ListCell *nextNotify)
/* Advance queue_head appropriately, and detect if page is full */
if (asyncQueueAdvance(&(queue_head), qe.length))
{
+ LWLock *lock;
+
+ pageno = QUEUE_POS_PAGE(queue_head);
+ lock = SimpleLruGetBankLock(NotifyCtl, pageno);
+ if (lock != prevlock)
+ {
+ LWLockRelease(prevlock);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
+ prevlock = lock;
+ }
+
/*
* Page is full, so we're done here, but first fill the next page
* with zeroes. The reason to do this is to ensure that slru.c's
@@ -1460,7 +1476,7 @@ asyncQueueAddEntries(ListCell *nextNotify)
/* Success, so update the global QUEUE_HEAD */
QUEUE_HEAD = queue_head;
- LWLockRelease(NotifySLRULock);
+ LWLockRelease(prevlock);
return nextNotify;
}
@@ -1931,9 +1947,9 @@ asyncQueueReadAllNotifications(void)
/*
* We copy the data from SLRU into a local buffer, so as to avoid
- * holding the NotifySLRULock while we are examining the entries
- * and possibly transmitting them to our frontend. Copy only the
- * part of the page we will actually inspect.
+ * holding the SLRU lock while we are examining the entries and
+ * possibly transmitting them to our frontend. Copy only the part
+ * of the page we will actually inspect.
*/
slotno = SimpleLruReadPage_ReadOnly(NotifyCtl, curpage,
InvalidTransactionId);
@@ -1953,7 +1969,7 @@ asyncQueueReadAllNotifications(void)
NotifyCtl->shared->page_buffer[slotno] + curoffset,
copysize);
/* Release lock that we got from SimpleLruReadPage_ReadOnly() */
- LWLockRelease(NotifySLRULock);
+ LWLockRelease(SimpleLruGetBankLock(NotifyCtl, curpage));
/*
* Process messages up to the stop position, end of page, or an
@@ -1994,7 +2010,7 @@ asyncQueueReadAllNotifications(void)
*
* The current page must have been fetched into page_buffer from shared
* memory. (We could access the page right in shared memory, but that
- * would imply holding the NotifySLRULock throughout this routine.)
+ * would imply holding the SLRU bank lock throughout this routine.)
*
* We stop if we reach the "stop" position, or reach a notification from an
* uncommitted transaction, or reach the end of the page.
@@ -2147,7 +2163,7 @@ asyncQueueAdvanceTail(void)
if (asyncQueuePagePrecedes(oldtailpage, boundary))
{
/*
- * SimpleLruTruncate() will ask for NotifySLRULock but will also
+ * SimpleLruTruncate() will ask for SLRU bank locks but will also
* release the lock again.
*/
SimpleLruTruncate(NotifyCtl, newtailpage);
@@ -2378,3 +2394,12 @@ ClearPendingActionsAndNotifies(void)
pendingActions = NULL;
pendingNotifies = NULL;
}
+
+/*
+ * GUC check_hook for notify_buffers
+ */
+bool
+check_notify_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("notify_buffers", newval);
+}
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 71677cf031..79778b5813 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -163,6 +163,13 @@ static const char *const BuiltinTrancheNames[] = {
[LWTRANCHE_LAUNCHER_HASH] = "LogicalRepLauncherHash",
[LWTRANCHE_DSM_REGISTRY_DSA] = "DSMRegistryDSA",
[LWTRANCHE_DSM_REGISTRY_HASH] = "DSMRegistryHash",
+ [LWTRANCHE_COMMITTS_SLRU] = "CommitTSSLRU",
+ [LWTRANCHE_MULTIXACTOFFSET_SLRU] = "MultixactOffsetSLRU",
+ [LWTRANCHE_MULTIXACTMEMBER_SLRU] = "MultixactMemberSLRU",
+ [LWTRANCHE_NOTIFY_SLRU] = "NotifySLRU",
+ [LWTRANCHE_SERIAL_SLRU] = "SerialSLRU",
+ [LWTRANCHE_SUBTRANS_SLRU] = "SubtransSLRU",
+ [LWTRANCHE_XACT_SLRU] = "XactSLRU",
};
StaticAssertDecl(lengthof(BuiltinTrancheNames) ==
@@ -776,7 +783,7 @@ GetLWLockIdentifier(uint32 classId, uint16 eventId)
* in mode.
*
* This function will not block waiting for a lock to become free - that's the
- * callers job.
+ * caller's job.
*
* Returns true if the lock isn't free and we need to wait.
*/
diff --git a/src/backend/storage/lmgr/lwlocknames.txt \
b/src/backend/storage/lmgr/lwlocknames.txt index 3d59d3646e..284d168f77 100644
--- a/src/backend/storage/lmgr/lwlocknames.txt
+++ b/src/backend/storage/lmgr/lwlocknames.txt
@@ -16,11 +16,11 @@ WALBufMappingLock 7
WALWriteLock 8
ControlFileLock 9
# 10 was CheckpointLock
-XactSLRULock 11
-SubtransSLRULock 12
+# 11 was XactSLRULock
+# 12 was SubtransSLRULock
MultiXactGenLock 13
-MultiXactOffsetSLRULock 14
-MultiXactMemberSLRULock 15
+# 14 was MultiXactOffsetSLRULock
+# 15 was MultiXactMemberSLRULock
RelCacheInitLock 16
CheckpointerCommLock 17
TwoPhaseStateLock 18
@@ -31,19 +31,19 @@ AutovacuumLock 22
AutovacuumScheduleLock 23
SyncScanLock 24
RelationMappingLock 25
-NotifySLRULock 26
+#26 was NotifySLRULock
NotifyQueueLock 27
SerializableXactHashLock 28
SerializableFinishedListLock 29
SerializablePredicateListLock 30
-SerialSLRULock 31
+# 31 was SerialSLRULock
SyncRepLock 32
BackgroundWorkerLock 33
DynamicSharedMemoryControlLock 34
AutoFileLock 35
ReplicationSlotAllocationLock 36
ReplicationSlotControlLock 37
-CommitTsSLRULock 38
+#38 was CommitTsSLRULock
CommitTsLock 39
ReplicationOriginLock 40
MultiXactTruncationLock 41
diff --git a/src/backend/storage/lmgr/predicate.c \
b/src/backend/storage/lmgr/predicate.c index eed63a05ed..1a7ff92bff 100644
--- a/src/backend/storage/lmgr/predicate.c
+++ b/src/backend/storage/lmgr/predicate.c
@@ -137,8 +137,8 @@
* SerialControlLock
* - Protects SerialControlData members
*
- * SerialSLRULock
- * - Protects SerialSlruCtl
+ * SLRU bank locks
+ * - Protect the pg_serial SLRU banks
*
* Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
@@ -213,6 +213,7 @@
#include "storage/predicate_internals.h"
#include "storage/proc.h"
#include "storage/procarray.h"
+#include "utils/guc_hooks.h"
#include "utils/rel.h"
#include "utils/snapmgr.h"
@@ -813,9 +814,9 @@ SerialInit(void)
*/
SerialSlruCtl->PagePrecedes = SerialPagePrecedesLogically;
SimpleLruInit(SerialSlruCtl, "Serial",
- NUM_SERIAL_BUFFERS, 0, SerialSLRULock, "pg_serial",
- LWTRANCHE_SERIAL_BUFFER, SYNC_HANDLER_NONE,
- false);
+ serializable_buffers, 0, "pg_serial",
+ LWTRANCHE_SERIAL_BUFFER, LWTRANCHE_SERIAL_SLRU,
+ SYNC_HANDLER_NONE, false);
#ifdef USE_ASSERT_CHECKING
SerialPagePrecedesLogicallyUnitTests();
#endif
@@ -841,6 +842,15 @@ SerialInit(void)
}
}
+/*
+ * GUC check_hook for serializable_buffers
+ */
+bool
+check_serial_buffers(int *newval, void **extra, GucSource source)
+{
+ return check_slru_buffers("serializable_buffers", newval);
+}
+
/*
* Record a committed read write serializable xid and the minimum
* commitSeqNo of any transactions to which this xid had a rw-conflict out.
@@ -854,15 +864,17 @@ SerialAdd(TransactionId xid, SerCommitSeqNo \
minConflictCommitSeqNo) int slotno;
int64 firstZeroPage;
bool isNewPage;
+ LWLock *lock;
Assert(TransactionIdIsValid(xid));
targetPage = SerialPage(xid);
+ lock = SimpleLruGetBankLock(SerialSlruCtl, targetPage);
/*
- * In this routine, we must hold both SerialControlLock and SerialSLRULock
- * simultaneously while making the SLRU data catch up with the new state
- * that we determine.
+ * In this routine, we must hold both SerialControlLock and the SLRU
+ * bank lock simultaneously while making the SLRU data catch up with
+ * the new state that we determine.
*/
LWLockAcquire(SerialControlLock, LW_EXCLUSIVE);
@@ -898,7 +910,7 @@ SerialAdd(TransactionId xid, SerCommitSeqNo \
minConflictCommitSeqNo) if (isNewPage)
serialControl->headPage = targetPage;
- LWLockAcquire(SerialSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
if (isNewPage)
{
@@ -916,7 +928,7 @@ SerialAdd(TransactionId xid, SerCommitSeqNo \
minConflictCommitSeqNo) SerialValue(slotno, xid) = minConflictCommitSeqNo;
SerialSlruCtl->shared->page_dirty[slotno] = true;
- LWLockRelease(SerialSLRULock);
+ LWLockRelease(lock);
LWLockRelease(SerialControlLock);
}
@@ -950,13 +962,13 @@ SerialGetMinConflictCommitSeqNo(TransactionId xid)
return 0;
/*
- * The following function must be called without holding SerialSLRULock,
+ * The following function must be called without holding SLRU bank lock,
* but will return with that lock held, which must then be released.
*/
slotno = SimpleLruReadPage_ReadOnly(SerialSlruCtl,
SerialPage(xid), xid);
val = SerialValue(slotno, xid);
- LWLockRelease(SerialSLRULock);
+ LWLockRelease(SimpleLruGetBankLock(SerialSlruCtl, SerialPage(xid)));
return val;
}
@@ -1367,7 +1379,7 @@ PredicateLockShmemSize(void)
/* Shared memory structures for SLRU tracking of old committed xids. */
size = add_size(size, sizeof(SerialControlData));
- size = add_size(size, SimpleLruShmemSize(NUM_SERIAL_BUFFERS, 0));
+ size = add_size(size, SimpleLruShmemSize(serializable_buffers, 0));
return size;
}
diff --git a/src/backend/utils/activity/wait_event_names.txt \
b/src/backend/utils/activity/wait_event_names.txt index cd22dca702..e896f8310c 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -292,11 +292,7 @@ SInvalWrite "Waiting to add a message to the shared catalog \
invalidation queue." WALBufMapping "Waiting to replace a page in WAL buffers."
WALWrite "Waiting for WAL buffers to be written to disk."
ControlFile "Waiting to read or update the <filename>pg_control</filename> file or \
create a new WAL file."
-XactSLRU "Waiting to access the transaction status SLRU cache."
-SubtransSLRU "Waiting to access the sub-transaction SLRU cache."
MultiXactGen "Waiting to read or update shared multixact state."
-MultiXactOffsetSLRU "Waiting to access the multixact offset SLRU cache."
-MultiXactMemberSLRU "Waiting to access the multixact member SLRU cache."
RelCacheInit "Waiting to read or update a <filename>pg_internal.init</filename> \
relation cache initialization file." CheckpointerComm "Waiting to manage fsync \
requests." TwoPhaseState "Waiting to read or update the state of prepared \
transactions." @@ -307,19 +303,16 @@ Autovacuum "Waiting to read or update the \
current state of autovacuum workers." AutovacuumSchedule "Waiting to ensure that a \
table selected for autovacuum still needs vacuuming." SyncScan "Waiting to select \
the starting location of a synchronized table scan." RelationMapping "Waiting to \
read or update a <filename>pg_filenode.map</filename> file (used to track the \
filenode assignments of certain system catalogs)."
-NotifySLRU "Waiting to access the <command>NOTIFY</command> message SLRU cache."
NotifyQueue "Waiting to read or update <command>NOTIFY</command> messages."
SerializableXactHash "Waiting to read or update information about serializable \
transactions." SerializableFinishedList "Waiting to access the list of finished \
serializable transactions." SerializablePredicateList "Waiting to access the list of \
predicate locks held by serializable transactions."
-SerialSLRU "Waiting to access the serializable transaction conflict SLRU cache."
SyncRep "Waiting to read or update information about the state of synchronous \
replication." BackgroundWorker "Waiting to read or update background worker state."
DynamicSharedMemoryControl "Waiting to read or update dynamic shared memory \
allocation information." AutoFile "Waiting to update the \
<filename>postgresql.auto.conf</filename> file." ReplicationSlotAllocation "Waiting \
to allocate or free a replication slot." ReplicationSlotControl "Waiting to read or \
update replication slot state."
-CommitTsSLRU "Waiting to access the commit timestamp SLRU cache."
CommitTs "Waiting to read or update the last value set for a transaction commit \
timestamp." ReplicationOrigin "Waiting to create, drop or use a replication origin."
MultiXactTruncation "Waiting to read or truncate multixact information."
@@ -372,6 +365,14 @@ LogicalRepLauncherDSA "Waiting to access logical replication \
launcher's dynamic LogicalRepLauncherHash "Waiting to access logical replication \
launcher's shared hash table." DSMRegistryDSA "Waiting to access dynamic shared \
memory registry's dynamic shared memory allocator." DSMRegistryHash "Waiting to \
access dynamic shared memory registry's shared hash table." +CommitTsSLRU "Waiting to \
access the commit timestamp SLRU cache." +MultiXactOffsetSLRU "Waiting to access the \
multixact offset SLRU cache." +MultiXactMemberSLRU "Waiting to access the multixact \
member SLRU cache." +NotifySLRU "Waiting to access the <command>NOTIFY</command> \
message SLRU cache." +SerialSLRU "Waiting to access the serializable transaction \
conflict SLRU cache." +SubtransSLRU "Waiting to access the sub-transaction SLRU \
cache." +XactSLRU "Waiting to access the transaction status SLRU cache."
+
#
# Wait Events - Lock
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 88b03e8fa3..7df342c70d 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -156,3 +156,12 @@ int64 VacuumPageDirty = 0;
int VacuumCostBalance = 0; /* working state for vacuum */
bool VacuumCostActive = false;
+
+/* configurable SLRU buffer sizes */
+int commit_timestamp_buffers = 0;
+int multixact_members_buffers = 32;
+int multixact_offsets_buffers = 16;
+int notify_buffers = 16;
+int serializable_buffers = 32;
+int subtransaction_buffers = 0;
+int transaction_buffers = 0;
diff --git a/src/backend/utils/misc/guc_tables.c \
b/src/backend/utils/misc/guc_tables.c index 7fe58518d7..502fd51939 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -28,6 +28,7 @@
#include "access/commit_ts.h"
#include "access/gin.h"
+#include "access/slru.h"
#include "access/toast_compression.h"
#include "access/twophase.h"
#include "access/xlog_internal.h"
@@ -2320,6 +2321,83 @@ struct config_int ConfigureNamesInt[] =
NULL, NULL, NULL
},
+ {
+ {"commit_timestamp_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the commit \
timestamp cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ &commit_timestamp_buffers,
+ 0, 0, SLRU_MAX_ALLOWED_BUFFERS,
+ check_commit_ts_buffers, NULL, NULL
+ },
+
+ {
+ {"multixact_members_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the MultiXact \
member cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ &multixact_members_buffers,
+ 32, 16, SLRU_MAX_ALLOWED_BUFFERS,
+ check_multixact_members_buffers, NULL, NULL
+ },
+
+ {
+ {"multixact_offsets_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the MultiXact \
offset cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ &multixact_offsets_buffers,
+ 16, 16, SLRU_MAX_ALLOWED_BUFFERS,
+ check_multixact_offsets_buffers, NULL, NULL
+ },
+
+ {
+ {"notify_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the \
LISTEN/NOTIFY message cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ ¬ify_buffers,
+ 16, 16, SLRU_MAX_ALLOWED_BUFFERS,
+ check_notify_buffers, NULL, NULL
+ },
+
+ {
+ {"serializable_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the \
serializable transaction cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ &serializable_buffers,
+ 32, 16, SLRU_MAX_ALLOWED_BUFFERS,
+ check_serial_buffers, NULL, NULL
+ },
+
+ {
+ {"subtransaction_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the \
sub-transaction cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ &subtransaction_buffers,
+ 0, 0, SLRU_MAX_ALLOWED_BUFFERS,
+ check_subtrans_buffers, NULL, NULL
+ },
+
+ {
+ {"transaction_buffers", PGC_POSTMASTER, RESOURCES_MEM,
+ gettext_noop("Sets the size of the dedicated buffer pool used for the transaction \
status cache."), + NULL,
+ GUC_UNIT_BLOCKS
+ },
+ &transaction_buffers,
+ 0, 0, SLRU_MAX_ALLOWED_BUFFERS,
+ check_transaction_buffers, 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/backend/utils/misc/postgresql.conf.sample \
b/src/backend/utils/misc/postgresql.conf.sample index da10b43dac..8b3a547a5e 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -50,6 +50,15 @@
#external_pid_file = '' # write an extra PID file
# (change requires restart)
+# - SLRU Buffers (change requires restart) -
+
+#commit_timestamp_buffers = 0 # memory for pg_commit_ts (0 = auto)
+#multixact_offsets_buffers = 16 # memory for pg_multixact/offsets
+#multixact_members_buffers = 32 # memory for pg_multixact/members
+#notify_buffers = 16 # memory for pg_notify
+#serializable_buffers = 32 # memory for pg_serial
+#subtransaction_buffers = 0 # memory for pg_subtrans (0 = auto)
+#transaction_buffers = 0 # memory for pg_xact (0 = auto)
#------------------------------------------------------------------------------
# CONNECTIONS AND AUTHENTICATION
diff --git a/src/include/access/clog.h b/src/include/access/clog.h
index becc365cb0..8e62917e49 100644
--- a/src/include/access/clog.h
+++ b/src/include/access/clog.h
@@ -40,7 +40,6 @@ extern void TransactionIdSetTreeStatus(TransactionId xid, int \
nsubxids, TransactionId *subxids, XidStatus status, XLogRecPtr lsn);
extern XidStatus TransactionIdGetStatus(TransactionId xid, XLogRecPtr *lsn);
-extern Size CLOGShmemBuffers(void);
extern Size CLOGShmemSize(void);
extern void CLOGShmemInit(void);
extern void BootStrapCLOG(void);
diff --git a/src/include/access/commit_ts.h b/src/include/access/commit_ts.h
index 9c6f3a35ca..82d3aa8627 100644
--- a/src/include/access/commit_ts.h
+++ b/src/include/access/commit_ts.h
@@ -27,7 +27,6 @@ extern bool TransactionIdGetCommitTsData(TransactionId xid,
extern TransactionId GetLatestCommitTsData(TimestampTz *ts,
RepOriginId *nodeid);
-extern Size CommitTsShmemBuffers(void);
extern Size CommitTsShmemSize(void);
extern void CommitTsShmemInit(void);
extern void BootStrapCommitTs(void);
diff --git a/src/include/access/multixact.h b/src/include/access/multixact.h
index 233f67dbcc..7ffd256c74 100644
--- a/src/include/access/multixact.h
+++ b/src/include/access/multixact.h
@@ -29,10 +29,6 @@
#define MaxMultiXactOffset ((MultiXactOffset) 0xFFFFFFFF)
-/* Number of SLRU buffers to use for multixact */
-#define NUM_MULTIXACTOFFSET_BUFFERS 8
-#define NUM_MULTIXACTMEMBER_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
diff --git a/src/include/access/slru.h b/src/include/access/slru.h
index 2109488654..19217f7db6 100644
--- a/src/include/access/slru.h
+++ b/src/include/access/slru.h
@@ -17,6 +17,27 @@
#include "storage/lwlock.h"
#include "storage/sync.h"
+/*
+ * SLRU bank size for slotno hash banks. Limit the bank size to 16 because we
+ * perform sequential search within a bank (while looking for a target page or
+ * while doing victim buffer search) and if we keep this size big then it may
+ * affect the performance.
+ */
+#define SLRU_BANK_SIZE 16
+
+/*
+ * Number of bank locks to protect the in memory buffer slot access within a
+ * SLRU bank. If the number of banks are <= SLRU_MAX_BANKLOCKS then there will
+ * be one lock per bank; otherwise each lock will protect multiple banks depends
+ * upon the number of banks.
+ */
+#define SLRU_MAX_BANKLOCKS 128
+
+/*
+ * To avoid overflowing internal arithmetic and the size_t data type, the
+ * number of buffers must not exceed this number.
+ */
+#define SLRU_MAX_ALLOWED_BUFFERS ((1024 * 1024 * 1024) / BLCKSZ)
/*
* Define SLRU segment size. A page is the same BLCKSZ as is used everywhere
@@ -55,8 +76,6 @@ typedef enum
*/
typedef struct SlruSharedData
{
- LWLock *ControlLock;
-
/* Number of buffers managed by this SLRU structure */
int num_slots;
@@ -69,8 +88,30 @@ typedef struct SlruSharedData
bool *page_dirty;
int64 *page_number;
int *page_lru_count;
+
+ /* The buffer_locks protects the I/O on each buffer slots */
LWLockPadded *buffer_locks;
+ /* Locks to protect the in memory buffer slot access in SLRU bank. */
+ LWLockPadded *bank_locks;
+
+ /*----------
+ * A bank-wise LRU counter is maintained because we do a victim buffer
+ * search within a bank. Furthermore, manipulating an individual bank
+ * counter avoids frequent cache invalidation since we update it every time
+ * we access the page.
+ *
+ * We mark a page "most recently used" by setting
+ * page_lru_count[slotno] = ++bank_cur_lru_count[bankno];
+ * The oldest page in the bank is therefore the one with the highest value
+ * of
+ * bank_cur_lru_count[bankno] - 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 *bank_cur_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
@@ -82,17 +123,6 @@ typedef struct SlruSharedData
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;
-
/*
* 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
@@ -145,15 +175,35 @@ typedef struct SlruCtlData
* it's always the same, it doesn't need to be in shared memory.
*/
char Dir[64];
+
+ /*
+ * Mask for slotno banks, considering 1GB SLRU buffer pool size and the
+ * SLRU_BANK_SIZE bits16 should be sufficient for the bank mask.
+ */
+ bits16 bank_mask;
} SlruCtlData;
typedef SlruCtlData *SlruCtl;
+/*
+ * Get the SLRU bank lock for given SlruCtl and the pageno.
+ *
+ * This lock needs to be acquired to access the slru buffer slots in the
+ * respective bank.
+ */
+static inline LWLock *
+SimpleLruGetBankLock(SlruCtl ctl, int64 pageno)
+{
+ int banklockno;
+
+ banklockno = (pageno & ctl->bank_mask) % SLRU_MAX_BANKLOCKS;
+ return &(ctl->shared->bank_locks[banklockno].lock);
+}
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,
- SyncRequestHandler sync_handler,
+ const char *subdir, int buffer_tranche_id,
+ int bank_tranche_id, SyncRequestHandler sync_handler,
bool long_segment_names);
extern int SimpleLruZeroPage(SlruCtl ctl, int64 pageno);
extern int SimpleLruReadPage(SlruCtl ctl, int64 pageno, bool write_ok,
@@ -182,5 +232,6 @@ extern bool SlruScanDirCbReportPresence(SlruCtl ctl, char \
*filename, int64 segpage, void *data);
extern bool SlruScanDirCbDeleteAll(SlruCtl ctl, char *filename, int64 segpage,
void *data);
+extern bool check_slru_buffers(const char *name, int *newval);
#endif /* SLRU_H */
diff --git a/src/include/access/subtrans.h b/src/include/access/subtrans.h
index b0d2ad57e5..e2213cf3fd 100644
--- a/src/include/access/subtrans.h
+++ b/src/include/access/subtrans.h
@@ -11,9 +11,6 @@
#ifndef SUBTRANS_H
#define SUBTRANS_H
-/* Number of SLRU buffers to use for subtrans */
-#define NUM_SUBTRANS_BUFFERS 32
-
extern void SubTransSetParent(TransactionId xid, TransactionId parent);
extern TransactionId SubTransGetParent(TransactionId xid);
extern TransactionId SubTransGetTopmostTransaction(TransactionId xid);
diff --git a/src/include/commands/async.h b/src/include/commands/async.h
index 80b8583421..78daa25fa0 100644
--- a/src/include/commands/async.h
+++ b/src/include/commands/async.h
@@ -15,11 +15,6 @@
#include <signal.h>
-/*
- * The number of SLRU page buffers we use for the notification queue.
- */
-#define NUM_NOTIFY_BUFFERS 8
-
extern PGDLLIMPORT bool Trace_notify;
extern PGDLLIMPORT int max_notify_queue_pages;
extern PGDLLIMPORT volatile sig_atomic_t notifyInterruptPending;
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 0b01c1f093..39b8ed9425 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -178,6 +178,14 @@ extern PGDLLIMPORT int MaxConnections;
extern PGDLLIMPORT int max_worker_processes;
extern PGDLLIMPORT int max_parallel_workers;
+extern PGDLLIMPORT int commit_timestamp_buffers;
+extern PGDLLIMPORT int multixact_members_buffers;
+extern PGDLLIMPORT int multixact_offsets_buffers;
+extern PGDLLIMPORT int notify_buffers;
+extern PGDLLIMPORT int serializable_buffers;
+extern PGDLLIMPORT int subtransaction_buffers;
+extern PGDLLIMPORT int transaction_buffers;
+
extern PGDLLIMPORT int MyProcPid;
extern PGDLLIMPORT pg_time_t MyStartTime;
extern PGDLLIMPORT TimestampTz MyStartTimestamp;
diff --git a/src/include/storage/lwlock.h b/src/include/storage/lwlock.h
index 50a65e046d..10bea8c595 100644
--- a/src/include/storage/lwlock.h
+++ b/src/include/storage/lwlock.h
@@ -209,6 +209,13 @@ typedef enum BuiltinTrancheIds
LWTRANCHE_LAUNCHER_HASH,
LWTRANCHE_DSM_REGISTRY_DSA,
LWTRANCHE_DSM_REGISTRY_HASH,
+ LWTRANCHE_COMMITTS_SLRU,
+ LWTRANCHE_MULTIXACTMEMBER_SLRU,
+ LWTRANCHE_MULTIXACTOFFSET_SLRU,
+ LWTRANCHE_NOTIFY_SLRU,
+ LWTRANCHE_SERIAL_SLRU,
+ LWTRANCHE_SUBTRANS_SLRU,
+ LWTRANCHE_XACT_SLRU,
LWTRANCHE_FIRST_USER_DEFINED,
} BuiltinTrancheIds;
diff --git a/src/include/storage/predicate.h b/src/include/storage/predicate.h
index a7edd38fa9..14ee9b94a2 100644
--- a/src/include/storage/predicate.h
+++ b/src/include/storage/predicate.h
@@ -26,10 +26,6 @@ extern PGDLLIMPORT int max_predicate_locks_per_xact;
extern PGDLLIMPORT int max_predicate_locks_per_relation;
extern PGDLLIMPORT int max_predicate_locks_per_page;
-
-/* Number of SLRU buffers to use for Serial SLRU */
-#define NUM_SERIAL_BUFFERS 16
-
/*
* A handle used for sharing SERIALIZABLEXACT objects between the participants
* in a parallel query.
diff --git a/src/include/utils/guc_hooks.h b/src/include/utils/guc_hooks.h
index 5300c44f3b..44b0cbf9a1 100644
--- a/src/include/utils/guc_hooks.h
+++ b/src/include/utils/guc_hooks.h
@@ -46,6 +46,8 @@ extern bool check_client_connection_check_interval(int *newval, \
void **extra, extern bool check_client_encoding(char **newval, void **extra, \
GucSource source); extern void assign_client_encoding(const char *newval, void \
*extra); extern bool check_cluster_name(char **newval, void **extra, GucSource \
source); +extern bool check_commit_ts_buffers(int *newval, void **extra,
+ GucSource source);
extern const char *show_data_directory_mode(void);
extern bool check_datestyle(char **newval, void **extra, GucSource source);
extern void assign_datestyle(const char *newval, void *extra);
@@ -91,6 +93,11 @@ extern bool check_max_worker_processes(int *newval, void **extra,
GucSource source);
extern bool check_max_stack_depth(int *newval, void **extra, GucSource source);
extern void assign_max_stack_depth(int newval, void *extra);
+extern bool check_multixact_members_buffers(int *newval, void **extra,
+ GucSource source);
+extern bool check_multixact_offsets_buffers(int *newval, void **extra,
+ GucSource source);
+extern bool check_notify_buffers(int *newval, void **extra, GucSource source);
extern bool check_primary_slot_name(char **newval, void **extra,
GucSource source);
extern bool check_random_seed(double *newval, void **extra, GucSource source);
@@ -122,12 +129,15 @@ extern void assign_role(const char *newval, void *extra);
extern const char *show_role(void);
extern bool check_search_path(char **newval, void **extra, GucSource source);
extern void assign_search_path(const char *newval, void *extra);
+extern bool check_serial_buffers(int *newval, void **extra, GucSource source);
extern bool check_session_authorization(char **newval, void **extra, GucSource \
source); extern void assign_session_authorization(const char *newval, void *extra);
extern void assign_session_replication_role(int newval, void *extra);
extern void assign_stats_fetch_consistency(int newval, void *extra);
extern bool check_ssl(bool *newval, void **extra, GucSource source);
extern bool check_stage_log_stats(bool *newval, void **extra, GucSource source);
+extern bool check_subtrans_buffers(int *newval, void **extra,
+ GucSource source);
extern bool check_synchronous_standby_names(char **newval, void **extra,
GucSource source);
extern void assign_synchronous_standby_names(const char *newval, void *extra);
@@ -152,6 +162,7 @@ extern const char *show_timezone(void);
extern bool check_timezone_abbreviations(char **newval, void **extra,
GucSource source);
extern void assign_timezone_abbreviations(const char *newval, void *extra);
+extern bool check_transaction_buffers(int *newval, void **extra, GucSource source);
extern bool check_transaction_deferrable(bool *newval, void **extra, GucSource \
source); extern bool check_transaction_isolation(int *newval, void **extra, \
GucSource source); extern bool check_transaction_read_only(bool *newval, void \
**extra, GucSource source);
diff --git a/src/test/modules/test_slru/test_slru.c \
b/src/test/modules/test_slru/test_slru.c index 4b31f331ca..068a21f125 100644
--- a/src/test/modules/test_slru/test_slru.c
+++ b/src/test/modules/test_slru/test_slru.c
@@ -40,10 +40,6 @@ PG_FUNCTION_INFO_V1(test_slru_delete_all);
/* Number of SLRU page slots */
#define NUM_TEST_BUFFERS 16
-/* SLRU control lock */
-LWLock TestSLRULock;
-#define TestSLRULock (&TestSLRULock)
-
static SlruCtlData TestSlruCtlData;
#define TestSlruCtl (&TestSlruCtlData)
@@ -63,9 +59,9 @@ test_slru_page_write(PG_FUNCTION_ARGS)
int64 pageno = PG_GETARG_INT64(0);
char *data = text_to_cstring(PG_GETARG_TEXT_PP(1));
int slotno;
+ LWLock *lock = SimpleLruGetBankLock(TestSlruCtl, pageno);
- LWLockAcquire(TestSLRULock, LW_EXCLUSIVE);
-
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = SimpleLruZeroPage(TestSlruCtl, pageno);
/* these should match */
@@ -80,7 +76,7 @@ test_slru_page_write(PG_FUNCTION_ARGS)
BLCKSZ - 1);
SimpleLruWritePage(TestSlruCtl, slotno);
- LWLockRelease(TestSLRULock);
+ LWLockRelease(lock);
PG_RETURN_VOID();
}
@@ -99,13 +95,14 @@ test_slru_page_read(PG_FUNCTION_ARGS)
bool write_ok = PG_GETARG_BOOL(1);
char *data = NULL;
int slotno;
+ LWLock *lock = SimpleLruGetBankLock(TestSlruCtl, pageno);
/* find page in buffers, reading it if necessary */
- LWLockAcquire(TestSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
slotno = SimpleLruReadPage(TestSlruCtl, pageno,
write_ok, InvalidTransactionId);
data = (char *) TestSlruCtl->shared->page_buffer[slotno];
- LWLockRelease(TestSLRULock);
+ LWLockRelease(lock);
PG_RETURN_TEXT_P(cstring_to_text(data));
}
@@ -116,14 +113,15 @@ test_slru_page_readonly(PG_FUNCTION_ARGS)
int64 pageno = PG_GETARG_INT64(0);
char *data = NULL;
int slotno;
+ LWLock *lock = SimpleLruGetBankLock(TestSlruCtl, pageno);
/* find page in buffers, reading it if necessary */
slotno = SimpleLruReadPage_ReadOnly(TestSlruCtl,
pageno,
InvalidTransactionId);
- Assert(LWLockHeldByMe(TestSLRULock));
+ Assert(LWLockHeldByMe(lock));
data = (char *) TestSlruCtl->shared->page_buffer[slotno];
- LWLockRelease(TestSLRULock);
+ LWLockRelease(lock);
PG_RETURN_TEXT_P(cstring_to_text(data));
}
@@ -133,10 +131,11 @@ test_slru_page_exists(PG_FUNCTION_ARGS)
{
int64 pageno = PG_GETARG_INT64(0);
bool found;
+ LWLock *lock = SimpleLruGetBankLock(TestSlruCtl, pageno);
- LWLockAcquire(TestSLRULock, LW_EXCLUSIVE);
+ LWLockAcquire(lock, LW_EXCLUSIVE);
found = SimpleLruDoesPhysicalPageExist(TestSlruCtl, pageno);
- LWLockRelease(TestSLRULock);
+ LWLockRelease(lock);
PG_RETURN_BOOL(found);
}
@@ -221,6 +220,7 @@ test_slru_shmem_startup(void)
const bool long_segment_names = true;
const char slru_dir_name[] = "pg_test_slru";
int test_tranche_id;
+ int test_buffer_tranche_id;
if (prev_shmem_startup_hook)
prev_shmem_startup_hook();
@@ -234,12 +234,15 @@ test_slru_shmem_startup(void)
/* initialize the SLRU facility */
test_tranche_id = LWLockNewTrancheId();
LWLockRegisterTranche(test_tranche_id, "test_slru_tranche");
- LWLockInitialize(TestSLRULock, test_tranche_id);
+
+ test_buffer_tranche_id = LWLockNewTrancheId();
+ LWLockRegisterTranche(test_tranche_id, "test_buffer_tranche");
TestSlruCtl->PagePrecedes = test_slru_page_precedes_logically;
SimpleLruInit(TestSlruCtl, "TestSLRU",
- NUM_TEST_BUFFERS, 0, TestSLRULock, slru_dir_name,
- test_tranche_id, SYNC_HANDLER_NONE, long_segment_names);
+ NUM_TEST_BUFFERS, 0, slru_dir_name,
+ test_buffer_tranche_id, test_tranche_id, SYNC_HANDLER_NONE,
+ long_segment_names);
}
void
--
2.39.2
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic