> > hdparm -tT /dev/md0 /dev/sda7 /dev/sdb6 /dev/md0 /dev/sda7 /dev/sdb6
hdparm seems to support the bonnie result where block reads are faster,
albeit a lesser extent (dd == 85% vs 75% for bonnie).
[100MB dd write, read, delete on the raid array]
18.1MB/s writes, 10.7MB/s reads even though thi
| > is it correct to apply the
daemons/raid/alpha/raid0145-19990824-2.2.11.gz
| > patch to the (latest) 2.2.12 kernel?
|
| Yes, and just ignore errors (one fs.h.rej iirc)
I went risky and recompiled and repatched and rebooted remotely, and it
came
back up. So my locking up system is now at
[ Wednesday, September 15, 1999 ] Lawrence Dickson wrote:
>raidhotremove seems to THINK it can work without unmounting
> the raid array fs... same with the echo to /proc/scsi/scsi ...
> it's really all just syncing code, isn't it, guys?
I've been curious what raidsetfaulty would do (if anythi
[ Wednesday, September 15, 1999 ] Jon Pike wrote:
> is it correct to apply the daemons/raid/alpha/raid0145-19990824-2.2.11.gz
> patch to the (latest) 2.2.12 kernel?
Yes, and just ignore errors (one fs.h.rej iirc)
> should we be waiting for a raid0145-19990824-2.2.12.gz patch instead?
nope
I'll
[ Wednesday, September 15, 1999 ] CJones wrote:
> In a single user sequential read, you will get no better performance
> that a normal disk, and I would suspect, that with overheads and such
> for the raid device, you will have some degredation. 25% seems like
> more than some though.
Not sure i
[ Wednesday, September 15, 1999 ] [EMAIL PROTECTED] wrote:
> > Also read the /usr/doc info on calculating stride.
>
> The version I have doesn't mention anything useful in connection with
> RAID-1, only RAID-4/5, so I left it alone. I'd be glad to change this
> to any reasonable number, though.
In a thoughtful message, Clay Jones <[EMAIL PROTECTED]> writes:
> I have not fully read your explanations, but you staed that the
> theoretical performance of raid 1 was 200% of a normal disk. That
> is true in a "Multi User" environment, where 2 users are reading
> simultaneously, and adding bo
All,
I appreciate the amount of play my "newbie" question has
had, and have the feeling we are teetering an inch from an
answer. I've got to leap that inch - the infuriating
alternative is that our whole Linux-RAID development gets
tossed and replaced with antediluvian hardware RAID at
trem
I have not fully read your explanations, but you staed that the
theoretical performance of raid 1 was 200% of a normal disk. That is
true in a "Multi User" environment, where 2 users are reading
simultaneously, and adding both of their read numbers together.
In a single user sequential read, you
On Tue, 14 Sep 1999, Lawrence Dickson wrote:
So I take it the 18 disk RAID has to be unmounted before I
can do this. That's a killer.
eek, i was tired.. i didn't mean to say raidstop - sorry. The array
doesn't need to be stopped if it's a fault tolerant array. So should
be:
The *disk to
kiko wrote:
>
> On Wed, 15 Sep 1999, Stephen Waters wrote:
>
> > Tom Livingston wrote:
> > >
> > > Jason A Diegmueller wrote:
> > > > NOTE: I can't go newer then 2.2.11 at this time due to the fact
> > > >the latest released raid0145 patch is for 2.2.11. RAID
> > > >people, I haven't
On Wed, 15 Sep 1999, Stephen Waters wrote:
> Tom Livingston wrote:
> >
> > Jason A Diegmueller wrote:
> > > NOTE: I can't go newer then 2.2.11 at this time due to the fact
> > >the latest released raid0145 patch is for 2.2.11. RAID
> > >people, I haven't tried it yet: Will it patch 2
Tim Moore <[EMAIL PROTECTED]> writes with a number of great questions:
> > The trouble I'm having is that my RAID-1 read performance appears
> > substantially worse than just using the same disk partitions directly.
>
> How did you measure bonnie performance on the raw partitions?
Sorry, the w
hi everyone!
this seems to be implied in everything that's been said so far, but i don't
think anyone has explicitly told us:
is it correct to apply the
ftp://ftp.fi.kernel.org/pub/linux/daemons/raid/alpha/raid0145-19990824-2.2.1
1.gz patch to the (latest) 2.2.12 kernel? should we be waiting f
> From: Chris Garrigues <[EMAIL PROTECTED]>
> Date: Wed, 15 Sep 1999 16:00:39 -0500
>
> --==_Exmh_1625741955P
> Content-Type: text/plain; charset=us-ascii
>
> > From: "Theron J. Lewis" <[EMAIL PROTECTED]>
> > Date: Wed, 15 Sep 1999 13:37:13 -0700 (PDT)
> >
> > If I'm not mistaken, the 2.2.5-2
On Wed, 15 Sep 1999, Jason A. Diegmueller wrote:
> NOTE: I can't go newer then 2.2.11 at this time due to the fact
>the latest released raid0145 patch is for 2.2.11. RAID
>people, I haven't tried it yet: Will it patch 2.2.12 without
>too much hassle?
Yes; the only changes made i
Tom Livingston wrote:
>
> Jason A Diegmueller wrote:
> > NOTE: I can't go newer then 2.2.11 at this time due to the fact
> >the latest released raid0145 patch is for 2.2.11. RAID
> >people, I haven't tried it yet: Will it patch 2.2.12 without
> >too much hassle?
>
> Yep, the 2.2.
A couple people have already send me helpful suggestions, asking for
information that I really should have included in my first post.
First off, m. allan noah <[EMAIL PROTECTED]> writes:
> a 192 meg bonnie test is useless when you have 128 megs of ram. try a
> bonnie test of 1 gig and that will
> The trouble I'm having is that my RAID-1 read performance appears
> substantially worse than just using the same disk partitions directly.
How did you measure bonnie performance on the raw partitions?
---Sequential Output ---Sequential Input--
--Random--
-Pe
> From: "Theron J. Lewis" <[EMAIL PROTECTED]>
> Date: Wed, 15 Sep 1999 13:37:13 -0700 (PDT)
>
> If I'm not mistaken, the 2.2.5-22 and 2.2.5smp-22 kernels from redhat
> (which are definitely RPM'd) have the patches for hardware and software
> raid already rolled together, and there is a raidtools
I've been using the 428 on a Dell 4200. 2x300MHz PII, stock RH
2.2.5-15smp, driver from megatrends site, 2xACEnic GbE, no frills NFS
server configuration, 5x9MB RAID 5, board in a primary PCI slot with no
shared interrupts.
~18 MB/s on larger multi-stream, sequential i/o tests (dd & bonnie
cockt
If I'm not mistaken, the 2.2.5-22 and 2.2.5smp-22 kernels from redhat
(which are definitely RPM'd) have the patches for hardware and software
raid already rolled together, and there is a raidtools that matches it
that you can install.
The 2.2.5 kernel release 22 is part of the redhat updates.
I
[ Wednesday, September 15, 1999 ] [EMAIL PROTECTED] wrote:
> cat /tmp/bonnie-md0
> ---Sequential Output ---Sequential Input-- --Random--
> -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
> Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU
Jason A Diegmueller wrote:
> NOTE: I can't go newer then 2.2.11 at this time due to the fact
>the latest released raid0145 patch is for 2.2.11. RAID
>people, I haven't tried it yet: Will it patch 2.2.12 without
>too much hassle?
Yep, the 2.2.11 raid patches work fine for 2.2.12.
Howdy! I am installing the Linux software RAID for the first time, and
I'm having a puzzling performance problem. Any help would be appreciated.
My thanks to the authors of the software and the raidtools docs; this
all rocks! I'm very impressed with it.
Although I sent in my subscription request
I don't know if this is related or not, but I was having trouble with a
similar( I assume) box. 2 cpus, intel card, adaptec 2940, but without RAID.
You don't have an AGP video card in there, do you. I can't explain it, nor
did I ever investigate it. But, when I switched out the AGP card for a P
> From [EMAIL PROTECTED] Wed Sep 15 13:50:22 1999
>
> Good morning to everyone.
>
> > correct me if I'm wrong, but I think the current recipe is patching 2.2.12
> > with the latest raid alpha patch (for 2.2.11) and when patch complains
> > about fs.h, tell it to completely skip fs.h since change
In response to the HP Netserver LXe Pro lockup issue I had before,
and with the responses I've gotten so far, here is my current
plan of attack. Any further input or suggestions are as always
welcome:
1. I'm compiling without SMP support as we speak. The most this
thing has made it is 3 ful
On Sep 14, 4:57pm, David Holl wrote:
} Subject: Re: Newbie: What to do when a disk fails?
Good morning to everyone.
> correct me if I'm wrong, but I think the current recipe is patching 2.2.12
> with the latest raid alpha patch (for 2.2.11) and when patch complains
> about fs.h, tell it to comp
Hmm... My Dual Celeron box works fine with the MegaRAID 428. I'm using
2.2.13pre6 at the moment. I did update to the UF80 firmware but I was
using the original firmware before without any real problem. My problem
is it won't swallow my narrow devices.
Might you have bad memory on the card?
Brian
Jason,
I had problems where a mismatched system running 2 PPro 200 would spew
kernel panics and/or lockup. The problem was that the stepping number
of each processor was different. The SMP kernel would notify at boot
that they were incompatible, but would go ahead and try to use them
an
you mentioned kernel 2.2.11? there is a nasty memory leak in the tcp
code... while we were on it, the machine would lock up about once every
36-40 hours. 2.2.12 cleared it up.
On Wed, 15 Sep 1999, Jason A. Diegmueller wrote:
-I must say I've never seen this in my entire life, so
-I wanted to
I had similar problems with a newly acquired system, and managed to
isolate the onboard Intel EtherExpress Pro as being the culprit in my
case. Using a different NIC worked much, much better. My system also had
an Adpatec 78XX adpater (not onboard). I tried both 3Com 3C905 and
Asante PCI 10/100 NI
Hi, I'm new to linux-raid and haven't seen a pointer to a FAQ yet, so bear
with me. This question isn't in the HOWTO.
Has anybody RPM'd the raid kernel and the raid tools?
I use RPM to aid in autoconfiguration of a number of systems, so if nobody
else has RPM'd this software, I'll do it, but
I must say I've never seen this in my entire life, so
I wanted to get some input. This is sent to both the
linux-admin and linux-raid lists.
I have a customer/friend (yes, the two-in-one combo that
is often noted for being dangerous =) who recently upgraded
an old SCO setup they had to SCO Opens
On Tue, 14 Sep 1999, Chad Schmutzer wrote:
> The system in question is a Dell PowerEdge 6300 with 4 processors.
> I have the Dell OEM AMI MegaRAID 428 controller configured for RAID 5.
>
> When I boot with any 2.2.x SMP kernel and run a command which utilizes
> the disk (such as untarring a larg
36 matches
Mail list logo