I said:
> It is VERY, VERY hard to place 12
> drives (I have two 4 gigs for raid boot/root) inside a case and stay under
> the 18" ide cable restriction!! Many, many cables are sold that
> are longer than this maximum 18" cable, but these cables can and
> will cause errors under udma under linux
Hi all,
I'm running Red Hat 6.0 + updates and "2.3.3ac3+efs1.0b" = 2.3.3 with
Alan Cox's patch #3, and efs 1.0b (so I can read SGI CDs in my CD
drive). I was having problems that mkraid from the Red Hat 6.0
raidtools-0.90-3.i386.rpm that even with the right force arg, mkraid
still aborted.
Afte
Hi folks,
I was just searching through the archives for help on a RAID problem and
the posts were helpful, so I decided to "give something back" to the
group.
Chris R. Brown ([EMAIL PROTECTED]) wrote:
> I've just come back to my RAID project and have run into some
> more problems. I was w
On Wed, 30 Jun 1999, Michael Tibor wrote:
> On Wed, 30 Jun 1999, Stanley, Jeremy wrote:
>
> > I believe it is 66MBps per channel, but keep in mind that Ultra2 SCSI
> > runs 80MBps per device and has been around for a couple of years.
> > Ultra3 is supposed to run around 160MBps. My U2/5-drive R
On Wed, 30 Jun 1999, Stanley, Jeremy wrote:
> I believe it is 66MBps per channel, but keep in mind that Ultra2 SCSI
> runs 80MBps per device and has been around for a couple of years.
> Ultra3 is supposed to run around 160MBps. My U2/5-drive RAID0 has a
> "theoretical" bandwidth of 400MBps
Actu
On Wed, 30 Jun 1999, D. Lance Robinson wrote:
> Try bumping your chunk-size up. I usually use 64. When this number is low,
> you cause more scsi requests to be performed than needed. If really big (
> >=256 ) RAID 0 won't help much.
Richard said in his original message that he's running IDE disk
Any news on when a patch (with the fixes for the stuff that 2.2.8 broke)
might be available for 2.2.10?
I'm looking to deploy a couple of new servers and would like to try and
deploy them with as current a build as possible.
-- Nathan
---
Chris R. Brown wrote:
> I've just come back to my RAID project and have run into some
> more problems. I was wondering if anyone on the list has kludged
> three promise ultra 33 cards and one onboard IDE controller together
> in one box. I'm still trying to get a big (128 gig) array going, b
D. Lance Robinson wrote:
>
> Try bumping your chunk-size up. I usually use 64. When this number is low,
> you cause more scsi requests to be performed than needed. If really big (
> >=256 ) RAID 0 won't help much.
>
What if the chunk size matches ext2fs's group size (i.e. 8M)? This would
give ve
there is an article at wickedpc
(http://www.wickedpc.com/faqs/harddrivetweaking/B) that talks about
the new IBM 22GB Drive ATA-66. Basically ATA-66 doesn't add that much in
speed (like 8%), but it reduces CPU overhead alot. So you shoudl be
rocking with 3 or 4 of those 22GB beasts in a RAID5.
I believe it is 66MBps per channel, but keep in mind that Ultra2 SCSI
runs 80MBps per device and has been around for a couple of years.
Ultra3 is supposed to run around 160MBps. My U2/5-drive RAID0 has a
"theoretical" bandwidth of 400MBps compared with a 2-drive (one on each
IDE channel) UDMA RAI
Hello all,
I've just come back to my RAID project and have run into some
more problems. I was wondering if anyone on the list has kludged
three promise ultra 33 cards and one onboard IDE controller together
in one box. I'm still trying to get a big (128 gig) array going, but
it isn't wor
Hey Guys,
I am building a server that I want to use Linux RAID on. I've heard that
the new IDE spec "U-DMA-66" is supposed to be an extremely fast technology.
(is that 66 MHz, or 66MB/s?) Anyway, I was wondering if anyone here has had
any experience with this (in RAID formation, or not). Has S
Try bumping your chunk-size up. I usually use 64. When this number is low,
you cause more scsi requests to be performed than needed. If really big (
>=256 ) RAID 0 won't help much.
<>< Lance.
Richard Schroeder wrote:
> Help,
> I have set up RAID-0 on my Linux Redhat 6.0. I am using RAID-0
> (s
The RAID takes a lot of CPU overhead that normal disk access doesn't.
You failed to mention what CPU speed you were running. Also, if you are
running sufficient RAM. I typically don't run on less than a K6-200 with
64MB of RAM. Most of my servers have at least 96MB RAM, my latest server
is running
15 matches
Mail list logo
