[Top] [All Lists]

Re: XFS Test Results Interpretation

To: xfs@xxxxxxxxxxx
Subject: Re: XFS Test Results Interpretation
From: Stan Hoeppner <stan@xxxxxxxxxxxxxxxxx>
Date: Sat, 23 Oct 2010 22:38:25 -0500
In-reply-to: <3C5E029826A0704DB5998577FCFF46F0095A278CBF@dagobah>
References: <3C5E029826A0704DB5998577FCFF46F0095A278CBF@dagobah>
User-agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv: Gecko/20101013 Thunderbird/3.1.5
Andrew Debenham put forth on 10/23/2010 9:59 PM:
> I am in the process of trying to determine the best parameters to use when 
> creating and mounting an XFS file system on some new hardware we are going to 
> be using.  My company has two separate applications that will be running on 
> the same hardware (but on separate systems).  One application is the 
> PostgreSQL database and the other is a custom application that does writes to 
> many (~1,000) relatively small (~672MB) files concurrently.

Post the detailed hardware specs (server, local RAID or SAN, number of
disks in stripe set, RAID level, etc), and if both applications are
running on the same physical machine or different machines.  Are both
apps writing to the same XFS filesystem or two different filesystems?
Your description of "what is where" was very confusing.

Oh, and Bonnie++ test results are usually useless, as well as IOZone,
etc.  Next time ask before taking the time to run benchmarks and jump
through hoops to get the data onto the list. :)


<Prev in Thread] Current Thread [Next in Thread>