xfs
[Top] [All Lists]

Re: Performance Characteristics of All Linux RAIDs (mdadm/bonnie++)

To: Kasper Sandberg <lkml@xxxxxxxxxxx>
Subject: Re: Performance Characteristics of All Linux RAIDs (mdadm/bonnie++)
From: Justin Piszcz <jpiszcz@xxxxxxxxxxxxxxx>
Date: Thu, 29 May 2008 17:08:59 -0400 (EDT)
Cc: Chris Snook <csnook@xxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx, linux-raid@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx
In-reply-to: <1212055050.25169.33.camel@localhost>
References: <alpine.DEB.1.10.0805280442330.4527@p34.internal.lan> <483D7CE8.4000600@redhat.com> <alpine.DEB.1.10.0805281329450.29755@p34.internal.lan> <483DB0EC.3090403@redhat.com> <alpine.DEB.1.10.0805281523560.29755@p34.internal.lan> <1212055050.25169.33.camel@localhost>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Alpine 1.10 (DEB 962 2008-03-14)


On Thu, 29 May 2008, Kasper Sandberg wrote:

On Wed, 2008-05-28 at 15:27 -0400, Justin Piszcz wrote:

On Wed, 28 May 2008, Chris Snook wrote:

Justin Piszcz wrote:


On Wed, 28 May 2008, Chris Snook wrote:

Justin Piszcz wrote:
Hardware:

Given that one of the greatest benefits of NCQ/TCQ is with parity RAID,
I'd be fascinated to see how enabling NCQ changes your results.  Of
course, you'd want to use a single SATA controller with a known good NCQ
implementation, and hard drives known to not do stupid things like disable
readahead when NCQ is enabled.
Only/usually on multi-threaded jobs/tasks, yes?

Generally, yes, but there's caching and readahead at various layers in software that can expose the benefit on certain single-threaded workloads as well.

Also, I turn off NCQ on all of my hosts that has it enabled by default
because
there are many bugs that occur when NCQ is on, they are working on it in
the
libata layer but IMO it is not safe at all for running SATA disks w/NCQ as
with it on I have seen drives drop out of the array (with it off, no
problems).


Are you using SATA drives with RAID-optimized firmware? Most SATA manufacturers have variants of their drives for a few dollars more that have firmware that provides bounded latency for error recovery operations, for precisely this reason.
I see--however, as I understood it there were bugs utilizing NCQ in libata?
You wouldnt happen to have some more information about this? i havent
personally had problems yet, but i havent used it for very long - but
since it comes activated by DEFAULT, i would assume it to be relatively
stable?
Not off-hand, check LKML and my email address from early this year or last year and/or the ide-list.

Justin.


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