Re: Testing Sandforce SSD - Mailing list pgsql-performance

From Greg Smith
Subject Re: Testing Sandforce SSD
Date
Msg-id 4C58216B.7050401@2ndquadrant.com
Whole thread Raw
In response to Re: Testing Sandforce SSD  (Yeb Havinga <yebhavinga@gmail.com>)
List pgsql-performance
Yeb Havinga wrote:
> Small IO size: 4 KB
> Maximum Small IOPS=86883 @ Small=8 and Large=0
>
> Small IO size: 8 KB
> Maximum Small IOPS=48798 @ Small=11 and Large=0

Conclusion:  you can write 4KB blocks almost twice as fast as 8KB ones.
This is a useful observation about the effectiveness of the write cache
on the unit, but not really a surprise.  On ideal hardware performance
should double if you halve the write size.  I already wagered the
difference in pgbench results is caused by the same math.

--
Greg Smith  2ndQuadrant US  Baltimore, MD
PostgreSQL Training, Services and Support
greg@2ndQuadrant.com   www.2ndQuadrant.us


pgsql-performance by date:

Previous
From: Yeb Havinga
Date:
Subject: Re: Testing Sandforce SSD
Next
From: Yeb Havinga
Date:
Subject: Re: Testing Sandforce SSD