Обсуждение: Performance drop after upgrading to 8.4.4?
Hi,
I was doing some benchmarking while changing configuration options to try to get more performance out of our postgresql servers and noticed that when running pgbench against 8.4.3 vs 8.4.4 on identical hardware and configuration there is a large difference in performance. I know tuning is a very deep topic and benchmarking is hardly an accurate indication of real world performance but I was still surprised by these results and wanted to know what I am doing wrong.
Hardware specs are:
2x Quad core Xeons 2.4Ghz
16GB RAM
2x RAID1 7.2k RPM disks
Relevant Postgresql Configuration:
max_connections = 1000
shared_buffers = 4096MB
temp_buffers = 8MB
max_prepared_transactions = 1000
work_mem = 8MB
maintenance_work_mem = 512MB
wal_buffers = 8MB
checkpoint_segments = 192
checkpoint_timeout = 30min
effective_cache_size = 12288MB
Results for the 8.4.3 (8.4.3-2PGDG.el5) host:
[root@some-host ~]# pgbench -h dbs3 -U postgres -i -s 100 pgbench1 > /dev/null 2>&1 && pgbench -h dbs3 -U postgres -c 100 -t 100000 pgbench1
starting vacuum...end.
transaction type: TPC-B (sort of)
scaling factor: 100
query mode: simple
number of clients: 100
number of transactions per client: 100000
number of transactions actually processed: 10000000/10000000
tps = 4612.734318 (including connections establishing)
tps = 4613.308264 (excluding connections establishing)
Results for the 8.4.4 (8.4.4-1PGDG.el5) host:
[root@ some-host ~]# pgbench -h dbs4 -U postgres -i -s 100 pgbench1 > /dev/null 2>&1 && pgbench -h dbs4 -U postgres -c 100 -t 100000 pgbench1
starting vacuum...end.
transaction type: TPC-B (sort of)
scaling factor: 100
query mode: simple
number of clients: 100
number of transactions per client: 100000
number of transactions actually processed: 10000000/10000000
tps = 2799.134267 (including connections establishing)
tps = 2799.451407 (excluding connections establishing)
Any input? I can reproduce these numbers consistently. By the way, I am a new postgresql user so my experience is limited.
Cheers,
Max
No one has had this problem??? Should I perhaps direct this to the developers list?
Cheers,
Max
From: pgsql-general-owner@postgresql.org [mailto:pgsql-general-owner@postgresql.org] On Behalf Of Max Williams
Sent: 03 June 2010 14:22
To: pgsql-general@postgresql.org
Subject: [GENERAL] Performance drop after upgrading to 8.4.4?
Hi,
I was doing some benchmarking while changing configuration options to try to get more performance out of our postgresql servers and noticed that when running pgbench against 8.4.3 vs 8.4.4 on identical hardware and configuration there is a large difference in performance. I know tuning is a very deep topic and benchmarking is hardly an accurate indication of real world performance but I was still surprised by these results and wanted to know what I am doing wrong.
Hardware specs are:
2x Quad core Xeons 2.4Ghz
16GB RAM
2x RAID1 7.2k RPM disks
Relevant Postgresql Configuration:
max_connections = 1000
shared_buffers = 4096MB
temp_buffers = 8MB
max_prepared_transactions = 1000
work_mem = 8MB
maintenance_work_mem = 512MB
wal_buffers = 8MB
checkpoint_segments = 192
checkpoint_timeout = 30min
effective_cache_size = 12288MB
Results for the 8.4.3 (8.4.3-2PGDG.el5) host:
[root@some-host ~]# pgbench -h dbs3 -U postgres -i -s 100 pgbench1 > /dev/null 2>&1 && pgbench -h dbs3 -U postgres -c 100 -t 100000 pgbench1
starting vacuum...end.
transaction type: TPC-B (sort of)
scaling factor: 100
query mode: simple
number of clients: 100
number of transactions per client: 100000
number of transactions actually processed: 10000000/10000000
tps = 4612.734318 (including connections establishing)
tps = 4613.308264 (excluding connections establishing)
Results for the 8.4.4 (8.4.4-1PGDG.el5) host:
[root@ some-host ~]# pgbench -h dbs4 -U postgres -i -s 100 pgbench1 > /dev/null 2>&1 && pgbench -h dbs4 -U postgres -c 100 -t 100000 pgbench1
starting vacuum...end.
transaction type: TPC-B (sort of)
scaling factor: 100
query mode: simple
number of clients: 100
number of transactions per client: 100000
number of transactions actually processed: 10000000/10000000
tps = 2799.134267 (including connections establishing)
tps = 2799.451407 (excluding connections establishing)
Any input? I can reproduce these numbers consistently. By the way, I am a new postgresql user so my experience is limited.
Cheers,
Max
Max Williams wrote: > > No one has had this problem??? Should I perhaps direct this to the > developers list? > pgsql-performance is the list you should have sent this to. There are several people who are subscribed to that one but not to -general or -hackers who enjoy helping with this particular type of problem. Make sure you include your operating system and disk controller information on that one, I wasn't sure where to start without those two bits of info. Also, see if the problem goes away if the client load is smaller. Peak pgbench performance on your system is going to be with between 8 and 16 clients, and the way it falls off after that depends on operating systems issues rather than PostgreSQL ones. -- Greg Smith 2ndQuadrant US Baltimore, MD PostgreSQL Training, Services and Support greg@2ndQuadrant.com www.2ndQuadrant.us
On Thu, Jun 3, 2010 at 9:22 AM, Max Williams <Max.Williams@mflow.com> wrote: > Hi, > > I was doing some benchmarking while changing configuration options to try to > get more performance out of our postgresql servers and noticed that when > running pgbench against 8.4.3 vs 8.4.4 on identical hardware and > configuration there is a large difference in performance. I know tuning is a > very deep topic and benchmarking is hardly an accurate indication of real > world performance but I was still surprised by these results and wanted to > know what I am doing wrong. > > > > Hardware specs are: > > 2x Quad core Xeons 2.4Ghz > > 16GB RAM > > 2x RAID1 7.2k RPM disks > > > > Relevant Postgresql Configuration: > > max_connections = 1000 > > shared_buffers = 4096MB > > temp_buffers = 8MB > > max_prepared_transactions = 1000 > > work_mem = 8MB > > maintenance_work_mem = 512MB > > wal_buffers = 8MB > > checkpoint_segments = 192 > > checkpoint_timeout = 30min > > effective_cache_size = 12288MB > > > > Results for the 8.4.3 (8.4.3-2PGDG.el5) host: > > [root@some-host ~]# pgbench -h dbs3 -U postgres -i -s 100 pgbench1 > > /dev/null 2>&1 && pgbench -h dbs3 -U postgres -c 100 -t 100000 pgbench1 > > starting vacuum...end. > > transaction type: TPC-B (sort of) > > scaling factor: 100 > > query mode: simple > > number of clients: 100 > > number of transactions per client: 100000 > > number of transactions actually processed: 10000000/10000000 > > tps = 4612.734318 (including connections establishing) > > tps = 4613.308264 (excluding connections establishing) > > > > Results for the 8.4.4 (8.4.4-1PGDG.el5) host: > > [root@ some-host ~]# pgbench -h dbs4 -U postgres -i -s 100 pgbench1 > > /dev/null 2>&1 && pgbench -h dbs4 -U postgres -c 100 -t 100000 pgbench1 > > starting vacuum...end. > > transaction type: TPC-B (sort of) > > scaling factor: 100 > > query mode: simple > > number of clients: 100 > > number of transactions per client: 100000 > > number of transactions actually processed: 10000000/10000000 > > tps = 2799.134267 (including connections establishing) > > tps = 2799.451407 (excluding connections establishing) > > > > Any input? I can reproduce these numbers consistently. By the way, I am a > new postgresql user so my experience is limited. nothing jumps out to me in terms of the release notes. any chance of getting some oprofile runs? merlin