atom feed18 messages in org.freebsd.freebsd-fsRAID-3 and RAID-4 (was: RAID1 Softwar...
FromSent OnAttachments
Bagnara StefanoNov 6, 1998 8:35 am 
Christopher NielsenNov 6, 1998 1:35 pm 
Greg LeheyNov 6, 1998 3:49 pm 
Greg LeheyNov 6, 1998 3:51 pm 
Christopher NielsenNov 6, 1998 4:41 pm 
Bill VermillionNov 6, 1998 4:41 pm 
Greg LeheyNov 7, 1998 1:35 am 
Bill VermillionNov 7, 1998 5:31 am 
Greg LeheyNov 7, 1998 3:18 pm 
Kenneth D. MerryNov 7, 1998 10:08 pm 
Greg LeheyNov 7, 1998 11:08 pm 
Justin T. GibbsNov 7, 1998 11:17 pm 
Bill VermillionNov 8, 1998 3:29 am 
Eivind EklundNov 8, 1998 4:59 am 
Greg LeheyNov 8, 1998 7:55 pm 
Greg LeheyNov 8, 1998 7:58 pm 
Justin T. GibbsNov 8, 1998 10:17 pm 
Greg LeheyNov 8, 1998 10:25 pm 
Subject:RAID-3 and RAID-4 (was: RAID1 Software vs Hardware)
From:Greg Lehey (gr@lemis.com)
Date:Nov 8, 1998 10:25:51 pm
List:org.freebsd.freebsd-fs

On Sunday, 8 November 1998 at 23:17:36 -0700, Justin T. Gibbs wrote:

On Sunday, 8 November 1998 at 0:17:36 -0700, Justin T. Gibbs wrote:

RAID 3 is still used, and is still useful. All of Pluto's products (see http://www.plutotech.com) use RAID 3. It works quite well for video data.

I suppose it gives you good throughput. But how do you handle the I/O load? Are you effectively delivering a single video stream?

RAID 3 is ideal when your data requests are always a multiple of the strip size.

I'm not sure we're talking about the same thing. In my book, RAID-3 is a RAID-4 with a stripe size of 1 byte. How do you define it?

RAID-3 confines parity to 1 member of the array. The size of the stripe is not a part of the specification. In the case of Pluto products, we usually use a stripe size of 1MB which implies a per-unit access of 1MB/N-1 (N being number of members in the RAID group).

This looks like RAID-4 to me. Where do you see the difference?

Greg

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