gluster-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Gluster-devel] Hello... stripping and fault tolerant systems...


From: Krishna Srinivas
Subject: Re: [Gluster-devel] Hello... stripping and fault tolerant systems...
Date: Fri, 30 May 2008 12:01:25 +0530

On Fri, May 30, 2008 at 10:06 AM, Anand Avati <address@hidden> wrote:
>
>>
>> Yes, You can use stripe and afr, preferably stripe over a bunch of AFRs.
>
> I would suggest the other way round if you have a read-heavy work load.
>
> AFR ( STRIPE (server1, server2), server3)
>
> Let afr serve over the stripe for high performance by default, and server3
> be a backup. This works well for read-heavy workloads.

How will afr over stripe help for read-heavy work loads?

I suggested stripe over afrs keeping in mind AFR's currently bad selfheal logic
for big files. Selfheal will be very optimal in stripe over afrs.

Krishna

>
> avati
>




reply via email to

[Prev in Thread] Current Thread [Next in Thread]