Postgres Pro
Downloads
Home   >   mailing lists

Re: [HACKERS] Should we cacheline align PGXACT? - Mailing list pgsql-hackers

From Ashutosh Sharma
Subject Re: [HACKERS] Should we cacheline align PGXACT?
Date
Msg-id CAE9k0P=84-naHEpyaTYmcev7LBJ99fmeJuxNVZMz-CHPCqYquA@mail.gmail.com
Whole thread Raw
In response to Re: [HACKERS] Should we cacheline align PGXACT?  (Simon Riggs <simon@2ndquadrant.com>)
Responses Re: [HACKERS] Should we cacheline align PGXACT?  (Simon Riggs <simon@2ndquadrant.com>)
List pgsql-hackers
Tree view
On Tue, Feb 28, 2017 at 11:44 PM, Simon Riggs <simon@2ndquadrant.com> wrote:
On 28 February 2017 at 11:34, Ashutosh Sharma <ashu.coek88@gmail.com> wrote:
 
So, Here are the pgbench results I got with 'reduce_pgxact_access_AtEOXact.v2.patch' on a read-write workload.

Thanks for performing a test.

I see a low yet noticeable performance gain across the board on that workload.

That is quite surprising to see a gain on that workload. The main workload we have been discussing was the full read-only test (-S). For that case the effect should be much more noticeable based upon Andres' earlier comments.

Would it be possible to re-run the test using only the -S workload? Thanks very much.

Okay, I already had the results for read-oly workload but just forgot to share it along with the results for read-write test. Here are the results for read-only
test,

CLIENT COUNTTPS (HEAD)TPS (PATCH)% IMPROVEMENT
4263223125918.75617354
863499694729.406447346
161811551865342.96928045
323335043375331.208081462
643503413537470.9721956608
723663393738982.063389374
1284433814785627.934710779
18029987533411811.41909129
1962691942755252.351835479
2562200272359957.257291151


The pgbench settings and non-default params are,

pgbench -i -s 300 postgres
pgbench -M prepared -c $thread -j $thread -T $time_for_reading -S postgres

where, time_for_reading = 10mins

non default param:
shared_buffers=8GB
max_connections=300

--
With Regards,
Ashutosh Sharma
EnterpriseDB:http://www.enterprisedb.com

pgbench settings:
pgbench -i -s 300 postgres
pgbench -M prepared -c $thread -j $thread -T $time_for_reading  postgres

where, time_for_reading = 30mins

non default GUC param
shared_buffers=8GB
max_connections=300

pg_wal is located in SSD.

CLIENT COUNTTPS (HEAD)TPS (PATCH)% IMPROVEMENT
4258826010.5023183926
8509450980.0785237534
1610294103070.1262871576
3219779198150.182011224
6427908283461.569442454
7227823284162.131330194
12828455286180.5728342998
18026739268790.5235797898
19627820279630.5140186916
25628763289690.7161978931


Also, Excel sheet (results-readwrite-300-SF.xlsx) containing the results for all the 3 runs is attached.



--
Simon Riggs                http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services

pgsql-hackers by date:

Previous
From: Peter Eisentraut
Date:
Subject: Re: [HACKERS] rename pg_log directory?
Next
From: Peter Eisentraut
Date:
Subject: Re: [HACKERS] rename pg_log directory?