agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 5/6] Add copy progress reporting regression tests.
17+ messages / 2 participants
[nested] [flat]

* [PATCH 5/6] Add copy progress reporting regression tests.
@ 2021-02-09 12:06  Josef Šimánek <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Josef Šimánek @ 2021-02-09 12:06 UTC (permalink / raw)

This tests some basic features of copy progress reporting.

Sadly, we can only request one snapshot of progress_reporting each
transaction / statement, so we can't (easily) get intermediate results without
each result requiring a seperate statement being run.

Author: Josef Šimánek, Matthias van de Meent
---
 src/test/regress/input/copy.source  | 57 +++++++++++++++++++++++++++++
 src/test/regress/output/copy.source | 44 ++++++++++++++++++++++
 2 files changed, 101 insertions(+)

diff --git a/src/test/regress/input/copy.source b/src/test/regress/input/copy.source
index a1d529ad36..ddde33e7cc 100644
--- a/src/test/regress/input/copy.source
+++ b/src/test/regress/input/copy.source
@@ -201,3 +201,60 @@ select * from parted_copytest where b = 1;
 select * from parted_copytest where b = 2;
 
 drop table parted_copytest;
+
+--
+-- progress reporting
+-- 
+
+-- setup
+-- reuse employer datatype, that has a small sized data set
+
+create table progress_reporting (
+	name 		text,
+	age			int4,
+	location 	point,
+	salary 		int4,
+	manager 	name
+);
+
+create function notice_after_progress_reporting() returns trigger AS
+$$
+declare report record;
+begin
+	-- We cannot expect 'pid' nor 'relid' to be consistent over runs due to 
+	-- variance in system process ids, and concurrency in runs of tests.
+	-- Additionally, due to the usage of this test in pg_regress, the 'datid'
+	-- also is not consistent between runs.
+	select into report (to_jsonb(r) - '{pid,relid,datid}'::text[]) as value
+		from pg_stat_progress_copy r
+		where pid = pg_backend_pid();
+
+	raise info 'progress: %', report.value::text;
+
+	RETURN NEW;
+END;
+$$ LANGUAGE plpgsql;
+
+create trigger check_after_progress_reporting
+	after insert on progress_reporting
+	for each statement
+	execute function notice_after_progress_reporting();
+
+-- reporting of STDIO imports, and correct bytes-processed/tuples-processed reporting
+
+copy progress_reporting from stdin;
+sharon	25	(15,12)	1000	sam
+sam	30	(10,5)	2000	bill
+bill	20	(11,10)	1000	sharon
+\.
+
+-- reporting of FILE imports, and correct reporting of tuples-excluded
+
+copy progress_reporting from '@abs_srcdir@/data/emp.data'
+	where (salary < 2000);
+
+-- cleanup progress_reporting
+
+drop trigger check_after_progress_reporting on progress_reporting;
+drop function notice_after_progress_reporting();
+drop table progress_reporting;
diff --git a/src/test/regress/output/copy.source b/src/test/regress/output/copy.source
index 938d3551da..60f4206aa1 100644
--- a/src/test/regress/output/copy.source
+++ b/src/test/regress/output/copy.source
@@ -165,3 +165,47 @@ select * from parted_copytest where b = 2;
 (1 row)
 
 drop table parted_copytest;
+--
+-- progress reporting
+-- 
+-- setup
+-- reuse employer datatype, that has a small sized data set
+create table progress_reporting (
+	name 		text,
+	age			int4,
+	location 	point,
+	salary 		int4,
+	manager 	name
+);
+create function notice_after_progress_reporting() returns trigger AS
+$$
+declare report record;
+begin
+	-- We cannot expect 'pid' nor 'relid' to be consistent over runs due to 
+	-- variance in system process ids, and concurrency in runs of tests.
+	-- Additionally, due to the usage of this test in pg_regress, the 'datid'
+	-- also is not consistent between runs.
+	select into report (to_jsonb(r) - '{pid,relid,datid}'::text[]) as value
+		from pg_stat_progress_copy r
+		where pid = pg_backend_pid();
+
+	raise info 'progress: %', report.value::text;
+
+	RETURN NEW;
+END;
+$$ LANGUAGE plpgsql;
+create trigger check_after_progress_reporting
+	after insert on progress_reporting
+	for each statement
+	execute function notice_after_progress_reporting();
+-- reporting of STDIO imports, and correct bytes-processed/tuples-processed reporting
+copy progress_reporting from stdin;
+INFO:  progress: {"command": "COPY FROM", "datname": "regression", "io_target": "STDIO", "bytes_total": 0, "bytes_processed": 79, "tuples_excluded": 0, "tuples_processed": 3}
+-- reporting of FILE imports, and correct reporting of tuples-excluded
+copy progress_reporting from '@abs_srcdir@/data/emp.data'
+	where (salary < 2000);
+INFO:  progress: {"command": "COPY FROM", "datname": "regression", "io_target": "FILE", "bytes_total": 79, "bytes_processed": 79, "tuples_excluded": 1, "tuples_processed": 2}
+-- cleanup progress_reporting
+drop trigger check_after_progress_reporting on progress_reporting;
+drop function notice_after_progress_reporting();
+drop table progress_reporting;
-- 
2.26.2


--------------DA8D60BF026F7ACE69A9AEE5
Content-Type: text/x-patch; charset=UTF-8;
 name="v7-0006-0003-review.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v7-0006-0003-review.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2 19/20] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index dffdd57e9b5..f5795b509c7 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.45.2.746.g06e570c0df.dirty


--oy2jwuii6tssbict
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0020-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.3 28/30] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 1f757d96f07..ac19fb87433 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--gbq4ah2rmhae7qhd
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.3-0029-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.4 27/29] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--4ckqsto27zwk2eqr
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.4-0028-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.5 28/30] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--abvteypvk35ocehs
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.5-0029-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.6 32/34] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--6g5xner6ro2tsnwz
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.6-0033-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.7 33/35] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--vsphh7g5lukufvxs--





^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.8 35/38] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--ow5flh3n247znjrs
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.8-0036-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.1 20/20] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index dffdd57e9b5..5be8125ad3a 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,11 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.45.2.827.g557ae147e6


--ggp33qz5xusicvk6--





^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.0 17/17] Temporary: Increase BAS_BULKREAD size
@ 2024-09-01 04:42  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2024-09-01 04:42 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index dffdd57e9b5..5be8125ad3a 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,11 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.45.2.827.g557ae147e6


--ww2auydviafoh7lh--





^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.9 27/30] Temporary: Increase BAS_BULKREAD size
@ 2025-03-15 16:29  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-15 16:29 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--23jbdfobqrqxnmx5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.9-0028-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.11 25/27] Temporary: Increase BAS_BULKREAD size
@ 2025-03-18 18:40  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-18 18:40 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--bjnmbpad43bpmfxt
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.11-0026-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.12 25/28] Temporary: Increase BAS_BULKREAD size
@ 2025-03-18 18:40  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-18 18:40 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--5i73spx2p4vwf7fe
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.12-0026-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.10 24/28] Temporary: Increase BAS_BULKREAD size
@ 2025-03-18 18:40  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-18 18:40 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--w6dfit2y42fwvotd
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.10-0025-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.14 26/29] Temporary: Increase BAS_BULKREAD size
@ 2025-03-18 18:40  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-18 18:40 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--m2na7lgr3zfazgom
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.14-0027-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.15 15/18] Temporary: Increase BAS_BULKREAD size
@ 2025-03-18 18:40  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-18 18:40 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--xevce4sdbnyxplun
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.15-0016-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

* [PATCH v2.13 25/28] Temporary: Increase BAS_BULKREAD size
@ 2025-03-18 18:40  Andres Freund <[email protected]>
  0 siblings, 0 replies; 17+ messages in thread

From: Andres Freund @ 2025-03-18 18:40 UTC (permalink / raw)

Without this we only can execute very little AIO for sequential scans, as
there's just not enough buffers in the ring.  This isn't the right fix, as
just increasing the ring size can have negative performance implications in
workloads where the kernel has all the data cached.

Author:
Reviewed-By:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/backend/storage/buffer/freelist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index 336715b6c63..b72a5957a20 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -555,7 +555,12 @@ GetAccessStrategy(BufferAccessStrategyType btype)
 			return NULL;
 
 		case BAS_BULKREAD:
-			ring_size_kb = 256;
+
+			/*
+			 * FIXME: Temporary increase to allow large enough streaming reads
+			 * to actually benefit from AIO. This needs a better solution.
+			 */
+			ring_size_kb = 2 * 1024;
 			break;
 		case BAS_BULKWRITE:
 			ring_size_kb = 16 * 1024;
-- 
2.48.1.76.g4e746b1a31.dirty


--pro7bqageygxfsvg
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2.13-0026-WIP-Use-MAP_POPULATE.patch"



^ permalink  raw  reply  [nested|flat] 17+ messages in thread

end of thread, other threads:[~2025-03-18 18:40 UTC | newest]

Thread overview: 17+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2021-02-09 12:06 [PATCH 5/6] Add copy progress reporting regression tests. Josef Šimánek <[email protected]>
2024-09-01 04:42 [PATCH v2.7 33/35] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.6 32/34] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.8 35/38] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2 19/20] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.1 20/20] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.5 28/30] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.0 17/17] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.4 27/29] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2024-09-01 04:42 [PATCH v2.3 28/30] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-15 16:29 [PATCH v2.9 27/30] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-18 18:40 [PATCH v2.14 26/29] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-18 18:40 [PATCH v2.15 15/18] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-18 18:40 [PATCH v2.13 25/28] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-18 18:40 [PATCH v2.10 24/28] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-18 18:40 [PATCH v2.12 25/28] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>
2025-03-18 18:40 [PATCH v2.11 25/27] Temporary: Increase BAS_BULKREAD size Andres Freund <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox