From: | "Kevin Grittner" <Kevin(dot)Grittner(at)wicourts(dot)gov> |
---|---|
To: | "Scott Marlowe" <scott(dot)marlowe(at)gmail(dot)com>, "Jennifer Spencer" <jenniferm411(at)hotmail(dot)com> |
Cc: | <scott(dot)lists(at)enterprisedb(dot)com>,<pgsql-admin(at)postgresql(dot)org> |
Subject: | Re: Catching up Production from Warm Standby after maintenance - Please help |
Date: | 2009-07-08 15:52:39 |
Message-ID: | 4A547A770200002500028580@gw.wicourts.gov |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-admin |
Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> wrote:
> Jennifer Spencer<jenniferm411(at)hotmail(dot)com> wrote:
>> new ones coming have 5 TB each of RAID disks mirrored across to
>> another 5TB (20 5.4gb spinning disks). Not sure the RAID level but
>> I think it's level six. They each have 16 CPUs, and (I believe)
>> 128 Gb of RAM, connected to our NFS network on a 10g switch (at
>> least I think it's the 10 gigabit switch - it might be one
>> gigabit).
> get a battery backed cache if you can.
I'd say that with the rest of the hardware described, performance will
be very disappointing without a good RAID controller with battery
backed cache configured for write-back. Also, file system (we use
XFS) and mount options (we use noatime and nobarrier), and elevator
(we use deadline) can make a big difference.
-Kevin
From | Date | Subject | |
---|---|---|---|
Next Message | Kevin Grittner | 2009-07-08 16:02:10 | Re: Catching up Production from Warm Standby after maintenance - Please help |
Previous Message | Scott Marlowe | 2009-07-08 02:17:34 | Re: Catching up Production from Warm Standby after maintenance - Please help |