v30 attached rebased and pgstat_io_ops.c builds with meson now also, I tested with pgstat_report_stat() only flushing when forced and tests still pass
From 153b06200b36891c9e07df526a86dbd913e36e3e Mon Sep 17 00:00:00 2001 From: Melanie Plageman <melanieplage...@gmail.com> Date: Thu, 11 Aug 2022 18:28:50 -0400 Subject: [PATCH v30 3/3] Add system view tracking IO ops per backend type
Add pg_stat_io, a system view which tracks the number of IOOps (allocs, extends, fsyncs, reads, and writes) done through each IOContext (shared buffers, local buffers, strategy buffers) by each type of backend (e.g. client backend, checkpointer). Some BackendTypes do not accumulate IO operations statistics and will not be included in the view. Some IOContexts are not used by some BackendTypes and will not be in the view. For example, checkpointer does not use a BufferAccessStrategy (currently), so there will be no row for the "strategy" IOContext for checkpointer. Some IOOps are invalid in combination with certain IOContexts. Those cells will be NULL in the view to distinguish between 0 observed IOOps of that type and an invalid combination. For example, local buffers are not fsync'd so cells for all BackendTypes for IOCONTEXT_STRATEGY and IOOP_FSYNC will be NULL. Some BackendTypes never perform certain IOOps. Those cells will also be NULL in the view. For example, bgwriter should not perform reads. View stats are populated with statistics incremented when a backend performs an IO Operation and maintained by the cumulative statistics subsystem. Each row of the view shows stats for a particular BackendType and IOContext combination (e.g. shared buffer accesses by checkpointer) and each column in the view is the total number of IO Operations done (e.g. writes). So a cell in the view would be, for example, the number of shared buffers written by checkpointer since the last stats reset. Note that some of the cells in the view are redundant with fields in pg_stat_bgwriter (e.g. buffers_backend), however these have been kept in pg_stat_bgwriter for backwards compatibility. Deriving the redundant pg_stat_bgwriter stats from the IO operations stats structures was also problematic due to the separate reset targets for 'bgwriter' and 'io'. Suggested by Andres Freund Author: Melanie Plageman <melanieplage...@gmail.com> Reviewed-by: Andres Freund <and...@anarazel.de> Reviewed-by: Justin Pryzby <pry...@telsasoft.com> Reviewed-by: Kyotaro Horiguchi <horikyota....@gmail.com> Discussion: https://www.postgresql.org/message-id/flat/20200124195226.lth52iydq2n2uilq%40alap3.anarazel.de --- doc/src/sgml/monitoring.sgml | 115 ++++++++++++++- src/backend/catalog/system_views.sql | 12 ++ src/backend/utils/adt/pgstatfuncs.c | 117 ++++++++++++++++ src/include/catalog/pg_proc.dat | 9 ++ src/test/regress/expected/rules.out | 9 ++ src/test/regress/expected/stats.out | 202 +++++++++++++++++++++++++++ src/test/regress/sql/stats.sql | 104 ++++++++++++++ 7 files changed, 567 insertions(+), 1 deletion(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 9440b41770..c7ca078bc8 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -448,6 +448,15 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser </entry> </row> + <row> + <entry><structname>pg_stat_io</structname><indexterm><primary>pg_stat_io</primary></indexterm></entry> + <entry>A row for each IO Context for each backend type showing + statistics about backend IO operations. See + <link linkend="monitoring-pg-stat-io-view"> + <structname>pg_stat_io</structname></link> for details. + </entry> + </row> + <row> <entry><structname>pg_stat_wal</structname><indexterm><primary>pg_stat_wal</primary></indexterm></entry> <entry>One row only, showing statistics about WAL activity. See @@ -3600,7 +3609,111 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i <structfield>stats_reset</structfield> <type>timestamp with time zone</type> </para> <para> - Time at which these statistics were last reset + Time at which these statistics were last reset. + </para></entry> + </row> + </tbody> + </tgroup> + </table> + + </sect2> + + <sect2 id="monitoring-pg-stat-io-view"> + <title><structname>pg_stat_io</structname></title> + + <indexterm> + <primary>pg_stat_io</primary> + </indexterm> + + <para> + The <structname>pg_stat_io</structname> view has a row for each backend type + and IO Context containing global data for the cluster on IO Operations done + by that backend type in that IO Context. + </para> + + <table id="pg-stat-io-view" xreflabel="pg_stat_io"> + <title><structname>pg_stat_io</structname> View</title> + <tgroup cols="1"> + <thead> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + <tbody> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>backend_type</structfield> <type>text</type> + </para> + <para> + Type of backend (e.g. background worker, autovacuum worker). + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>io_context</structfield> <type>text</type> + </para> + <para> + IO Context used (e.g. shared buffers, local buffers). + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>alloc</structfield> <type>bigint</type> + </para> + <para> + Number of buffers allocated. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>read</structfield> <type>bigint</type> + </para> + <para> + Number of blocks read. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>write</structfield> <type>bigint</type> + </para> + <para> + Number of blocks written. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>extend</structfield> <type>bigint</type> + </para> + <para> + Number of blocks extended. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>fsync</structfield> <type>bigint</type> + </para> + <para> + Number of blocks fsynced. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>stats_reset</structfield> <type>timestamp with time zone</type> + </para> + <para> + Time at which these statistics were last reset. </para></entry> </row> </tbody> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 55f7ec79e0..f3c10ae711 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1114,6 +1114,18 @@ CREATE VIEW pg_stat_bgwriter AS pg_stat_get_buf_alloc() AS buffers_alloc, pg_stat_get_bgwriter_stat_reset_time() AS stats_reset; +CREATE VIEW pg_stat_io AS +SELECT + b.backend_type, + b.io_context, + b.alloc, + b.read, + b.write, + b.extend, + b.fsync, + b.stats_reset +FROM pg_stat_get_io() b; + CREATE VIEW pg_stat_wal AS SELECT w.wal_records, diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 88c737f4f9..7815639350 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -1726,6 +1726,123 @@ pg_stat_get_buf_alloc(PG_FUNCTION_ARGS) PG_RETURN_INT64(pgstat_fetch_stat_bgwriter()->buf_alloc); } +/* +* When adding a new column to the pg_stat_io view, add a new enum value +* here above IO_NUM_COLUMNS. +*/ +typedef enum io_stat_col +{ + IO_COL_BACKEND_TYPE, + IO_COL_IO_CONTEXT, + IO_COL_ALLOCS, + IO_COL_READS, + IO_COL_WRITES, + IO_COL_EXTENDS, + IO_COL_FSYNCS, + IO_COL_RESET_TIME, + IO_NUM_COLUMNS, +} io_stat_col; + +/* + * When adding a new IOOp, add a new io_stat_col and add a case to this + * function returning the corresponding io_stat_col. + */ +static io_stat_col +pgstat_io_op_get_index(IOOp io_op) +{ + switch (io_op) + { + case IOOP_ALLOC: + return IO_COL_ALLOCS; + case IOOP_READ: + return IO_COL_READS; + case IOOP_WRITE: + return IO_COL_WRITES; + case IOOP_EXTEND: + return IO_COL_EXTENDS; + case IOOP_FSYNC: + return IO_COL_FSYNCS; + } + + elog(ERROR, "unrecognized IOOp value: %d", io_op); +} + +Datum +pg_stat_get_io(PG_FUNCTION_ARGS) +{ + PgStat_BackendIOContextOps *backends_io_stats; + ReturnSetInfo *rsinfo; + Datum reset_time; + + SetSingleFuncCall(fcinfo, 0); + rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + + backends_io_stats = pgstat_fetch_backend_io_context_ops(); + + reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp); + + for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++) + { + Datum bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype)); + bool expect_backend_stats = true; + PgStat_IOContextOps *io_context_ops = &backends_io_stats->stats[bktype]; + + /* + * For those BackendTypes without IO Operation stats, skip + * representing them in the view altogether. + */ + expect_backend_stats = pgstat_io_op_stats_collected(bktype); + + for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++) + { + PgStat_IOOpCounters *counters = &io_context_ops->data[io_context]; + const char *io_context_str = pgstat_io_context_desc(io_context); + + Datum values[IO_NUM_COLUMNS] = {0}; + bool nulls[IO_NUM_COLUMNS] = {0}; + + /* + * Some combinations of IOCONTEXT and BackendType are not valid + * for any type of IO Operation. In such cases, omit the entire + * row from the view. + */ + if (!expect_backend_stats || + !pgstat_bktype_io_context_valid(bktype, io_context)) + { + pgstat_io_context_ops_assert_zero(counters); + continue; + } + + values[IO_COL_BACKEND_TYPE] = bktype_desc; + values[IO_COL_IO_CONTEXT] = CStringGetTextDatum(io_context_str); + values[IO_COL_ALLOCS] = Int64GetDatum(counters->allocs); + values[IO_COL_READS] = Int64GetDatum(counters->reads); + values[IO_COL_WRITES] = Int64GetDatum(counters->writes); + values[IO_COL_EXTENDS] = Int64GetDatum(counters->extends); + values[IO_COL_FSYNCS] = Int64GetDatum(counters->fsyncs); + values[IO_COL_RESET_TIME] = TimestampTzGetDatum(reset_time); + + /* + * Some combinations of BackendType and IOOp and of IOContext and + * IOOp are not valid. Set these cells in the view NULL and assert + * that these stats are zero as expected. + */ + for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) + { + if (!(pgstat_io_op_valid(bktype, io_context, io_op))) + { + pgstat_io_op_assert_zero(counters, io_op); + nulls[pgstat_io_op_get_index(io_op)] = true; + } + } + + tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); + } + } + + return (Datum) 0; +} + /* * Returns statistics of WAL activity */ diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index a07e737a33..1c263abec8 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -5646,6 +5646,15 @@ proname => 'pg_stat_get_buf_alloc', provolatile => 's', proparallel => 'r', prorettype => 'int8', proargtypes => '', prosrc => 'pg_stat_get_buf_alloc' }, +{ oid => '8459', descr => 'statistics: per backend type IO statistics', + proname => 'pg_stat_get_io', provolatile => 'v', + prorows => '14', proretset => 't', + proparallel => 'r', prorettype => 'record', proargtypes => '', + proallargtypes => '{text,text,int8,int8,int8,int8,int8,timestamptz}', + proargmodes => '{o,o,o,o,o,o,o,o}', + proargnames => '{backend_type,io_context,alloc,read,write,extend,fsync,stats_reset}', + prosrc => 'pg_stat_get_io' }, + { oid => '1136', descr => 'statistics: information about WAL activity', proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's', proparallel => 'r', prorettype => 'record', proargtypes => '', diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 9dd137415e..d313420d67 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1868,6 +1868,15 @@ pg_stat_gssapi| SELECT s.pid, s.gss_enc AS encrypted FROM pg_stat_get_activity(NULL::integer) s(datid, pid, usesysid, application_name, state, query, wait_event_type, wait_event, xact_start, query_start, backend_start, state_change, client_addr, client_hostname, client_port, backend_xid, backend_xmin, backend_type, ssl, sslversion, sslcipher, sslbits, ssl_client_dn, ssl_client_serial, ssl_issuer_dn, gss_auth, gss_princ, gss_enc, leader_pid, query_id) WHERE (s.client_port IS NOT NULL); +pg_stat_io| SELECT b.backend_type, + b.io_context, + b.alloc, + b.read, + b.write, + b.extend, + b.fsync, + b.stats_reset + FROM pg_stat_get_io() b(backend_type, io_context, alloc, read, write, extend, fsync, stats_reset); pg_stat_progress_analyze| SELECT s.pid, s.datid, d.datname, diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out index 6a10dc462b..d1a6502c54 100644 --- a/src/test/regress/expected/stats.out +++ b/src/test/regress/expected/stats.out @@ -907,4 +907,206 @@ SELECT pg_stat_get_subscription_stats(NULL); (1 row) +-- Test that allocs, reads, writes, and extends to shared buffers and fsyncs +-- done to ensure durability of shared buffers are tracked in pg_stat_io. +SELECT sum(alloc) AS io_sum_shared_allocs_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(read) AS io_sum_shared_reads_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(write) AS io_sum_shared_writes_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(extend) AS io_sum_shared_extends_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(fsync) AS io_sum_shared_fsyncs_before FROM pg_stat_io WHERE io_context = 'shared' \gset +-- Create a regular table and insert some data to generate IOCONTEXT_SHARED +-- allocs and extends. +CREATE TABLE test_io_shared(a int); +INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +-- After a checkpoint, there should be some additional IOCONTEXT_SHARED writes +-- and fsyncs. +CHECKPOINT; +SELECT sum(alloc) AS io_sum_shared_allocs_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(write) AS io_sum_shared_writes_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(extend) AS io_sum_shared_extends_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(fsync) AS io_sum_shared_fsyncs_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT :io_sum_shared_allocs_after > :io_sum_shared_allocs_before; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_shared_writes_after > :io_sum_shared_writes_before; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_shared_extends_after > :io_sum_shared_extends_before; + ?column? +---------- + t +(1 row) + +SELECT current_setting('fsync') = 'off' OR :io_sum_shared_fsyncs_after > :io_sum_shared_fsyncs_before; + ?column? +---------- + t +(1 row) + +-- Change the tablespace so that the table is rewritten directly, then SELECT +-- from it to cause it to be read back into shared buffers. +SET allow_in_place_tablespaces = true; +CREATE TABLESPACE test_io_shared_stats_tblspc LOCATION ''; +ALTER TABLE test_io_shared SET TABLESPACE test_io_shared_stats_tblspc; +SELECT COUNT(*) FROM test_io_shared; + count +------- + 100 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(read) AS io_sum_shared_reads_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT :io_sum_shared_reads_after > :io_sum_shared_reads_before; + ?column? +---------- + t +(1 row) + +DROP TABLE test_io_shared; +DROP TABLESPACE test_io_shared_stats_tblspc; +-- Test that allocs, extends, reads, and writes of temporary tables are tracked +-- in pg_stat_io. +-- Set temp_buffers to a low value so that we can trigger writes with fewer +-- inserted tuples. +SET temp_buffers TO '1MB'; +CREATE TEMPORARY TABLE test_io_local(a int, b TEXT); +SELECT sum(alloc) AS io_sum_local_allocs_before FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(read) AS io_sum_local_reads_before FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(write) AS io_sum_local_writes_before FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(extend) AS io_sum_local_extends_before FROM pg_stat_io WHERE io_context = 'local' \gset +-- Insert enough values that we need to reuse and write out dirty local +-- buffers. +INSERT INTO test_io_local SELECT generate_series(1, 8000) as id, repeat('a', 100); +-- Read in evicted buffers. +SELECT COUNT(*) FROM test_io_local; + count +------- + 8000 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(alloc) AS io_sum_local_allocs_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(read) AS io_sum_local_reads_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(write) AS io_sum_local_writes_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(extend) AS io_sum_local_extends_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT :io_sum_local_allocs_after > :io_sum_local_allocs_before; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_local_reads_after > :io_sum_local_reads_before; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_local_writes_after > :io_sum_local_writes_before; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_local_extends_after > :io_sum_local_extends_before; + ?column? +---------- + t +(1 row) + +RESET temp_buffers; +-- Test that, when using a BufferAccessStrategy, reusing buffers from the +-- Strategy ring count as "Strategy" allocs in pg_stat_io. Also test that +-- Strategy reads are counted as such. +-- Set wal_skip_threshold smaller than the expected size of test_io_strategy so +-- that, even if wal_level is minimal, VACUUM FULL will fsync the newly +-- rewritten test_io_strategy instead of writing it to WAL. Writing it to WAL +-- will result in the newly written relation pages being in shared buffers -- +-- preventing us from testing BufferAccessStrategy allocs and reads. +SET wal_skip_threshold = '1 kB'; +SELECT sum(alloc) AS io_sum_strategy_allocs_before FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT sum(read) AS io_sum_strategy_reads_before FROM pg_stat_io WHERE io_context = 'strategy' \gset +CREATE TABLE test_io_strategy(a int, b int) WITH (autovacuum_enabled = 'false'); +INSERT INTO test_io_strategy SELECT i, i from generate_series(1, 8000)i; +-- Ensure that the next VACUUM will need to perform IO by rewriting the table +-- first with VACUUM (FULL). +VACUUM (FULL) test_io_strategy; +VACUUM (PARALLEL 0) test_io_strategy; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(alloc) AS io_sum_strategy_allocs_after FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT sum(read) AS io_sum_strategy_reads_after FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT :io_sum_strategy_allocs_after > :io_sum_strategy_allocs_before; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_strategy_reads_after > :io_sum_strategy_reads_before; + ?column? +---------- + t +(1 row) + +DROP TABLE test_io_strategy; +RESET wal_skip_threshold; +-- Test that, when using a BufferAccessStrategy and creating a relation, +-- Strategy extends are counted in pg_stat_io. +-- A CTAS uses a Bulk Write strategy. +SELECT sum(extend) AS io_sum_strategy_extends_before FROM pg_stat_io WHERE io_context = 'strategy' \gset +CREATE TABLE test_io_strategy_extend AS SELECT i FROM generate_series(1,100)i; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(extend) AS io_sum_strategy_extends_after FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT :io_sum_strategy_extends_after > :io_sum_strategy_extends_before; + ?column? +---------- + t +(1 row) + +DROP TABLE test_io_strategy_extend; +-- Test stats reset +SELECT sum(alloc) + sum(extend) + sum(fsync) + sum(read) + sum(write) AS io_stats_pre_reset FROM pg_stat_io \gset +SELECT pg_stat_reset_shared('io'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT sum(alloc) + sum(extend) + sum(fsync) + sum(read) + sum(write) AS io_stats_post_reset FROM pg_stat_io \gset +SELECT :io_stats_post_reset < :io_stats_pre_reset; + ?column? +---------- + t +(1 row) + -- End of Stats Test diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql index a6b0e9e042..bc8fa404a3 100644 --- a/src/test/regress/sql/stats.sql +++ b/src/test/regress/sql/stats.sql @@ -443,4 +443,108 @@ SELECT pg_stat_get_replication_slot(NULL); SELECT pg_stat_get_subscription_stats(NULL); +-- Test that allocs, reads, writes, and extends to shared buffers and fsyncs +-- done to ensure durability of shared buffers are tracked in pg_stat_io. +SELECT sum(alloc) AS io_sum_shared_allocs_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(read) AS io_sum_shared_reads_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(write) AS io_sum_shared_writes_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(extend) AS io_sum_shared_extends_before FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(fsync) AS io_sum_shared_fsyncs_before FROM pg_stat_io WHERE io_context = 'shared' \gset +-- Create a regular table and insert some data to generate IOCONTEXT_SHARED +-- allocs and extends. +CREATE TABLE test_io_shared(a int); +INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i; +SELECT pg_stat_force_next_flush(); +-- After a checkpoint, there should be some additional IOCONTEXT_SHARED writes +-- and fsyncs. +CHECKPOINT; +SELECT sum(alloc) AS io_sum_shared_allocs_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(write) AS io_sum_shared_writes_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(extend) AS io_sum_shared_extends_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT sum(fsync) AS io_sum_shared_fsyncs_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT :io_sum_shared_allocs_after > :io_sum_shared_allocs_before; +SELECT :io_sum_shared_writes_after > :io_sum_shared_writes_before; +SELECT :io_sum_shared_extends_after > :io_sum_shared_extends_before; +SELECT current_setting('fsync') = 'off' OR :io_sum_shared_fsyncs_after > :io_sum_shared_fsyncs_before; +-- Change the tablespace so that the table is rewritten directly, then SELECT +-- from it to cause it to be read back into shared buffers. +SET allow_in_place_tablespaces = true; +CREATE TABLESPACE test_io_shared_stats_tblspc LOCATION ''; +ALTER TABLE test_io_shared SET TABLESPACE test_io_shared_stats_tblspc; +SELECT COUNT(*) FROM test_io_shared; +SELECT pg_stat_force_next_flush(); +SELECT sum(read) AS io_sum_shared_reads_after FROM pg_stat_io WHERE io_context = 'shared' \gset +SELECT :io_sum_shared_reads_after > :io_sum_shared_reads_before; +DROP TABLE test_io_shared; +DROP TABLESPACE test_io_shared_stats_tblspc; + +-- Test that allocs, extends, reads, and writes of temporary tables are tracked +-- in pg_stat_io. + +-- Set temp_buffers to a low value so that we can trigger writes with fewer +-- inserted tuples. +SET temp_buffers TO '1MB'; +CREATE TEMPORARY TABLE test_io_local(a int, b TEXT); +SELECT sum(alloc) AS io_sum_local_allocs_before FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(read) AS io_sum_local_reads_before FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(write) AS io_sum_local_writes_before FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(extend) AS io_sum_local_extends_before FROM pg_stat_io WHERE io_context = 'local' \gset +-- Insert enough values that we need to reuse and write out dirty local +-- buffers. +INSERT INTO test_io_local SELECT generate_series(1, 8000) as id, repeat('a', 100); +-- Read in evicted buffers. +SELECT COUNT(*) FROM test_io_local; +SELECT pg_stat_force_next_flush(); +SELECT sum(alloc) AS io_sum_local_allocs_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(read) AS io_sum_local_reads_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(write) AS io_sum_local_writes_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT sum(extend) AS io_sum_local_extends_after FROM pg_stat_io WHERE io_context = 'local' \gset +SELECT :io_sum_local_allocs_after > :io_sum_local_allocs_before; +SELECT :io_sum_local_reads_after > :io_sum_local_reads_before; +SELECT :io_sum_local_writes_after > :io_sum_local_writes_before; +SELECT :io_sum_local_extends_after > :io_sum_local_extends_before; +RESET temp_buffers; + +-- Test that, when using a BufferAccessStrategy, reusing buffers from the +-- Strategy ring count as "Strategy" allocs in pg_stat_io. Also test that +-- Strategy reads are counted as such. + +-- Set wal_skip_threshold smaller than the expected size of test_io_strategy so +-- that, even if wal_level is minimal, VACUUM FULL will fsync the newly +-- rewritten test_io_strategy instead of writing it to WAL. Writing it to WAL +-- will result in the newly written relation pages being in shared buffers -- +-- preventing us from testing BufferAccessStrategy allocs and reads. +SET wal_skip_threshold = '1 kB'; +SELECT sum(alloc) AS io_sum_strategy_allocs_before FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT sum(read) AS io_sum_strategy_reads_before FROM pg_stat_io WHERE io_context = 'strategy' \gset +CREATE TABLE test_io_strategy(a int, b int) WITH (autovacuum_enabled = 'false'); +INSERT INTO test_io_strategy SELECT i, i from generate_series(1, 8000)i; +-- Ensure that the next VACUUM will need to perform IO by rewriting the table +-- first with VACUUM (FULL). +VACUUM (FULL) test_io_strategy; +VACUUM (PARALLEL 0) test_io_strategy; +SELECT pg_stat_force_next_flush(); +SELECT sum(alloc) AS io_sum_strategy_allocs_after FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT sum(read) AS io_sum_strategy_reads_after FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT :io_sum_strategy_allocs_after > :io_sum_strategy_allocs_before; +SELECT :io_sum_strategy_reads_after > :io_sum_strategy_reads_before; +DROP TABLE test_io_strategy; +RESET wal_skip_threshold; + +-- Test that, when using a BufferAccessStrategy and creating a relation, +-- Strategy extends are counted in pg_stat_io. +-- A CTAS uses a Bulk Write strategy. +SELECT sum(extend) AS io_sum_strategy_extends_before FROM pg_stat_io WHERE io_context = 'strategy' \gset +CREATE TABLE test_io_strategy_extend AS SELECT i FROM generate_series(1,100)i; +SELECT pg_stat_force_next_flush(); +SELECT sum(extend) AS io_sum_strategy_extends_after FROM pg_stat_io WHERE io_context = 'strategy' \gset +SELECT :io_sum_strategy_extends_after > :io_sum_strategy_extends_before; +DROP TABLE test_io_strategy_extend; + +-- Test stats reset +SELECT sum(alloc) + sum(extend) + sum(fsync) + sum(read) + sum(write) AS io_stats_pre_reset FROM pg_stat_io \gset +SELECT pg_stat_reset_shared('io'); +SELECT sum(alloc) + sum(extend) + sum(fsync) + sum(read) + sum(write) AS io_stats_post_reset FROM pg_stat_io \gset +SELECT :io_stats_post_reset < :io_stats_pre_reset; + -- End of Stats Test -- 2.34.1
From e0df4be80d5b47a2837ad3c993798de6b4e9b618 Mon Sep 17 00:00:00 2001 From: Melanie Plageman <melanieplage...@gmail.com> Date: Mon, 22 Aug 2022 11:35:20 -0400 Subject: [PATCH v30 2/3] Aggregate IO operation stats per BackendType Stats on IOOps for all IOContexts for a backend are tracked locally. Add functionality for backends to flush these stats to shared memory and accumulate them with those from all other backends, exited and live. Also add reset and snapshot functions used by cumulative stats system for management of these statistics. The aggregated stats in shared memory could be extended in the future with per-backend stats -- useful for per connection IO statistics and monitoring. Some BackendTypes will not flush their pending statistics at regular intervals and explicitly call pgstat_flush_io_ops() during the course of normal operations to flush their backend-local IO Operation statistics to shared memory in a timely manner. Because not all BackendType, IOOp, IOContext combinations are valid, the validity of the stats is checked before flushing pending stats and before reading in the existing stats file to shared memory. Author: Melanie Plageman <melanieplage...@gmail.com> Reviewed-by: Andres Freund <and...@anarazel.de> Reviewed-by: Justin Pryzby <pry...@telsasoft.com> Reviewed-by: Kyotaro Horiguchi <horikyota....@gmail.com> Discussion: https://www.postgresql.org/message-id/flat/20200124195226.lth52iydq2n2uilq%40alap3.anarazel.de --- doc/src/sgml/monitoring.sgml | 2 + src/backend/utils/activity/pgstat.c | 35 ++++ src/backend/utils/activity/pgstat_bgwriter.c | 7 +- .../utils/activity/pgstat_checkpointer.c | 7 +- src/backend/utils/activity/pgstat_io_ops.c | 153 ++++++++++++++++++ src/backend/utils/activity/pgstat_relation.c | 15 +- src/backend/utils/activity/pgstat_shmem.c | 4 + src/backend/utils/activity/pgstat_wal.c | 4 +- src/backend/utils/adt/pgstatfuncs.c | 4 +- src/include/miscadmin.h | 2 + src/include/pgstat.h | 81 +++++++++- src/include/utils/pgstat_internal.h | 37 +++++ src/tools/pgindent/typedefs.list | 3 + 13 files changed, 347 insertions(+), 7 deletions(-) diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1d9509a2f6..9440b41770 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -5360,6 +5360,8 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i the <structname>pg_stat_bgwriter</structname> view, <literal>archiver</literal> to reset all the counters shown in the <structname>pg_stat_archiver</structname> view, + <literal>io</literal> to reset all the counters shown in the + <structname>pg_stat_io</structname> view, <literal>wal</literal> to reset all the counters shown in the <structname>pg_stat_wal</structname> view or <literal>recovery_prefetch</literal> to reset all the counters shown diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c index 609f0b1ad8..e66dde0ea5 100644 --- a/src/backend/utils/activity/pgstat.c +++ b/src/backend/utils/activity/pgstat.c @@ -359,6 +359,15 @@ static const PgStat_KindInfo pgstat_kind_infos[PGSTAT_NUM_KINDS] = { .snapshot_cb = pgstat_checkpointer_snapshot_cb, }, + [PGSTAT_KIND_IOOPS] = { + .name = "io_ops", + + .fixed_amount = true, + + .reset_all_cb = pgstat_io_ops_reset_all_cb, + .snapshot_cb = pgstat_io_ops_snapshot_cb, + }, + [PGSTAT_KIND_SLRU] = { .name = "slru", @@ -582,6 +591,7 @@ pgstat_report_stat(bool force) /* Don't expend a clock check if nothing to do */ if (dlist_is_empty(&pgStatPending) && + !have_ioopstats && !have_slrustats && !pgstat_have_pending_wal()) { @@ -628,6 +638,9 @@ pgstat_report_stat(bool force) /* flush database / relation / function / ... stats */ partial_flush |= pgstat_flush_pending_entries(nowait); + /* flush IO Operations stats */ + partial_flush |= pgstat_flush_io_ops(nowait); + /* flush wal stats */ partial_flush |= pgstat_flush_wal(nowait); @@ -1321,6 +1334,14 @@ pgstat_write_statsfile(void) pgstat_build_snapshot_fixed(PGSTAT_KIND_CHECKPOINTER); write_chunk_s(fpout, &pgStatLocal.snapshot.checkpointer); + /* + * Write IO Operations stats struct + */ + pgstat_build_snapshot_fixed(PGSTAT_KIND_IOOPS); + write_chunk_s(fpout, &pgStatLocal.snapshot.io_ops.stat_reset_timestamp); + for (int i = 0; i < BACKEND_NUM_TYPES; i++) + write_chunk_s(fpout, &pgStatLocal.snapshot.io_ops.stats[i]); + /* * Write SLRU stats struct */ @@ -1495,6 +1516,20 @@ pgstat_read_statsfile(void) if (!read_chunk_s(fpin, &shmem->checkpointer.stats)) goto error; + /* + * Read IO Operations stats struct + */ + if (!read_chunk_s(fpin, &shmem->io_ops.stat_reset_timestamp)) + goto error; + + for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++) + { + pgstat_backend_io_stats_assert_well_formed(shmem->io_ops.stats[bktype].data, + bktype); + if (!read_chunk_s(fpin, &shmem->io_ops.stats[bktype].data)) + goto error; + } + /* * Read SLRU stats struct */ diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c index fbb1edc527..3d7f90a1b7 100644 --- a/src/backend/utils/activity/pgstat_bgwriter.c +++ b/src/backend/utils/activity/pgstat_bgwriter.c @@ -24,7 +24,7 @@ PgStat_BgWriterStats PendingBgWriterStats = {0}; /* - * Report bgwriter statistics + * Report bgwriter and IO Operation statistics */ void pgstat_report_bgwriter(void) @@ -56,6 +56,11 @@ pgstat_report_bgwriter(void) * Clear out the statistics buffer, so it can be re-used. */ MemSet(&PendingBgWriterStats, 0, sizeof(PendingBgWriterStats)); + + /* + * Report IO Operations statistics + */ + pgstat_flush_io_ops(false); } /* diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c index af8d513e7b..cfcf127210 100644 --- a/src/backend/utils/activity/pgstat_checkpointer.c +++ b/src/backend/utils/activity/pgstat_checkpointer.c @@ -24,7 +24,7 @@ PgStat_CheckpointerStats PendingCheckpointerStats = {0}; /* - * Report checkpointer statistics + * Report checkpointer and IO Operation statistics */ void pgstat_report_checkpointer(void) @@ -62,6 +62,11 @@ pgstat_report_checkpointer(void) * Clear out the statistics buffer, so it can be re-used. */ MemSet(&PendingCheckpointerStats, 0, sizeof(PendingCheckpointerStats)); + + /* + * Report IO Operation statistics + */ + pgstat_flush_io_ops(false); } /* diff --git a/src/backend/utils/activity/pgstat_io_ops.c b/src/backend/utils/activity/pgstat_io_ops.c index 5cfd40068d..8cd1239622 100644 --- a/src/backend/utils/activity/pgstat_io_ops.c +++ b/src/backend/utils/activity/pgstat_io_ops.c @@ -20,6 +20,39 @@ #include "utils/pgstat_internal.h" static PgStat_IOContextOps pending_IOOpStats; +bool have_ioopstats = false; + + +/* + * Helper function to accumulate source PgStat_IOOpCounters into target + * PgStat_IOOpCounters. If either of the passed-in PgStat_IOOpCounters are + * members of PgStatShared_IOContextOps, the caller is responsible for ensuring + * that the appropriate lock is held. + */ +static void +pgstat_accum_io_op(PgStat_IOOpCounters *target, PgStat_IOOpCounters *source, IOOp io_op) +{ + switch (io_op) + { + case IOOP_ALLOC: + target->allocs += source->allocs; + return; + case IOOP_EXTEND: + target->extends += source->extends; + return; + case IOOP_FSYNC: + target->fsyncs += source->fsyncs; + return; + case IOOP_READ: + target->reads += source->reads; + return; + case IOOP_WRITE: + target->writes += source->writes; + return; + } + + elog(ERROR, "unrecognized IOOp value: %d", io_op); +} void pgstat_count_io_op(IOOp io_op, IOContext io_context) @@ -51,6 +84,77 @@ pgstat_count_io_op(IOOp io_op, IOContext io_context) break; } + have_ioopstats = true; +} + +PgStat_BackendIOContextOps * +pgstat_fetch_backend_io_context_ops(void) +{ + pgstat_snapshot_fixed(PGSTAT_KIND_IOOPS); + + return &pgStatLocal.snapshot.io_ops; +} + +/* + * Flush out locally pending IO Operation statistics entries + * + * If no stats have been recorded, this function returns false. + * + * If nowait is true, this function returns true if the lock could not be + * acquired. Otherwise return false. + */ +bool +pgstat_flush_io_ops(bool nowait) +{ + PgStatShared_IOContextOps *type_shstats; + bool expect_backend_stats = true; + + if (!have_ioopstats) + return false; + + type_shstats = + &pgStatLocal.shmem->io_ops.stats[MyBackendType]; + + if (!nowait) + LWLockAcquire(&type_shstats->lock, LW_EXCLUSIVE); + else if (!LWLockConditionalAcquire(&type_shstats->lock, LW_EXCLUSIVE)) + return true; + + expect_backend_stats = pgstat_io_op_stats_collected(MyBackendType); + + for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++) + { + PgStat_IOOpCounters *sharedent = &type_shstats->data[io_context]; + PgStat_IOOpCounters *pendingent = &pending_IOOpStats.data[io_context]; + + if (!expect_backend_stats || + !pgstat_bktype_io_context_valid(MyBackendType, io_context)) + { + pgstat_io_context_ops_assert_zero(sharedent); + pgstat_io_context_ops_assert_zero(pendingent); + continue; + } + + for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) + { + if (!(pgstat_io_op_valid(MyBackendType, io_context, io_op))) + { + pgstat_io_op_assert_zero(sharedent, io_op); + pgstat_io_op_assert_zero(pendingent, io_op); + continue; + } + + pgstat_accum_io_op(sharedent, pendingent, io_op); + } + } + + LWLockRelease(&type_shstats->lock); + + memset(&pending_IOOpStats, 0, sizeof(pending_IOOpStats)); + + have_ioopstats = false; + + return false; } const char * @@ -89,6 +193,55 @@ pgstat_io_op_desc(IOOp io_op) elog(ERROR, "unrecognized IOOp value: %d", io_op); } +void +pgstat_io_ops_reset_all_cb(TimestampTz ts) +{ + PgStatShared_BackendIOContextOps *backends_stats_shmem = &pgStatLocal.shmem->io_ops; + + for (int i = 0; i < BACKEND_NUM_TYPES; i++) + { + PgStatShared_IOContextOps *stats_shmem = &backends_stats_shmem->stats[i]; + + LWLockAcquire(&stats_shmem->lock, LW_EXCLUSIVE); + + /* + * Use the lock in the first BackendType's PgStat_IOContextOps to + * protect the reset timestamp as well. + */ + if (i == 0) + backends_stats_shmem->stat_reset_timestamp = ts; + + memset(stats_shmem->data, 0, sizeof(stats_shmem->data)); + LWLockRelease(&stats_shmem->lock); + } +} + +void +pgstat_io_ops_snapshot_cb(void) +{ + PgStatShared_BackendIOContextOps *backends_stats_shmem = &pgStatLocal.shmem->io_ops; + PgStat_BackendIOContextOps *backends_stats_snap = &pgStatLocal.snapshot.io_ops; + + for (int i = 0; i < BACKEND_NUM_TYPES; i++) + { + PgStatShared_IOContextOps *stats_shmem = &backends_stats_shmem->stats[i]; + PgStat_IOContextOps *stats_snap = &backends_stats_snap->stats[i]; + + LWLockAcquire(&stats_shmem->lock, LW_SHARED); + + /* + * Use the lock in the first BackendType's PgStat_IOContextOps to + * protect the reset timestamp as well. + */ + if (i == 0) + backends_stats_snap->stat_reset_timestamp = backends_stats_shmem->stat_reset_timestamp; + + memcpy(stats_snap->data, stats_shmem->data, sizeof(stats_shmem->data)); + LWLockRelease(&stats_shmem->lock); + } + +} + /* * IO Operation statistics are not collected for all BackendTypes. * diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c index a846d9ffb6..7a2fd1ccf9 100644 --- a/src/backend/utils/activity/pgstat_relation.c +++ b/src/backend/utils/activity/pgstat_relation.c @@ -205,7 +205,7 @@ pgstat_drop_relation(Relation rel) } /* - * Report that the table was just vacuumed. + * Report that the table was just vacuumed and flush IO Operation statistics. */ void pgstat_report_vacuum(Oid tableoid, bool shared, @@ -257,10 +257,18 @@ pgstat_report_vacuum(Oid tableoid, bool shared, } pgstat_unlock_entry(entry_ref); + + /* + * Flush IO Operations statistics now. pgstat_report_stat() will flush IO + * Operation stats, however this will not be called after an entire + * autovacuum cycle is done -- which will likely vacuum many relations -- + * or until the VACUUM command has processed all tables and committed. + */ + pgstat_flush_io_ops(false); } /* - * Report that the table was just analyzed. + * Report that the table was just analyzed and flush IO Operation statistics. * * Caller must provide new live- and dead-tuples estimates, as well as a * flag indicating whether to reset the changes_since_analyze counter. @@ -340,6 +348,9 @@ pgstat_report_analyze(Relation rel, } pgstat_unlock_entry(entry_ref); + + /* see pgstat_report_vacuum() */ + pgstat_flush_io_ops(false); } /* diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c index 9a4f037959..275a7be166 100644 --- a/src/backend/utils/activity/pgstat_shmem.c +++ b/src/backend/utils/activity/pgstat_shmem.c @@ -202,6 +202,10 @@ StatsShmemInit(void) LWLockInitialize(&ctl->checkpointer.lock, LWTRANCHE_PGSTATS_DATA); LWLockInitialize(&ctl->slru.lock, LWTRANCHE_PGSTATS_DATA); LWLockInitialize(&ctl->wal.lock, LWTRANCHE_PGSTATS_DATA); + + for (int i = 0; i < BACKEND_NUM_TYPES; i++) + LWLockInitialize(&ctl->io_ops.stats[i].lock, + LWTRANCHE_PGSTATS_DATA); } else { diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c index 5a878bd115..9cac407b42 100644 --- a/src/backend/utils/activity/pgstat_wal.c +++ b/src/backend/utils/activity/pgstat_wal.c @@ -34,7 +34,7 @@ static WalUsage prevWalUsage; /* * Calculate how much WAL usage counters have increased and update - * shared statistics. + * shared WAL and IO Operation statistics. * * Must be called by processes that generate WAL, that do not call * pgstat_report_stat(), like walwriter. @@ -43,6 +43,8 @@ void pgstat_report_wal(bool force) { pgstat_flush_wal(force); + + pgstat_flush_io_ops(force); } /* diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index be15b4b2e5..88c737f4f9 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -2085,6 +2085,8 @@ pg_stat_reset_shared(PG_FUNCTION_ARGS) pgstat_reset_of_kind(PGSTAT_KIND_BGWRITER); pgstat_reset_of_kind(PGSTAT_KIND_CHECKPOINTER); } + else if (strcmp(target, "io") == 0) + pgstat_reset_of_kind(PGSTAT_KIND_IOOPS); else if (strcmp(target, "recovery_prefetch") == 0) XLogPrefetchResetStats(); else if (strcmp(target, "wal") == 0) @@ -2093,7 +2095,7 @@ pg_stat_reset_shared(PG_FUNCTION_ARGS) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("unrecognized reset target: \"%s\"", target), - errhint("Target must be \"archiver\", \"bgwriter\", \"recovery_prefetch\", or \"wal\"."))); + errhint("Target must be \"archiver\", \"io\", \"bgwriter\", \"recovery_prefetch\", or \"wal\"."))); PG_RETURN_VOID(); } diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index ee48e392ed..2b73deda2f 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -331,6 +331,8 @@ typedef enum BackendType B_WAL_WRITER, } BackendType; +#define BACKEND_NUM_TYPES B_WAL_WRITER + 1 + extern PGDLLIMPORT BackendType MyBackendType; extern const char *GetBackendTypeDesc(BackendType backendType); diff --git a/src/include/pgstat.h b/src/include/pgstat.h index ccc836a37f..d35072968b 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -48,6 +48,7 @@ typedef enum PgStat_Kind PGSTAT_KIND_ARCHIVER, PGSTAT_KIND_BGWRITER, PGSTAT_KIND_CHECKPOINTER, + PGSTAT_KIND_IOOPS, PGSTAT_KIND_SLRU, PGSTAT_KIND_WAL, } PgStat_Kind; @@ -242,7 +243,7 @@ typedef struct PgStat_TableXactStatus * ------------------------------------------------------------ */ -#define PGSTAT_FILE_FORMAT_ID 0x01A5BCA7 +#define PGSTAT_FILE_FORMAT_ID 0x01A5BCA8 typedef struct PgStat_ArchiverStats { @@ -314,6 +315,12 @@ typedef struct PgStat_IOContextOps PgStat_IOOpCounters data[IOCONTEXT_NUM_TYPES]; } PgStat_IOContextOps; +typedef struct PgStat_BackendIOContextOps +{ + TimestampTz stat_reset_timestamp; + PgStat_IOContextOps stats[BACKEND_NUM_TYPES]; +} PgStat_BackendIOContextOps; + typedef struct PgStat_StatDBEntry { PgStat_Counter n_xact_commit; @@ -496,6 +503,7 @@ extern PgStat_CheckpointerStats *pgstat_fetch_stat_checkpointer(void); */ extern void pgstat_count_io_op(IOOp io_op, IOContext io_context); +extern PgStat_BackendIOContextOps *pgstat_fetch_backend_io_context_ops(void); extern const char *pgstat_io_context_desc(IOContext io_context); extern const char *pgstat_io_op_desc(IOOp io_op); @@ -505,6 +513,77 @@ extern bool pgstat_bktype_io_context_valid(BackendType bktype, IOContext io_cont extern bool pgstat_io_op_valid(BackendType bktype, IOContext io_context, IOOp io_op); extern bool pgstat_expect_io_op(BackendType bktype, IOContext io_context, IOOp io_op); +/* + * Functions to assert that invalid IO Operation counters are zero. + */ +static inline void +pgstat_io_context_ops_assert_zero(PgStat_IOOpCounters *counters) +{ + Assert(counters->allocs == 0 && counters->extends == 0 && + counters->fsyncs == 0 && counters->reads == 0 && + counters->writes == 0); +} + +static inline void +pgstat_io_op_assert_zero(PgStat_IOOpCounters *counters, IOOp io_op) +{ + switch (io_op) + { + case IOOP_ALLOC: + Assert(counters->allocs == 0); + return; + case IOOP_EXTEND: + Assert(counters->extends == 0); + return; + case IOOP_FSYNC: + Assert(counters->fsyncs == 0); + return; + case IOOP_READ: + Assert(counters->reads == 0); + return; + case IOOP_WRITE: + Assert(counters->writes == 0); + return; + } + + /* Should not reach here */ + Assert(false); +} + +/* + * Assert that stats have not been counted for any combination of IOContext and + * IOOp which are not valid for the passed-in BackendType. The passed-in array + * of PgStat_IOOpCounters must contain stats from the BackendType specified by + * the second parameter. Caller is responsible for any locking if the passed-in + * array of PgStat_IOOpCounters is a member of PgStatShared_IOContextOps. + */ +static inline void +pgstat_backend_io_stats_assert_well_formed(PgStat_IOOpCounters + backend_io_context_ops[IOCONTEXT_NUM_TYPES], BackendType bktype) +{ + bool expect_backend_stats = true; + + if (!pgstat_io_op_stats_collected(bktype)) + expect_backend_stats = false; + + for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++) + { + if (!expect_backend_stats || + !pgstat_bktype_io_context_valid(bktype, io_context)) + { + pgstat_io_context_ops_assert_zero(&backend_io_context_ops[io_context]); + continue; + } + + for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) + { + if (!pgstat_io_op_valid(bktype, io_context, io_op)) + pgstat_io_op_assert_zero(&backend_io_context_ops[io_context], + io_op); + } + } +} + /* * Functions in pgstat_database.c diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h index 40a3602855..95f19cae99 100644 --- a/src/include/utils/pgstat_internal.h +++ b/src/include/utils/pgstat_internal.h @@ -329,6 +329,26 @@ typedef struct PgStatShared_Checkpointer PgStat_CheckpointerStats reset_offset; } PgStatShared_Checkpointer; +typedef struct PgStatShared_IOContextOps +{ + /* + * lock protects ->data + * If this PgStatShared_IOContextOps is + * PgStatShared_BackendIOContextOps->stats[0], lock also protects + * PgStatShared_BackendIOContextOps->stat_reset_timestamp. + */ + LWLock lock; + PgStat_IOOpCounters data[IOCONTEXT_NUM_TYPES]; +} PgStatShared_IOContextOps; + +typedef struct PgStatShared_BackendIOContextOps +{ + /* ->stats_reset_timestamp is protected by ->stats[0].lock */ + TimestampTz stat_reset_timestamp; + PgStatShared_IOContextOps stats[BACKEND_NUM_TYPES]; +} PgStatShared_BackendIOContextOps; + + typedef struct PgStatShared_SLRU { /* lock protects ->stats */ @@ -419,6 +439,7 @@ typedef struct PgStat_ShmemControl PgStatShared_Archiver archiver; PgStatShared_BgWriter bgwriter; PgStatShared_Checkpointer checkpointer; + PgStatShared_BackendIOContextOps io_ops; PgStatShared_SLRU slru; PgStatShared_Wal wal; } PgStat_ShmemControl; @@ -442,6 +463,8 @@ typedef struct PgStat_Snapshot PgStat_CheckpointerStats checkpointer; + PgStat_BackendIOContextOps io_ops; + PgStat_SLRUStats slru[SLRU_NUM_ELEMENTS]; PgStat_WalStats wal; @@ -549,6 +572,15 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait); +/* + * Functions in pgstat_io_ops.c + */ + +extern void pgstat_io_ops_reset_all_cb(TimestampTz ts); +extern void pgstat_io_ops_snapshot_cb(void); +extern bool pgstat_flush_io_ops(bool nowait); + + /* * Functions in pgstat_relation.c */ @@ -641,6 +673,11 @@ extern void pgstat_create_transactional(PgStat_Kind kind, Oid dboid, Oid objoid) extern PGDLLIMPORT PgStat_LocalState pgStatLocal; +/* + * Variables in pgstat_io_ops.c + */ + +extern PGDLLIMPORT bool have_ioopstats; /* * Variables in pgstat_slru.c diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 67218ec6f2..33c9362257 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2005,12 +2005,14 @@ PgFdwRelationInfo PgFdwScanState PgIfAddrCallback PgStatShared_Archiver +PgStatShared_BackendIOContextOps PgStatShared_BgWriter PgStatShared_Checkpointer PgStatShared_Common PgStatShared_Database PgStatShared_Function PgStatShared_HashEntry +PgStatShared_IOContextOps PgStatShared_Relation PgStatShared_ReplSlot PgStatShared_SLRU @@ -2018,6 +2020,7 @@ PgStatShared_Subscription PgStatShared_Wal PgStat_ArchiverStats PgStat_BackendFunctionEntry +PgStat_BackendIOContextOps PgStat_BackendSubEntry PgStat_BgWriterStats PgStat_CheckpointerStats -- 2.34.1
From 55564aca63fea479681456ff333fdbb5868589c4 Mon Sep 17 00:00:00 2001 From: Melanie Plageman <melanieplage...@gmail.com> Date: Mon, 22 Aug 2022 11:08:23 -0400 Subject: [PATCH v30 1/3] Track IO operation statistics locally Introduce "IOOp", an IO operation done by a backend, and "IOContext", the IO source, target, or type done by a backend. For example, the checkpointer may write a shared buffer out. This would be counted as an IOOp "write" on an IOContext IOCONTEXT_SHARED by BackendType "checkpointer". Each IOOp (alloc, read, write, extend, fsync) is counted per IOContext (local, shared, or strategy) through a call to pgstat_count_io_op(). The primary concern of these statistics is IO operations on data blocks during the course of normal database operations. IO operations done by, for example, the archiver or syslogger are not counted in these statistics. IOCONTEXT_LOCAL and IOCONTEXT_SHARED IOContexts concern operations on local and shared buffers. The IOCONTEXT_STRATEGY IOContext concerns IO operations on buffers as part of a BufferAccessStrategy. IOOP_ALLOC IOOps are counted in IOCONTEXT_SHARED and IOCONTEXT_LOCAL IOContexts whenever a buffer is acquired through [Local]BufferAlloc(). IOOP_ALLOC IOOps are counted in the IOCONTEXT_STRATEGY IOContext whenever a buffer already in the strategy ring is reused. IOOP_WRITE IOOps are counted in the IOCONTEXT_STRATEGY IOContext whenever the reused dirty buffer is written out. Stats on IOOps in all IOContexts for a given backend are counted in a backend's local memory. A subsequent commit will expose functions for aggregating and viewing these stats. Author: Melanie Plageman <melanieplage...@gmail.com> Reviewed-by: Andres Freund <and...@anarazel.de> Reviewed-by: Justin Pryzby <pry...@telsasoft.com> Reviewed-by: Kyotaro Horiguchi <horikyota....@gmail.com> Discussion: https://www.postgresql.org/message-id/flat/20200124195226.lth52iydq2n2uilq%40alap3.anarazel.de --- src/backend/postmaster/checkpointer.c | 12 ++ src/backend/storage/buffer/bufmgr.c | 60 +++++-- src/backend/storage/buffer/freelist.c | 21 ++- src/backend/storage/buffer/localbuf.c | 5 + src/backend/storage/sync/sync.c | 2 + src/backend/utils/activity/Makefile | 1 + src/backend/utils/activity/meson.build | 1 + src/backend/utils/activity/pgstat_io_ops.c | 199 +++++++++++++++++++++ src/include/pgstat.h | 53 ++++++ src/include/storage/buf_internals.h | 2 +- src/tools/pgindent/typedefs.list | 4 + 11 files changed, 348 insertions(+), 12 deletions(-) create mode 100644 src/backend/utils/activity/pgstat_io_ops.c diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c index 5fc076fc14..bd2e1de7c2 100644 --- a/src/backend/postmaster/checkpointer.c +++ b/src/backend/postmaster/checkpointer.c @@ -1116,6 +1116,18 @@ ForwardSyncRequest(const FileTag *ftag, SyncRequestType type) if (!AmBackgroundWriterProcess()) CheckpointerShmem->num_backend_fsync++; LWLockRelease(CheckpointerCommLock); + + /* + * We have no way of knowing if the current IOContext is + * IOCONTEXT_SHARED or IOCONTEXT_STRATEGY at this point, so count the + * fsync as being in the IOCONTEXT_SHARED IOContext. This is probably + * okay, because the number of backend fsyncs doesn't say anything + * about the efficacy of the BufferAccessStrategy. And counting both + * fsyncs done in IOCONTEXT_SHARED and IOCONTEXT_STRATEGY under + * IOCONTEXT_SHARED is likely clearer when investigating the number of + * backend fsyncs. + */ + pgstat_count_io_op(IOOP_FSYNC, IOCONTEXT_SHARED); return false; } diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c index 5b0e531f97..3573047235 100644 --- a/src/backend/storage/buffer/bufmgr.c +++ b/src/backend/storage/buffer/bufmgr.c @@ -482,7 +482,7 @@ static BufferDesc *BufferAlloc(SMgrRelation smgr, BlockNumber blockNum, BufferAccessStrategy strategy, bool *foundPtr); -static void FlushBuffer(BufferDesc *buf, SMgrRelation reln); +static void FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOContext io_context); static void FindAndDropRelationBuffers(RelFileLocator rlocator, ForkNumber forkNum, BlockNumber nForkBlock, @@ -823,6 +823,7 @@ ReadBuffer_common(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, BufferDesc *bufHdr; Block bufBlock; bool found; + IOContext io_context; bool isExtend; bool isLocalBuf = SmgrIsTemp(smgr); @@ -986,10 +987,24 @@ ReadBuffer_common(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, */ Assert(!(pg_atomic_read_u32(&bufHdr->state) & BM_VALID)); /* spinlock not needed */ - bufBlock = isLocalBuf ? LocalBufHdrGetBlock(bufHdr) : BufHdrGetBlock(bufHdr); + if (isLocalBuf) + { + bufBlock = LocalBufHdrGetBlock(bufHdr); + io_context = IOCONTEXT_LOCAL; + } + else + { + bufBlock = BufHdrGetBlock(bufHdr); + + if (strategy != NULL) + io_context = IOCONTEXT_STRATEGY; + else + io_context = IOCONTEXT_SHARED; + } if (isExtend) { + pgstat_count_io_op(IOOP_EXTEND, io_context); /* new buffers are zero-filled */ MemSet((char *) bufBlock, 0, BLCKSZ); /* don't set checksum for all-zero page */ @@ -1020,6 +1035,8 @@ ReadBuffer_common(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, smgrread(smgr, forkNum, blockNum, (char *) bufBlock); + pgstat_count_io_op(IOOP_READ, io_context); + if (track_io_timing) { INSTR_TIME_SET_CURRENT(io_time); @@ -1190,6 +1207,8 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, /* Loop here in case we have to try another victim buffer */ for (;;) { + bool from_ring; + /* * Ensure, while the spinlock's not yet held, that there's a free * refcount entry. @@ -1200,7 +1219,7 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, * Select a victim buffer. The buffer is returned with its header * spinlock still held! */ - buf = StrategyGetBuffer(strategy, &buf_state); + buf = StrategyGetBuffer(strategy, &buf_state, &from_ring); Assert(BUF_STATE_GET_REFCOUNT(buf_state) == 0); @@ -1237,6 +1256,8 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, if (LWLockConditionalAcquire(BufferDescriptorGetContentLock(buf), LW_SHARED)) { + IOContext io_context; + /* * If using a nondefault strategy, and writing the buffer * would require a WAL flush, let the strategy decide whether @@ -1263,13 +1284,28 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, } } + /* + * When a strategy is in use, if the target dirty buffer is an + * existing strategy buffer being reused, count this as a + * strategy write for the purposes of IO Operations statistics + * tracking. + * + * All dirty shared buffers upon first being added to the ring + * will be counted as shared buffer writes. + * + * When a strategy is not in use, the write can only be a + * "regular" write of a dirty shared buffer. + */ + + io_context = from_ring ? IOCONTEXT_STRATEGY : IOCONTEXT_SHARED; + /* OK, do the I/O */ TRACE_POSTGRESQL_BUFFER_WRITE_DIRTY_START(forkNum, blockNum, smgr->smgr_rlocator.locator.spcOid, smgr->smgr_rlocator.locator.dbOid, smgr->smgr_rlocator.locator.relNumber); - FlushBuffer(buf, NULL); + FlushBuffer(buf, NULL, io_context); LWLockRelease(BufferDescriptorGetContentLock(buf)); ScheduleBufferTagForWriteback(&BackendWritebackContext, @@ -2573,7 +2609,7 @@ SyncOneBuffer(int buf_id, bool skip_recently_used, WritebackContext *wb_context) PinBuffer_Locked(bufHdr); LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED); - FlushBuffer(bufHdr, NULL); + FlushBuffer(bufHdr, NULL, IOCONTEXT_SHARED); LWLockRelease(BufferDescriptorGetContentLock(bufHdr)); @@ -2823,7 +2859,7 @@ BufferGetTag(Buffer buffer, RelFileLocator *rlocator, ForkNumber *forknum, * as the second parameter. If not, pass NULL. */ static void -FlushBuffer(BufferDesc *buf, SMgrRelation reln) +FlushBuffer(BufferDesc *buf, SMgrRelation reln, IOContext io_context) { XLogRecPtr recptr; ErrorContextCallback errcallback; @@ -2903,6 +2939,8 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln) */ bufToWrite = PageSetChecksumCopy((Page) bufBlock, buf->tag.blockNum); + pgstat_count_io_op(IOOP_WRITE, io_context); + if (track_io_timing) INSTR_TIME_SET_CURRENT(io_start); @@ -3554,6 +3592,8 @@ FlushRelationBuffers(Relation rel) localpage, false); + pgstat_count_io_op(IOOP_WRITE, IOCONTEXT_LOCAL); + buf_state &= ~(BM_DIRTY | BM_JUST_DIRTIED); pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state); @@ -3589,7 +3629,7 @@ FlushRelationBuffers(Relation rel) { PinBuffer_Locked(bufHdr); LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED); - FlushBuffer(bufHdr, RelationGetSmgr(rel)); + FlushBuffer(bufHdr, RelationGetSmgr(rel), IOCONTEXT_SHARED); LWLockRelease(BufferDescriptorGetContentLock(bufHdr)); UnpinBuffer(bufHdr, true); } @@ -3687,7 +3727,7 @@ FlushRelationsAllBuffers(SMgrRelation *smgrs, int nrels) { PinBuffer_Locked(bufHdr); LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED); - FlushBuffer(bufHdr, srelent->srel); + FlushBuffer(bufHdr, srelent->srel, IOCONTEXT_SHARED); LWLockRelease(BufferDescriptorGetContentLock(bufHdr)); UnpinBuffer(bufHdr, true); } @@ -3897,7 +3937,7 @@ FlushDatabaseBuffers(Oid dbid) { PinBuffer_Locked(bufHdr); LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED); - FlushBuffer(bufHdr, NULL); + FlushBuffer(bufHdr, NULL, IOCONTEXT_SHARED); LWLockRelease(BufferDescriptorGetContentLock(bufHdr)); UnpinBuffer(bufHdr, true); } @@ -3924,7 +3964,7 @@ FlushOneBuffer(Buffer buffer) Assert(LWLockHeldByMe(BufferDescriptorGetContentLock(bufHdr))); - FlushBuffer(bufHdr, NULL); + FlushBuffer(bufHdr, NULL, IOCONTEXT_SHARED); } /* diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c index 990e081aae..50d04b2b6d 100644 --- a/src/backend/storage/buffer/freelist.c +++ b/src/backend/storage/buffer/freelist.c @@ -15,6 +15,7 @@ */ #include "postgres.h" +#include "pgstat.h" #include "port/atomics.h" #include "storage/buf_internals.h" #include "storage/bufmgr.h" @@ -198,13 +199,15 @@ have_free_buffer(void) * return the buffer with the buffer header spinlock still held. */ BufferDesc * -StrategyGetBuffer(BufferAccessStrategy strategy, uint32 *buf_state) +StrategyGetBuffer(BufferAccessStrategy strategy, uint32 *buf_state, bool *from_ring) { BufferDesc *buf; int bgwprocno; int trycounter; uint32 local_buf_state; /* to avoid repeated (de-)referencing */ + *from_ring = false; + /* * If given a strategy object, see whether it can select a buffer. We * assume strategy objects don't need buffer_strategy_lock. @@ -213,7 +216,22 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint32 *buf_state) { buf = GetBufferFromRing(strategy, buf_state); if (buf != NULL) + { + /* + * When a strategy is in use, reused buffers from the strategy + * ring will be counted as IOCONTEXT_STRATEGY allocations for the + * purposes of IO Operation statistics tracking. + * + * However, even when a strategy is in use, if a new buffer must + * be allocated from shared buffers and added to the ring, this is + * counted instead as an IOCONTEXT_SHARED allocation. So, only + * reused buffers are counted as having been allocated in the + * IOCONTEXT_STRATEGY IOContext. + */ + *from_ring = true; + pgstat_count_io_op(IOOP_ALLOC, IOCONTEXT_STRATEGY); return buf; + } } /* @@ -247,6 +265,7 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint32 *buf_state) * the rate of buffer consumption. Note that buffers recycled by a * strategy object are intentionally not counted here. */ + pgstat_count_io_op(IOOP_ALLOC, IOCONTEXT_SHARED); pg_atomic_fetch_add_u32(&StrategyControl->numBufferAllocs, 1); /* diff --git a/src/backend/storage/buffer/localbuf.c b/src/backend/storage/buffer/localbuf.c index 30d67d1c40..6b2f529fe7 100644 --- a/src/backend/storage/buffer/localbuf.c +++ b/src/backend/storage/buffer/localbuf.c @@ -18,6 +18,7 @@ #include "access/parallel.h" #include "catalog/catalog.h" #include "executor/instrument.h" +#include "pgstat.h" #include "storage/buf_internals.h" #include "storage/bufmgr.h" #include "utils/guc_hooks.h" @@ -196,6 +197,8 @@ LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum, BlockNumber blockNum, LocalRefCount[b]++; ResourceOwnerRememberBuffer(CurrentResourceOwner, BufferDescriptorGetBuffer(bufHdr)); + + pgstat_count_io_op(IOOP_ALLOC, IOCONTEXT_LOCAL); break; } } @@ -226,6 +229,8 @@ LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum, BlockNumber blockNum, localpage, false); + pgstat_count_io_op(IOOP_WRITE, IOCONTEXT_LOCAL); + /* Mark not-dirty now in case we error out below */ buf_state &= ~BM_DIRTY; pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state); diff --git a/src/backend/storage/sync/sync.c b/src/backend/storage/sync/sync.c index 9d6a9e9109..5718b52fb5 100644 --- a/src/backend/storage/sync/sync.c +++ b/src/backend/storage/sync/sync.c @@ -432,6 +432,8 @@ ProcessSyncRequests(void) total_elapsed += elapsed; processed++; + pgstat_count_io_op(IOOP_FSYNC, IOCONTEXT_SHARED); + if (log_checkpoints) elog(DEBUG1, "checkpoint sync: number=%d file=%s time=%.3f ms", processed, diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile index a2e8507fd6..0098785089 100644 --- a/src/backend/utils/activity/Makefile +++ b/src/backend/utils/activity/Makefile @@ -22,6 +22,7 @@ OBJS = \ pgstat_checkpointer.o \ pgstat_database.o \ pgstat_function.o \ + pgstat_io_ops.o \ pgstat_relation.o \ pgstat_replslot.o \ pgstat_shmem.o \ diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build index 5b3b558a67..1038324c32 100644 --- a/src/backend/utils/activity/meson.build +++ b/src/backend/utils/activity/meson.build @@ -7,6 +7,7 @@ backend_sources += files( 'pgstat_checkpointer.c', 'pgstat_database.c', 'pgstat_function.c', + 'pgstat_io_ops.c', 'pgstat_relation.c', 'pgstat_replslot.c', 'pgstat_shmem.c', diff --git a/src/backend/utils/activity/pgstat_io_ops.c b/src/backend/utils/activity/pgstat_io_ops.c new file mode 100644 index 0000000000..5cfd40068d --- /dev/null +++ b/src/backend/utils/activity/pgstat_io_ops.c @@ -0,0 +1,199 @@ +/* ------------------------------------------------------------------------- + * + * pgstat_io_ops.c + * Implementation of IO operation statistics. + * + * This file contains the implementation of IO operation statistics. It is kept + * separate from pgstat.c to enforce the line between the statistics access / + * storage implementation and the details about individual types of + * statistics. + * + * Copyright (c) 2021-2022, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/backend/utils/activity/pgstat_io_ops.c + * ------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "utils/pgstat_internal.h" + +static PgStat_IOContextOps pending_IOOpStats; + +void +pgstat_count_io_op(IOOp io_op, IOContext io_context) +{ + PgStat_IOOpCounters *pending_counters; + + Assert(io_context < IOCONTEXT_NUM_TYPES); + Assert(io_op < IOOP_NUM_TYPES); + Assert(pgstat_expect_io_op(MyBackendType, io_context, io_op)); + + pending_counters = &pending_IOOpStats.data[io_context]; + + switch (io_op) + { + case IOOP_ALLOC: + pending_counters->allocs++; + break; + case IOOP_EXTEND: + pending_counters->extends++; + break; + case IOOP_FSYNC: + pending_counters->fsyncs++; + break; + case IOOP_READ: + pending_counters->reads++; + break; + case IOOP_WRITE: + pending_counters->writes++; + break; + } + +} + +const char * +pgstat_io_context_desc(IOContext io_context) +{ + switch (io_context) + { + case IOCONTEXT_LOCAL: + return "local"; + case IOCONTEXT_SHARED: + return "shared"; + case IOCONTEXT_STRATEGY: + return "strategy"; + } + + elog(ERROR, "unrecognized IOContext value: %d", io_context); +} + +const char * +pgstat_io_op_desc(IOOp io_op) +{ + switch (io_op) + { + case IOOP_ALLOC: + return "alloc"; + case IOOP_EXTEND: + return "extend"; + case IOOP_FSYNC: + return "fsync"; + case IOOP_READ: + return "read"; + case IOOP_WRITE: + return "write"; + } + + elog(ERROR, "unrecognized IOOp value: %d", io_op); +} + +/* +* IO Operation statistics are not collected for all BackendTypes. +* +* The following BackendTypes do not participate in the cumulative stats +* subsystem or do not do IO operations worth reporting statistics on: +* - Syslogger because it is not connected to shared memory +* - Archiver because most relevant archiving IO is delegated to a +* specialized command or module +* - WAL Receiver and WAL Writer IO is not tracked in pg_stat_io for now +* +* Function returns true if BackendType participates in the cumulative stats +* subsystem for IO Operations and false if it does not. +*/ +bool +pgstat_io_op_stats_collected(BackendType bktype) +{ + return bktype != B_INVALID && bktype != B_ARCHIVER && bktype != B_LOGGER && + bktype != B_WAL_RECEIVER && bktype != B_WAL_WRITER; +} + +/* + * Some BackendTypes will never do IO in certain IOContexts. Check that the + * given BackendType is expected to do IO in the given IOContext. + */ +bool +pgstat_bktype_io_context_valid(BackendType bktype, IOContext io_context) +{ + bool no_strategy; + bool no_local; + + /* + * Not all BackendTypes will use a BufferAccessStrategy. + */ + no_strategy = bktype == B_AUTOVAC_LAUNCHER || bktype == + B_BG_WRITER || bktype == B_CHECKPOINTER; + + /* + * In core Postgres, only regular backends and WAL Sender processes + * executing queries should use local buffers. Parallel workers will not + * use local buffers (see InitLocalBuffers()); however, extensions + * leveraging background workers have no such limitation, so track IO + * Operations in IOCONTEXT_LOCAL for BackendType B_BG_WORKER. + */ + no_local = bktype == B_AUTOVAC_LAUNCHER || bktype == B_BG_WRITER || bktype + == B_CHECKPOINTER || bktype == B_AUTOVAC_WORKER || bktype == + B_STANDALONE_BACKEND || bktype == B_STARTUP; + + if (io_context == IOCONTEXT_STRATEGY && no_strategy) + return false; + + if (io_context == IOCONTEXT_LOCAL && no_local) + return false; + + return true; +} + +/* + * Some BackendTypes will never do certain IOOps and some IOOps should not + * occur in certain IOContexts. Check that the given IO Operation is valid for + * the given BackendType in the given IOContext. Note that there are currently + * no cases of an IO Operation being invalid for a particular BackendType only + * within a certain IOContext. + */ +bool +pgstat_io_op_valid(BackendType bktype, IOContext io_context, IOOp io_op) +{ + /* + * Some BackendTypes should never track IO Operation statistics. + */ + Assert(pgstat_io_op_stats_collected(bktype)); + + if ((bktype == B_BG_WRITER || bktype == B_CHECKPOINTER) && io_op == + IOOP_READ) + return false; + + if ((bktype == B_AUTOVAC_LAUNCHER || bktype == B_BG_WRITER || bktype == + B_CHECKPOINTER) && io_op == IOOP_EXTEND) + return false; + + /* + * Temporary tables using local buffers are not logged and thus do not + * require fsync'ing. + * + * IOOP_FSYNC IOOps done by a backend using a BufferAccessStrategy are + * counted in the IOCONTEXT_SHARED IOContext. See comment in + * ForwardSyncRequest() for more details. + */ + if ((io_context == IOCONTEXT_LOCAL || io_context == IOCONTEXT_STRATEGY) && + io_op == IOOP_FSYNC) + return false; + + return true; +} + +bool +pgstat_expect_io_op(BackendType bktype, IOContext io_context, IOOp io_op) +{ + if (!pgstat_io_op_stats_collected(bktype)) + return false; + + if (!pgstat_bktype_io_context_valid(bktype, io_context)) + return false; + + if (!(pgstat_io_op_valid(bktype, io_context, io_op))) + return false; + + return true; +} diff --git a/src/include/pgstat.h b/src/include/pgstat.h index ad7334a0d2..ccc836a37f 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -276,6 +276,44 @@ typedef struct PgStat_CheckpointerStats PgStat_Counter buf_fsync_backend; } PgStat_CheckpointerStats; +/* + * Types related to counting IO Operations for various IO Contexts + */ + +typedef enum IOOp +{ + IOOP_ALLOC, + IOOP_EXTEND, + IOOP_FSYNC, + IOOP_READ, + IOOP_WRITE, +} IOOp; + +#define IOOP_NUM_TYPES (IOOP_WRITE + 1) + +typedef enum IOContext +{ + IOCONTEXT_LOCAL, + IOCONTEXT_SHARED, + IOCONTEXT_STRATEGY, +} IOContext; + +#define IOCONTEXT_NUM_TYPES (IOCONTEXT_STRATEGY + 1) + +typedef struct PgStat_IOOpCounters +{ + PgStat_Counter allocs; + PgStat_Counter extends; + PgStat_Counter fsyncs; + PgStat_Counter reads; + PgStat_Counter writes; +} PgStat_IOOpCounters; + +typedef struct PgStat_IOContextOps +{ + PgStat_IOOpCounters data[IOCONTEXT_NUM_TYPES]; +} PgStat_IOContextOps; + typedef struct PgStat_StatDBEntry { PgStat_Counter n_xact_commit; @@ -453,6 +491,21 @@ extern void pgstat_report_checkpointer(void); extern PgStat_CheckpointerStats *pgstat_fetch_stat_checkpointer(void); +/* + * Functions in pgstat_io_ops.c + */ + +extern void pgstat_count_io_op(IOOp io_op, IOContext io_context); +extern const char *pgstat_io_context_desc(IOContext io_context); +extern const char *pgstat_io_op_desc(IOOp io_op); + +/* Validation functions in pgstat_io_ops.c */ +extern bool pgstat_io_op_stats_collected(BackendType bktype); +extern bool pgstat_bktype_io_context_valid(BackendType bktype, IOContext io_context); +extern bool pgstat_io_op_valid(BackendType bktype, IOContext io_context, IOOp io_op); +extern bool pgstat_expect_io_op(BackendType bktype, IOContext io_context, IOOp io_op); + + /* * Functions in pgstat_database.c */ diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 406db6be78..50d7e586e9 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -392,7 +392,7 @@ extern void ScheduleBufferTagForWriteback(WritebackContext *context, BufferTag * /* freelist.c */ extern BufferDesc *StrategyGetBuffer(BufferAccessStrategy strategy, - uint32 *buf_state); + uint32 *buf_state, bool *from_ring); extern void StrategyFreeBuffer(BufferDesc *buf); extern bool StrategyRejectBuffer(BufferAccessStrategy strategy, BufferDesc *buf); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 97c9bc1861..67218ec6f2 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1106,7 +1106,9 @@ ID INFIX INT128 INTERFACE_INFO +IOContext IOFuncSelector +IOOp IPCompareMethod ITEM IV @@ -2026,6 +2028,8 @@ PgStat_FetchConsistency PgStat_FunctionCallUsage PgStat_FunctionCounts PgStat_HashKey +PgStat_IOContextOps +PgStat_IOOpCounters PgStat_Kind PgStat_KindInfo PgStat_LocalState -- 2.34.1
