On Sun, 11 Oct 1998, Andy Poling wrote:
> For RAID levels 0, 4 and 5 (the various "striping" RAID levels, it depends
> upon your goal.
>
> If you want to get maximum throughput for a single process by using all your
> spindles in parallel for each read or write operation, then you want a small
On Mon, 12 Oct 1998, tommiy wrote:
> Thanks for the reply but I am still at a loss as to what is
> going wrong here at this end. [...]
does your array start up if RAID is compiled into the kernel instead of
modules? Note that you cannot autostart an array with modules, use
raidstart if yo
On Mon, 12 Oct 1998, Benjamin de los Angeles Jr. wrote:
> Basing from the short documentation included in raidtools -- is the chunk
> size used in writing AND reading data from a RAID device? If it is,
> then in a RAID0 setup, it would be better if I have smaller chunks i.e.
> 8k, that is if I ha
Correct me if I'm mistaken.
Basing from the short documentation included in raidtools -- is the chunk
size used in writing AND reading data from a RAID device? If it is,
then in a RAID0 setup, it would be better if I have smaller chunks i.e.
8k, that is if I have smaller sizes of data, ideally
MOLNAR Ingo wrote:
>
> On Sat, 10 Oct 1998, tommiy wrote:
>
> > I've been attempt to get the patches to work and it appears that maybe
> > there is a problem with raid 5 and the alpha 0.90 patches. mkraid
> > --updates updates my old array but i can never start it. [...]
>
> could you send me m
On Sat, 10 Oct 1998, MOLNAR Ingo wrote:
> On Fri, 9 Oct 1998, Dan Hollis wrote:
> > On Sat, 10 Oct 1998, MOLNAR Ingo wrote:
> > > in case you are talking about Linux's RAID5, there is a guaranteed speed
> > > of reconstruction:
> > > #define SPEED_LIMIT 100
> > Shouldnt this be a kernel boot optio
>From the linux-scsi list... I though ti might be of interest to those here.
-Andy
Global Auctions
http://www.globalauctions.com
-- Forwarded message --
Date: Fri, 9 Oct 1998 00:32:44 -0500
From: Charles Kerns <[EMAIL PROTECTED]>
To: [EMAIL PROTECTED]
Subject: Infortrend RAID
I had success with the patch by placing it in /usr/src and then creating
the dir /usr/src/linux/include/linux/raid then using patch on it.
Everything works fine then after completing that but before
compiling add to md.c this line
MD_EXPORT_SYMBOL(md_interrupt_thread);
else not
Recently <[EMAIL PROTECTED]> wrote:
> Yes. I agree with your work. It appears that the 0.90 drivers are
> majorly broken and do not function at all.
Not MAJORLY, I think. Ingo just made the classical mistake of
which I have made several times too -- he changed something in
Hi everone (Ingo ? :-)
I experience severe problems with the above raid patches and putting swap on a raid1
array (Pentium 233 MMX, 64 MB RAM, 2940UW, 2 UW IBM DDRS 4 GB scsi disks). The system
crashes consistently under heavy load (bonnie, exorcist etc.) while running fine for 3
days under (a
On Sat, 10 Oct 1998, MOLNAR Ingo wrote:
> if you have lots of data on your RAID0 array and cannot do a backup, then
> this is how it goes. But if you can recreate the RAID0 array after backing
> up all data in it, you can put this into your raidtab:
>
> persistent-superblock 1
>
> and t
What I mean is, the patch-2.0.35.gz that can be downloaded from kernel
distribution sites, which aside from RAID, includes other latest bug fixes
and features as well. So if I just patch the original 2.0.35 with
raid0145-19981005-C-2.0.35.gz, then I'm just adding the latest RAID patch
BUT NOT th
12 matches
Mail list logo
