agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
200+ messages / 4 participants
[nested] [flat]

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * value. In a 2nd step we adjust the number of elapsed ticks and
+		 * convert the remaining ticks.
+		 */
+		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * Subtract the ticks that we now already accounted for, so that they
+		 * don't get counted twice.
+		 */
+		t.ticks -= count * max_ticks_no_overflow;
+		Assert(t.ticks >= 0);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread

* [PATCH v1] Add per-backend AIO statistics
@ 2026-06-11 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 200+ messages in thread

From: Bertrand Drouvot @ 2026-06-11 09:45 UTC (permalink / raw)

This commit adds per-backend AIO statistics, providing per-backend AIO behavior
details.

This data can be retrieved with a new system function called
pg_stat_get_backend_aio(), that returns the following counters based on the PID
provided in input:

- started: total number of AIO operations initiated
- executed_sync: IOs that were executed synchronously (fallback path)
- executed_async: IOs that were submitted asynchronously to the IO method
- completed_self: IO completions processed by the issuing backend itself
- completed_other: IO completions processed on behalf of another backend
- handle_waits: times the backend had to wait for a free AIO handle
- submitted: number of submitted calls to the IO method

These counters are useful for understanding and tuning AIO behavior:

- executed_async / started. A ratio near zero means the backend is falling back
to synchronous execution (TOAST chunk fetches, temp buffers, ...).

- a non-zero handle_waits means the backend exhausted all its AIO handles. That
could mean that io_max_concurrency is too low.

- completed_self vs completed_other reveals cross-backend completion
patterns. That helps see how IO completion work is distributed and could
help interpret per backend IO statistics values.

- executed_async / submitted gives the average batch size per submit call.

This commit is straight-forward, relying on the infrastructure provided
by 9aea73fc61d4 (backend-level pgstats).

XXX: Bump catalog version. No need to touch PGSTAT_FILE_FORMAT_ID as backend
statistics are never written to disk.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 doc/src/sgml/monitoring.sgml                |  70 +++++++++++++
 src/backend/storage/aio/aio.c               |  13 +++
 src/backend/utils/activity/pgstat_backend.c | 109 ++++++++++++++++++++
 src/backend/utils/adt/pgstatfuncs.c         |  60 +++++++++++
 src/include/catalog/pg_proc.dat             |   7 ++
 src/include/pgstat.h                        |  25 +++++
 src/include/utils/pgstat_internal.h         |   3 +-
 src/test/modules/test_aio/t/001_aio.pl      |  32 ++++++
 src/tools/pgindent/typedefs.list            |   1 +
 9 files changed, 319 insertions(+), 1 deletion(-)
  24.4% doc/src/sgml/
   3.2% src/backend/storage/aio/
  25.3% src/backend/utils/activity/
  20.5% src/backend/utils/adt/
   4.9% src/include/catalog/
  10.0% src/include/
  11.1% src/test/modules/test_aio/t/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 12b9ee20d4a..1c566cf0e0e 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -5641,6 +5641,76 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-aio" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_aio</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_aio</function> ( <type>integer</type> )
+        <returnvalue>record</returnvalue>
+       </para>
+       <para>
+        Returns <acronym>AIO</acronym> (Asynchronous I/O) statistics about the
+        backend with the specified process ID. The returned values are:
+       <itemizedlist>
+        <listitem>
+         <para>
+          <literal>started</literal>: Total IOs initiated.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+           <literal>executed_sync</literal>: IOs executed synchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>executed_async</literal>: IOs submitted asynchronously.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_self</literal>: IO completions processed by this
+          backend.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>completed_other</literal>: IO completions processed on
+          behalf of other backends.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>handle_waits</literal>: Times waited for a free AIO handle.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>submitted</literal>: Number of submit calls to the IO
+          method. Compare with <literal>executed_async</literal> to determine
+          average batch size.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
+          <literal>stats_reset</literal>: Timestamp of last stats reset.
+         </para>
+        </listitem>
+       </itemizedlist>
+       </para>
+       <para>
+        The <literal>completed_other</literal> column is only meaningful
+        when <varname>io_method</varname> is set to <literal>io_uring</literal>;
+        with <literal>worker</literal> mode, IO completions are processed by
+        IO worker processes which do not track these statistics.
+       </para>
+       <para>
+        The function does not return AIO statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index 8f7e26607b9..507f1727d41 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -40,6 +40,7 @@
 
 #include "lib/ilist.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "port/atomics.h"
 #include "storage/aio.h"
 #include "storage/aio_internal.h"
@@ -458,6 +459,8 @@ pgaio_io_stage(PgAioHandle *ioh, PgAioOp op)
 				   "staged (synchronous: %d, in_batch: %d)",
 				   needs_synchronous, pgaio_my_backend->in_batchmode);
 
+	pgstat_count_backend_aio_start(needs_synchronous);
+
 	if (!needs_synchronous)
 	{
 		pgaio_my_backend->staged_ios[pgaio_my_backend->num_staged_ios++] = ioh;
@@ -544,6 +547,12 @@ pgaio_io_process_completion(PgAioHandle *ioh, int result)
 	/* condition variable broadcast ensures state is visible before wakeup */
 	ConditionVariableBroadcast(&ioh->cv);
 
+	/* Track AIO completion stats */
+	if (ioh->owner_procno == MyProcNumber)
+		pgstat_count_backend_aio_complete_self();
+	else
+		pgstat_count_backend_aio_complete_other();
+
 	/* contains call to pgaio_io_call_complete_local() */
 	if (ioh->owner_procno == MyProcNumber)
 		pgaio_io_reclaim(ioh);
@@ -762,6 +771,8 @@ pgaio_io_wait_for_free(void)
 {
 	int			reclaimed = 0;
 
+	pgstat_count_backend_aio_handle_wait();
+
 	pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
 				pgaio_my_backend->num_staged_ios,
 				dclist_count(&pgaio_my_backend->in_flight_ios),
@@ -1150,6 +1161,8 @@ pgaio_submit_staged(void)
 
 	Assert(total_submitted == did_submit);
 
+	pgstat_count_backend_aio_submitted();
+
 	pgaio_my_backend->num_staged_ios = 0;
 
 	pgaio_debug(DEBUG4,
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index b736b2ccc6f..4ad755f7f18 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -40,6 +40,7 @@
 static PgStat_BackendPending PendingBackendStats;
 static bool backend_has_iostats = false;
 static bool backend_has_lockstats = false;
+static bool backend_has_aiostats = false;
 
 /*
  * WAL usage counters saved from pgWalUsage at the previous call to
@@ -120,6 +121,74 @@ pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type)
 	pgstat_report_fixed = true;
 }
 
+/*
+ * Utility routines to report AIO stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_aio_start(bool synchronous)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.started++;
+	if (synchronous)
+		PendingBackendStats.aio_counters.executed_sync++;
+	else
+		PendingBackendStats.aio_counters.executed_async++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_self(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_self++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_complete_other(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.completed_other++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_handle_wait(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.handle_waits++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
+void
+pgstat_count_backend_aio_submitted(void)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	PendingBackendStats.aio_counters.submitted++;
+
+	backend_has_aiostats = true;
+	pgstat_report_fixed = true;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -326,6 +395,38 @@ pgstat_flush_backend_entry_lock(PgStat_EntryRef *entry_ref)
 	backend_has_lockstats = false;
 }
 
+/*
+ * Flush out locally pending backend AIO statistics.  Locking is managed
+ * by the caller.
+ */
+static void
+pgstat_flush_backend_entry_aio(PgStat_EntryRef *entry_ref)
+{
+	PgStatShared_Backend *shbackendent;
+	PgStat_AioCounters *bktype_shstats;
+
+	if (!backend_has_aiostats)
+		return;
+
+	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendent->stats.aio_counters;
+
+#define AIOSTAT_ACC(fld) \
+	(bktype_shstats->fld += PendingBackendStats.aio_counters.fld)
+	AIOSTAT_ACC(started);
+	AIOSTAT_ACC(executed_sync);
+	AIOSTAT_ACC(executed_async);
+	AIOSTAT_ACC(completed_self);
+	AIOSTAT_ACC(completed_other);
+	AIOSTAT_ACC(handle_waits);
+	AIOSTAT_ACC(submitted);
+#undef AIOSTAT_ACC
+
+	MemSet(&PendingBackendStats.aio_counters, 0, sizeof(PgStat_AioCounters));
+
+	backend_has_aiostats = false;
+}
+
 /*
  * Flush out locally pending backend statistics
  *
@@ -354,6 +455,10 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if ((flags & PGSTAT_BACKEND_FLUSH_LOCK) && backend_has_lockstats)
 		has_pending_data = true;
 
+	/* Some AIO data pending? */
+	if ((flags & PGSTAT_BACKEND_FLUSH_AIO) && backend_has_aiostats)
+		has_pending_data = true;
+
 	if (!has_pending_data)
 		return false;
 
@@ -372,6 +477,9 @@ pgstat_flush_backend(bool nowait, uint32 flags)
 	if (flags & PGSTAT_BACKEND_FLUSH_LOCK)
 		pgstat_flush_backend_entry_lock(entry_ref);
 
+	if (flags & PGSTAT_BACKEND_FLUSH_AIO)
+		pgstat_flush_backend_entry_aio(entry_ref);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return false;
@@ -411,6 +519,7 @@ pgstat_create_backend(ProcNumber procnum)
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 	backend_has_iostats = false;
 	backend_has_lockstats = false;
+	backend_has_aiostats = false;
 
 	/*
 	 * Initialize prevBackendWalUsage with pgWalUsage so that
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 565d0e70768..fb62a56f3fe 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1722,6 +1722,66 @@ pg_stat_get_backend_wal(PG_FUNCTION_ARGS)
 	return (pg_stat_wal_build_tuple(bktype_stats, backend_stats->stat_reset_timestamp));
 }
 
+/*
+ * Returns AIO statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_aio(PG_FUNCTION_ARGS)
+{
+#define PG_STAT_BACKEND_AIO_COLS	8
+	TupleDesc	tupdesc;
+	Datum		values[PG_STAT_BACKEND_AIO_COLS] = {0};
+	bool		nulls[PG_STAT_BACKEND_AIO_COLS] = {0};
+	int			pid;
+	PgStat_Backend *backend_stats;
+	PgStat_AioCounters aio_counters;
+
+	pid = PG_GETARG_INT32(0);
+	backend_stats = pgstat_fetch_stat_backend_by_pid(pid, NULL);
+
+	if (!backend_stats)
+		PG_RETURN_NULL();
+
+	aio_counters = backend_stats->aio_counters;
+
+	/* Initialise attributes information in the tuple descriptor */
+	tupdesc = CreateTemplateTupleDesc(PG_STAT_BACKEND_AIO_COLS);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "started",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 2, "executed_sync",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 3, "executed_async",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 4, "completed_self",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 5, "completed_other",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 6, "handle_waits",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 7, "submitted",
+					   INT8OID, -1, 0);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 8, "stats_reset",
+					   TIMESTAMPTZOID, -1, 0);
+	TupleDescFinalize(tupdesc);
+	BlessTupleDesc(tupdesc);
+
+	/* Fill values */
+	values[0] = Int64GetDatum(aio_counters.started);
+	values[1] = Int64GetDatum(aio_counters.executed_sync);
+	values[2] = Int64GetDatum(aio_counters.executed_async);
+	values[3] = Int64GetDatum(aio_counters.completed_self);
+	values[4] = Int64GetDatum(aio_counters.completed_other);
+	values[5] = Int64GetDatum(aio_counters.handle_waits);
+	values[6] = Int64GetDatum(aio_counters.submitted);
+
+	if (backend_stats->stat_reset_timestamp != 0)
+		values[7] = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+	else
+		nulls[7] = true;
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..a089860ada4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6108,6 +6108,13 @@
   proargmodes => '{i,o,o,o,o,o}',
   proargnames => '{backend_pid,locktype,waits,wait_time,fastpath_exceeded,stats_reset}',
   prosrc => 'pg_stat_get_backend_lock' },
+{ oid => '9082', descr => 'statistics: backend AIO activity',
+  proname => 'pg_stat_get_backend_aio', provolatile => 'v', proparallel => 'r',
+  prorettype => 'record', proargtypes => 'int4',
+  proallargtypes => '{int4,int8,int8,int8,int8,int8,int8,int8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,started,executed_sync,executed_async,completed_self,completed_other,handle_waits,submitted,stats_reset}',
+  prosrc => 'pg_stat_get_backend_aio' },
 { oid => '6248', descr => 'statistics: information about WAL prefetching',
   proname => 'pg_stat_get_recovery_prefetch', prorows => '1', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 58a44857f13..64afb2bc082 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -514,6 +514,21 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/* -------
+ * PgStat_AioCounters	AIO activity counters
+ * -------
+ */
+typedef struct PgStat_AioCounters
+{
+	PgStat_Counter started;
+	PgStat_Counter executed_sync;
+	PgStat_Counter executed_async;
+	PgStat_Counter completed_self;
+	PgStat_Counter completed_other;
+	PgStat_Counter handle_waits;
+	PgStat_Counter submitted;
+} PgStat_AioCounters;
+
 /* -------
  * PgStat_Backend		Backend statistics
  * -------
@@ -524,6 +539,7 @@ typedef struct PgStat_Backend
 	PgStat_BktypeIO io_stats;
 	PgStat_WalCounters wal_counters;
 	PgStat_PendingLock lock_stats;
+	PgStat_AioCounters aio_counters;
 } PgStat_Backend;
 
 /* ---------
@@ -542,6 +558,8 @@ typedef struct PgStat_BackendPending
 	 * PGSTAT_KIND_LOCK.
 	 */
 	PgStat_PendingLock pending_lock;
+	/* Store the AIO statistics counters */
+	PgStat_AioCounters aio_counters;
 } PgStat_BackendPending;
 
 /*
@@ -598,6 +616,13 @@ extern void pgstat_count_backend_io_op(IOObject io_object,
 extern void pgstat_count_backend_lock_waits(uint8 locktag_type, PgStat_Counter usecs);
 extern void pgstat_count_backend_lock_fastpath_exceeded(uint8 locktag_type);
 
+/* used by aio.c for AIO stats tracked in backends */
+extern void pgstat_count_backend_aio_start(bool synchronous);
+extern void pgstat_count_backend_aio_complete_self(void);
+extern void pgstat_count_backend_aio_complete_other(void);
+extern void pgstat_count_backend_aio_handle_wait(void);
+extern void pgstat_count_backend_aio_submitted(void);
+
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern PgStat_Backend *pgstat_fetch_stat_backend_by_pid(int pid,
 														BackendType *bktype);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index b3dc3ff7d8b..b2092fb42b9 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -706,7 +706,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_LOCK  (1 << 2) /* Flush lock statistics */
-#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK)
+#define PGSTAT_BACKEND_FLUSH_AIO   (1 << 3) /* Flush AIO statistics */
+#define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL | PGSTAT_BACKEND_FLUSH_LOCK | PGSTAT_BACKEND_FLUSH_AIO)
 
 extern bool pgstat_flush_backend(bool nowait, uint32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
diff --git a/src/test/modules/test_aio/t/001_aio.pl b/src/test/modules/test_aio/t/001_aio.pl
index 63cadd64c15..8ecf3d3ad91 100644
--- a/src/test/modules/test_aio/t/001_aio.pl
+++ b/src/test/modules/test_aio/t/001_aio.pl
@@ -1842,6 +1842,37 @@ read_buffers('$table', 0, 4)|,
 	$psql_c->quit();
 }
 
+# Test per-backend AIO statistics counters
+sub test_aio_stats
+{
+	my $io_method = shift;
+	my $node = shift;
+
+	my $psql = $node->background_psql('postgres', on_error_stop => 0);
+
+	# Reset backend stats, evict relation, then read it back to force
+	# physical IO through the AIO layer.
+	$psql->query_safe(qq(SELECT pg_stat_reset_backend_stats(pg_backend_pid())));
+	$psql->query_safe(qq(SELECT evict_rel('tbl_ok')));
+	$psql->query_safe(qq(SELECT count(*) FROM tbl_ok));
+	$psql->query_safe(qq(SELECT pg_stat_force_next_flush()));
+
+	# started must be > 0 after physical IO
+	my $started = $psql->query_safe(
+		qq(SELECT started FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	cmp_ok($started, '>', 0,
+		"$io_method: AIO stats: started > 0 after physical IO");
+
+	# invariant: started = executed_sync + executed_async
+	my $consistent = $psql->query_safe(
+		qq(SELECT started = executed_sync + executed_async
+		   FROM pg_stat_get_backend_aio(pg_backend_pid())));
+	is($consistent, 't',
+		"$io_method: AIO stats: started = executed_sync + executed_async");
+
+	$psql->quit();
+}
+
 # Run all tests that for the specified node / io_method
 sub test_io_method
 {
@@ -1878,6 +1909,7 @@ CHECKPOINT;
 	test_ignore_checksum($io_method, $node);
 	test_checksum_createdb($io_method, $node);
 	test_read_buffers($io_method, $node);
+	test_aio_stats($io_method, $node);
 
 	# generic injection tests
   SKIP:
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 117e7379f10..6ce3077fa5b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2329,6 +2329,7 @@ PgStatShared_ReplSlot
 PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
+PgStat_AioCounters
 PgStat_ArchiverStats
 PgStat_Backend
 PgStat_BackendPending
-- 
2.34.1


--Pi0/Nu3LVhi0Ij+H--





^ permalink  raw  reply  [nested|flat] 200+ messages in thread