</listitem>
</varlistentry>
- <varlistentry id="guc-track-wal-io-timing" xreflabel="track_wal_io_timing">
- <term><varname>track_wal_io_timing</varname> (<type>boolean</type>)
- <indexterm>
- <primary><varname>track_wal_io_timing</varname> configuration parameter</primary>
- </indexterm>
- </term>
- <listitem>
- <para>
- Enables timing of WAL I/O calls. This parameter is off by default,
- as it will repeatedly query the operating system for the current time,
- which may cause significant overhead on some platforms.
- You can use the <application>pg_test_timing</application> tool to
- measure the overhead of timing on your system.
- I/O timing information is
- displayed in <link linkend="monitoring-pg-stat-wal-view">
- <structname>pg_stat_wal</structname></link>.
- Only superusers and users with the appropriate <literal>SET</literal>
- privilege can change this setting.
- </para>
- </listitem>
- </varlistentry>
-
<varlistentry id="guc-track-functions" xreflabel="track_functions">
<term><varname>track_functions</varname> (<type>enum</type>)
<indexterm>
of block read, write, extend, and fsync times.
</para>
- <para>
- The parameter <xref linkend="guc-track-wal-io-timing"/> enables monitoring
- of WAL write and fsync times.
- </para>
-
<para>
Normally these parameters are set in <filename>postgresql.conf</filename> so
that they apply to all server processes, but it is possible to turn
</para></entry>
</row>
- <row>
- <entry role="catalog_table_entry"><para role="column_definition">
- <structfield>wal_write</structfield> <type>bigint</type>
- </para>
- <para>
- Number of times WAL buffers were written out to disk via
- <function>XLogWrite</function> request.
- See <xref linkend="wal-configuration"/> for more information about
- the internal WAL function <function>XLogWrite</function>.
- </para></entry>
- </row>
-
- <row>
- <entry role="catalog_table_entry"><para role="column_definition">
- <structfield>wal_sync</structfield> <type>bigint</type>
- </para>
- <para>
- Number of times WAL files were synced to disk via
- <function>issue_xlog_fsync</function> request
- (if <xref linkend="guc-fsync"/> is <literal>on</literal> and
- <xref linkend="guc-wal-sync-method"/> is either
- <literal>fdatasync</literal>, <literal>fsync</literal> or
- <literal>fsync_writethrough</literal>, otherwise zero).
- See <xref linkend="wal-configuration"/> for more information about
- the internal WAL function <function>issue_xlog_fsync</function>.
- </para></entry>
- </row>
-
- <row>
- <entry role="catalog_table_entry"><para role="column_definition">
- <structfield>wal_write_time</structfield> <type>double precision</type>
- </para>
- <para>
- Total amount of time spent writing WAL buffers to disk via
- <function>XLogWrite</function> request, in milliseconds
- (if <xref linkend="guc-track-wal-io-timing"/> is enabled,
- otherwise zero). This includes the sync time when
- <varname>wal_sync_method</varname> is either
- <literal>open_datasync</literal> or <literal>open_sync</literal>.
- </para></entry>
- </row>
-
- <row>
- <entry role="catalog_table_entry"><para role="column_definition">
- <structfield>wal_sync_time</structfield> <type>double precision</type>
- </para>
- <para>
- Total amount of time spent syncing WAL files to disk via
- <function>issue_xlog_fsync</function> request, in milliseconds
- (if <varname>track_wal_io_timing</varname> is enabled,
- <varname>fsync</varname> is <literal>on</literal>, and
- <varname>wal_sync_method</varname> is either
- <literal>fdatasync</literal>, <literal>fsync</literal> or
- <literal>fsync_writethrough</literal>, otherwise zero).
- </para></entry>
- </row>
-
<row>
<entry role="catalog_table_entry"><para role="column_definition">
<structfield>stats_reset</structfield> <type>timestamp with time zone</type>
int wal_retrieve_retry_interval = 5000;
int max_slot_wal_keep_size_mb = -1;
int wal_decode_buffer_size = 512 * 1024;
-bool track_wal_io_timing = false;
#ifdef WAL_DEBUG
bool XLOG_DEBUG = false;
errno = 0;
/*
- * Measure I/O timing to write WAL data, for pg_stat_io and/or
- * pg_stat_wal.
+ * Measure I/O timing to write WAL data, for pg_stat_io.
*/
- start = pgstat_prepare_io_time(track_io_timing || track_wal_io_timing);
+ start = pgstat_prepare_io_time();
pgstat_report_wait_start(WAIT_EVENT_WAL_WRITE);
written = pg_pwrite(openLogFile, from, nleft, startoffset);
pgstat_count_io_op_time(IOOBJECT_WAL, IOCONTEXT_NORMAL,
IOOP_WRITE, start, 1, written);
- /*
- * Increment the I/O timing and the number of times WAL data
- * were written out to disk.
- */
- if (track_wal_io_timing)
- {
- instr_time end;
-
- INSTR_TIME_SET_CURRENT(end);
- INSTR_TIME_ACCUM_DIFF(PendingWalStats.wal_write_time, end, start);
- }
-
- PendingWalStats.wal_write++;
-
if (written <= 0)
{
char xlogfname[MAXFNAMELEN];
errmsg("could not create file \"%s\": %m", tmppath)));
/* Measure I/O timing when initializing segment */
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
pgstat_report_wait_start(WAIT_EVENT_WAL_INIT_WRITE);
save_errno = 0;
}
/* Measure I/O timing when flushing segment */
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
pgstat_report_wait_start(WAIT_EVENT_WAL_INIT_SYNC);
if (pg_fsync(fd) != 0)
return;
/*
- * Measure I/O timing to sync the WAL file for pg_stat_io and/or
- * pg_stat_wal.
+ * Measure I/O timing to sync the WAL file for pg_stat_io.
*/
- start = pgstat_prepare_io_time(track_io_timing || track_wal_io_timing);
+ start = pgstat_prepare_io_time();
pgstat_report_wait_start(WAIT_EVENT_WAL_SYNC);
switch (wal_sync_method)
pgstat_report_wait_end();
- /*
- * Increment the I/O timing and the number of times WAL files were synced.
- */
- if (track_wal_io_timing)
- {
- instr_time end;
-
- INSTR_TIME_SET_CURRENT(end);
- INSTR_TIME_ACCUM_DIFF(PendingWalStats.wal_sync_time, end, start);
- }
-
pgstat_count_io_op_time(IOOBJECT_WAL, IOCONTEXT_NORMAL, IOOP_FSYNC,
start, 1, 0);
-
- PendingWalStats.wal_sync++;
}
/*
#ifndef FRONTEND
/* Measure I/O timing when reading segment */
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
#endif
readOff = targetPageOff;
/* Measure I/O timing when reading segment */
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff);
w.wal_fpi,
w.wal_bytes,
w.wal_buffers_full,
- w.wal_write,
- w.wal_sync,
- w.wal_write_time,
- w.wal_sync_time,
w.stats_reset
FROM pg_stat_get_wal() w;
io_pages[io_buffers_len++] = BufferGetBlock(buffers[i]);
}
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
smgrreadv(operation->smgr, forknum, io_first_block, io_pages, io_buffers_len);
pgstat_count_io_op_time(io_object, io_context, IOOP_READ, io_start,
1, io_buffers_len * BLCKSZ);
}
}
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
/*
* Note: if smgrzeroextend fails, we will end up with buffers that are
*/
bufToWrite = PageSetChecksumCopy((Page) bufBlock, buf->tag.blockNum);
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
/*
* bufToWrite is either the shared buffer or a copy, as appropriate.
PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
smgrwrite(srel,
BufTagGetForkNum(&bufHdr->tag),
sort_pending_writebacks(wb_context->pending_writebacks,
wb_context->nr_pending);
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
/*
* Coalesce neighbouring writes, but nothing else. For that we iterate
PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
/* And write... */
smgrwrite(oreln,
}
}
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
/* actually extend relation */
smgrzeroextend(bmr.smgr, fork, first_block, extend_by, false);
ereport(DEBUG1,
(errmsg_internal("could not forward fsync request because request queue is full")));
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
if (FileSync(seg->mdfd_vfd, WAIT_EVENT_DATA_FILE_SYNC) < 0)
ereport(data_sync_elevel(ERROR),
need_to_close = true;
}
- io_start = pgstat_prepare_io_time(track_io_timing);
+ io_start = pgstat_prepare_io_time();
/* Sync the file. */
result = FileSync(file, WAIT_EVENT_DATA_FILE_SYNC);
}
/*
- * Initialize the internal timing for an IO operation, depending on an
- * IO timing GUC.
+ * Initialize the internal timing for an IO operation.
*/
instr_time
-pgstat_prepare_io_time(bool track_io_guc)
+pgstat_prepare_io_time(void)
{
instr_time io_start;
- if (track_io_guc)
+ if (track_io_timing)
INSTR_TIME_SET_CURRENT(io_start);
else
{
#include "utils/pgstat_internal.h"
-PgStat_PendingWalStats PendingWalStats = {0};
-
/*
* WAL usage counters saved from pgWalUsage at the previous call to
* pgstat_report_wal(). This is used to calculate how much WAL usage
#define WALSTAT_ACC(fld, var_to_add) \
(stats_shmem->stats.fld += var_to_add.fld)
-#define WALSTAT_ACC_INSTR_TIME(fld) \
- (stats_shmem->stats.fld += INSTR_TIME_GET_MICROSEC(PendingWalStats.fld))
WALSTAT_ACC(wal_records, wal_usage_diff);
WALSTAT_ACC(wal_fpi, wal_usage_diff);
WALSTAT_ACC(wal_bytes, wal_usage_diff);
WALSTAT_ACC(wal_buffers_full, wal_usage_diff);
- WALSTAT_ACC(wal_write, PendingWalStats);
- WALSTAT_ACC(wal_sync, PendingWalStats);
- WALSTAT_ACC_INSTR_TIME(wal_write_time);
- WALSTAT_ACC_INSTR_TIME(wal_sync_time);
-#undef WALSTAT_ACC_INSTR_TIME
#undef WALSTAT_ACC
LWLockRelease(&stats_shmem->lock);
*/
prevWalUsage = pgWalUsage;
- /*
- * Clear out the statistics buffer, so it can be re-used.
- */
- MemSet(&PendingWalStats, 0, sizeof(PendingWalStats));
-
return false;
}
}
/*
- * To determine whether any WAL activity has occurred since last time, not
- * only the number of generated WAL records but also the numbers of WAL
- * writes and syncs need to be checked. Because even transaction that
- * generates no WAL records can write or sync WAL data when flushing the
- * data pages.
+ * To determine whether WAL usage happened.
*/
bool
pgstat_wal_have_pending_cb(void)
{
- return pgWalUsage.wal_records != prevWalUsage.wal_records ||
- PendingWalStats.wal_write != 0 ||
- PendingWalStats.wal_sync != 0;
+ return pgWalUsage.wal_records != prevWalUsage.wal_records;
}
void
Datum
pg_stat_get_wal(PG_FUNCTION_ARGS)
{
-#define PG_STAT_GET_WAL_COLS 9
+#define PG_STAT_GET_WAL_COLS 5
TupleDesc tupdesc;
Datum values[PG_STAT_GET_WAL_COLS] = {0};
bool nulls[PG_STAT_GET_WAL_COLS] = {0};
NUMERICOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 4, "wal_buffers_full",
INT8OID, -1, 0);
- TupleDescInitEntry(tupdesc, (AttrNumber) 5, "wal_write",
- INT8OID, -1, 0);
- TupleDescInitEntry(tupdesc, (AttrNumber) 6, "wal_sync",
- INT8OID, -1, 0);
- TupleDescInitEntry(tupdesc, (AttrNumber) 7, "wal_write_time",
- FLOAT8OID, -1, 0);
- TupleDescInitEntry(tupdesc, (AttrNumber) 8, "wal_sync_time",
- FLOAT8OID, -1, 0);
- TupleDescInitEntry(tupdesc, (AttrNumber) 9, "stats_reset",
+ TupleDescInitEntry(tupdesc, (AttrNumber) 5, "stats_reset",
TIMESTAMPTZOID, -1, 0);
BlessTupleDesc(tupdesc);
Int32GetDatum(-1));
values[3] = Int64GetDatum(wal_stats->wal_buffers_full);
- values[4] = Int64GetDatum(wal_stats->wal_write);
- values[5] = Int64GetDatum(wal_stats->wal_sync);
-
- /* Convert counters from microsec to millisec for display */
- values[6] = Float8GetDatum(((double) wal_stats->wal_write_time) / 1000.0);
- values[7] = Float8GetDatum(((double) wal_stats->wal_sync_time) / 1000.0);
- values[8] = TimestampTzGetDatum(wal_stats->stat_reset_timestamp);
+ values[4] = TimestampTzGetDatum(wal_stats->stat_reset_timestamp);
/* Returns the record as Datum */
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
false,
NULL, NULL, NULL
},
- {
- {"track_wal_io_timing", PGC_SUSET, STATS_CUMULATIVE,
- gettext_noop("Collects timing statistics for WAL I/O activity."),
- NULL
- },
- &track_wal_io_timing,
- false,
- NULL, NULL, NULL
- },
{
{"update_process_title", PGC_SUSET, PROCESS_TITLE,
#track_counts = on
#track_cost_delay_timing = off
#track_io_timing = off
-#track_wal_io_timing = off
#track_functions = none # none, pl, all
#stats_fetch_consistency = cache # cache, none, snapshot
extern PGDLLIMPORT bool log_checkpoints;
extern PGDLLIMPORT int CommitDelay;
extern PGDLLIMPORT int CommitSiblings;
-extern PGDLLIMPORT bool track_wal_io_timing;
extern PGDLLIMPORT int wal_decode_buffer_size;
extern PGDLLIMPORT int CheckPointSegments;
*/
/* yyyymmddN */
-#define CATALOG_VERSION_NO 202502212
+#define CATALOG_VERSION_NO 202502241
#endif
{ oid => '1136', descr => 'statistics: information about WAL activity',
proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
proparallel => 'r', prorettype => 'record', proargtypes => '',
- proallargtypes => '{int8,int8,numeric,int8,int8,int8,float8,float8,timestamptz}',
- proargmodes => '{o,o,o,o,o,o,o,o,o}',
- proargnames => '{wal_records,wal_fpi,wal_bytes,wal_buffers_full,wal_write,wal_sync,wal_write_time,wal_sync_time,stats_reset}',
+ proallargtypes => '{int8,int8,numeric,int8,timestamptz}',
+ proargmodes => '{o,o,o,o,o}',
+ proargnames => '{wal_records,wal_fpi,wal_bytes,wal_buffers_full,stats_reset}',
prosrc => 'pg_stat_get_wal' },
{ oid => '6248', descr => 'statistics: information about WAL prefetching',
proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
* ------------------------------------------------------------
*/
-#define PGSTAT_FILE_FORMAT_ID 0x01A5BCB3
+#define PGSTAT_FILE_FORMAT_ID 0x01A5BCB4
typedef struct PgStat_ArchiverStats
{
PgStat_Counter wal_fpi;
uint64 wal_bytes;
PgStat_Counter wal_buffers_full;
- PgStat_Counter wal_write;
- PgStat_Counter wal_sync;
- PgStat_Counter wal_write_time;
- PgStat_Counter wal_sync_time;
TimestampTz stat_reset_timestamp;
} PgStat_WalStats;
-/*
- * This struct stores wal-related durations as instr_time, which makes it
- * cheaper and easier to accumulate them, by not requiring type
- * conversions. During stats flush instr_time will be converted into
- * microseconds.
- */
-typedef struct PgStat_PendingWalStats
-{
- PgStat_Counter wal_write;
- PgStat_Counter wal_sync;
- instr_time wal_write_time;
- instr_time wal_sync_time;
-} PgStat_PendingWalStats;
-
-
/*
* Functions in pgstat.c
*/
BackendType bktype);
extern void pgstat_count_io_op(IOObject io_object, IOContext io_context,
IOOp io_op, uint32 cnt, uint64 bytes);
-extern instr_time pgstat_prepare_io_time(bool track_io_guc);
+extern instr_time pgstat_prepare_io_time(void);
extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
IOOp io_op, instr_time start_time,
uint32 cnt, uint64 bytes);
/* updated by the traffic cop and in errfinish() */
extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
-
-/*
- * Variables in pgstat_wal.c
- */
-
-/* updated directly by backends and background processes */
-extern PGDLLIMPORT PgStat_PendingWalStats PendingWalStats;
-
-
#endif /* PGSTAT_H */
wal_fpi,
wal_bytes,
wal_buffers_full,
- wal_write,
- wal_sync,
- wal_write_time,
- wal_sync_time,
stats_reset
- FROM pg_stat_get_wal() w(wal_records, wal_fpi, wal_bytes, wal_buffers_full, wal_write, wal_sync, wal_write_time, wal_sync_time, stats_reset);
+ FROM pg_stat_get_wal() w(wal_records, wal_fpi, wal_bytes, wal_buffers_full, stats_reset);
pg_stat_wal_receiver| SELECT pid,
status,
receive_start_lsn,
PgStat_LocalState
PgStat_PendingDroppedStatsItem
PgStat_PendingIO
-PgStat_PendingWalStats
PgStat_SLRUStats
PgStat_ShmemControl
PgStat_Snapshot
projects / postgresql.git / commitdiff