[lustre-discuss] varying sequential read performance.

Scott Denham sdenham at cray.com
Thu Apr 5 12:41:57 PDT 2018


>From: John Bent <johnbent at gmail.com>
>To: John Bauer <bauerj at iodoctors.com>
>Subject: Re: [lustre-discuss] varying sequential read performance.

> "I suspect that this OSC is using an OSS that is under heavier load."

> If you want to confirm this, it seems like you could create files with
> striping parameters such that you have a single file on each OSS.  Well, I
>  know you can make stripe=1 so it's only on one OSS but can you
> control/query on *which* OSS is the stripe?  Assuming you can, then you
> just benchmark performance for each file (i.e. OSS) and you can discover
> more explicitly whether you have a slow OSS.

We have used Lustre pools in the past for this. They can overlap, so it is 
Possible to create N pools with each pool containing only one OSS. 

Scott Denham
Staff Engineer - Presales at Cray, Inc



More information about the lustre-discuss mailing list