Re: Has anybody looked at RAID-5 vinum performance on the "whole system"?

[ Available lists | Index of freebsd-hackers | Month of Jun 2000 | Week of 13 Jun 2000 | Raw email | View thread | Wrap long lines | Reply | Tag ]
From
Wes Peters <wes@softweyr.com>
Date
13 Jun 2000 21:44:13
Subject
Re: Has anybody looked at RAID-5 vinum performance on the "whole system"?
Message-ID
39470DBA.D8045A1A@softweyr.com

References to
Replies

[ Hide this part ]
Jaye Mathisen wrote:
>
> I was just curious what people's thoughts were on the potential "total
> system throughput" (whatever you choose it to be), wrt using software
> RAID.
>
> It would seem that software RAID would just kill big chunks of cache,
> especially CPU cache, moving lots of data throught it to calcuate CRC's.
>
> perhaps the raid 1/0's would be fine, since the calcuation could be
> ignored.

Greg can probably give a better answer than I can, but one thing to be
aware of is that host-based RAID, like Vinum, usually has access to a
lot more processor and memory resources than hardware RAID controllers.

My experience is limited to running an I/O bound, not compute-bound,
server using both Vinum and a Mylex DAC1100 with 64MB RAM, using RAID-1.
The system was a DELL 2400 with 2x 600 Mhz Pentium III. The application
was a non-interactive web filter running over millions of web pages
grabbed by a spider. The total throughput was significantly higher on
the software RAID system. The application inherently sloshes through
the caches anyhow, so little cache affect is achieved.

--
"Where am I, and what am I doing in this handbasket?"

Wes Peters Softweyr LLC
wes@softweyr.com http://softweyr.com/


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message



Elapsed time: 0.556 seconds