| From: | Mark Kirkwood <mark(dot)kirkwood(at)catalyst(dot)net(dot)nz> | 
|---|---|
| To: | Jan Nielsen <jan(dot)sture(dot)nielsen(at)gmail(dot)com> | 
| Cc: | pgsql-performance(at)postgresql(dot)org | 
| Subject: | Re: Configuration Recommendations | 
| Date: | 2012-05-24 04:59:44 | 
| Message-ID: | 4FBDC040.2000406@catalyst.net.nz | 
| Views: | Whole Thread | Raw Message | Download mbox | Resend email | 
| Thread: | |
| Lists: | pgsql-performance | 
On 20/05/12 03:47, Jan Nielsen wrote:
> In this test, the local mount's buffered reads perform best around RA~10k @
> 150MB/sec then starts a steady decline. The SAN mount has a similar but
> more subtle decline with a maximum around RA~5k @ 80MB/sec but with much
> greater variance. I was surprised at the 80MB/sec for the SAN - I was
> expecting 150MB/sec - and I'm also surprised at the variance. I understand
> that there are many more elements involved for the SAN: more drives,
> network overhead&  latency, iscsi, etc. but I'm still surprised.
>
> Is this expected behavior for a SAN mount or is this a hint at some
> misconfiguration? Thoughts?
>
>
Is the SAN mount via iSCSI?  If so and also if the connection is a 
single 1Gbit interface then 80MB/s is reasonable. You might get closer 
to 100MB/s by tweaking things like MTU for the interface concerned, but 
to get more performance either bonding several 1Gbit links or using 
10Gbit is required.
Regards
Mark
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Rajesh Kumar. Mallah | 2012-05-24 05:26:47 | Re: High load average in 64-core server , no I/O wait and CPU is idle | 
| Previous Message | Claudio Freire | 2012-05-24 03:53:43 | Re: High load average in 64-core server , no I/O wait and CPU is idle |