From: | Craig Ringer <ringerc(at)ringerc(dot)id(dot)au> |
---|---|
To: | Samuel Gendler <sgendler(at)ideasculptor(dot)com> |
Cc: | Reza Taheri <rtaheri(at)vmware(dot)com>, Robert Klemme <shortcutter(at)googlemail(dot)com>, "pgsql-performance(at)postgresql(dot)org" <pgsql-performance(at)postgresql(dot)org> |
Subject: | Re: The need for clustered indexes to boost TPC-V performance |
Date: | 2012-07-06 00:57:40 |
Message-ID: | 4FF63804.2060107@ringerc.id.au |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-general pgsql-performance |
On 07/06/2012 04:52 AM, Samuel Gendler wrote:
>
>
> On Thu, Jul 5, 2012 at 1:37 PM, Reza Taheri <rtaheri(at)vmware(dot)com
> <mailto:rtaheri(at)vmware(dot)com>> wrote:
>
>
> I provided more config details in an earlier email.
>
>
>
> I hate to disagree, but unless I didn't get a message sent to the list
It looks like that might be the case. I got a message with Message-ID
66CE997FB523C04E9749452273184C6C137CB88CDD(at)exch-mbx-113(dot)vmware(dot)com sent
at Thu, 5 Jul 2012 11:33:46 -0700 that contained the basic info,
postgresql.conf, etc. Belated, but it was sent. I can't find this
message in the archives and the copy I got came direct to me via cc, so
I suspect our friendly mailing list system has silently held it for
moderation due to size/attachment.
I'll reproduce the content below, followed by an inline copy of the
postgresql.conf with only changed lines:
On 07/06/2012 02:33 AM, Reza Taheri wrote:
>
> OK, some config details.
>
> We are using:
>
> ·Two blades of an HP BladeSystem c-Class c7000 with 2-socket Intel
> E5520 (Nehalem-EP) processors and 48GB of memory per blade
>
> o8 cores, 16 threads per blade
>
> o48GB of RAM per blade
>
> ·Storage was an EMC VNX5700 with 14 SSDs fronting 32 15K RPM drives
>
> ·The Tier B database VM was alone on a blade with 16 vCPUs, 40GB of
> memory, 4 virtual drives with various RAID levels
>
> ·The driver and Tier A VMs were on the second blade
>
> oSo we set PGHOST on the client system to point to the server
>
> ·RHEL 6.1
>
> ·PostgreSQL 8.4
>
> ·unixODBC 2.3.2
>
> We stuck with PGSQL 8.4 since it is the stock version shipped with
> RHEL 6. I am building a new, larger testbed, and will switch to PGSQL
> 9 with that.
>
>
postgresql.conf:
[craig(at)ayaki ~]$ egrep -v '(^\s*#)|(^\s*$)' /tmp/postgresql2.conf | cut
-d '#' -f 1
listen_addresses = '*'
max_connections = 320
shared_buffers = 28GB
temp_buffers = 200MB
work_mem = 10MB
maintenance_work_mem = 10MB
bgwriter_delay = 10ms
bgwriter_lru_maxpages = 20
wal_buffers = 16MB
checkpoint_segments = 128
checkpoint_timeout = 30min
checkpoint_completion_target = 0.9
default_statistics_target = 10000
logging_collector = on
log_directory = 'pg_log'
log_filename = 'postgresql-%a.log'
log_truncate_on_rotation = on
log_rotation_age = 1d
log_rotation_size = 0
datestyle = 'iso, mdy'
lc_messages = 'en_US.UTF-8'
lc_monetary = 'en_US.UTF-8'
lc_numeric = 'en_US.UTF-8'
lc_time = 'en_US.UTF-8'
default_text_search_config = 'pg_catalog.english'
From | Date | Subject | |
---|---|---|---|
Next Message | Reza Taheri | 2012-07-06 01:00:41 | Re: The need for clustered indexes to boost TPC-V performance |
Previous Message | Craig Ringer | 2012-07-06 00:46:11 | Re: The need for clustered indexes to boost TPC-V performance |
From | Date | Subject | |
---|---|---|---|
Next Message | Reza Taheri | 2012-07-06 01:00:41 | Re: The need for clustered indexes to boost TPC-V performance |
Previous Message | Mark Kirkwood | 2012-07-06 00:51:33 | SSDs again, LSI Warpdrive 2 anyone? |