Hello,
I've got a Lustre system where I'd like to improve single client write
performance, The Lustre manual reads "Lustre single client node throughput
has been measured at 2 GB/s (max)" (section 1.1.1 Lustre Key Features),
and the web site
http://docs.hp.com/en/SFSUGG3-D/apas02.html
On Thu, 2010-03-11 at 16:55 +0530, Vineet ghatge wrote:
> Can someone suggest why i encountered this? I have installed all
> packages in Red hat Linux 9.
May I suggest you update to distribution that is more recent? RHL 9 came
out in 2003 IIRC, and sported a nifty 2.4 vintage kernel. It is not
s
Thank you. Just signed up.
~Lawrence
Rosie Krupski wrote:
> Hi All, I think I accidentally hit the wrong button on this so I'm
> forwarding to the list.
>
> Lawrence, You may want to consider, if you haven't already, signing
> up for the list so that your emails are automatically approved.
>
On 2010-03-11, at 11:58, Lawrence Sorrillo wrote:
> Lustre 1.8.2 supports 2.6.18-164.11.1.el5 (EL5u4), however, we have
> 24GB
> on our machine so we use 2.6.18-164.11.1.el5PAE. This also seems to
> be a problem. I thought that since the 2.6.18-164 was supported
> getting lustre to
> accommod
Nicolas:
Lustre 1.8.2 supports 2.6.18-164.11.1.el5 (EL5u4), however, we have 24GB
on our machine so we use
2.6.18-164.11.1.el5PAE. This also seems to be a problem. I thought that
since the 2.6.18-164 was supported getting lustre to
accommodate the "PAE" would not be difficult, but I have failed
Hi All, I think I accidentally hit the wrong button on this so I'm
forwarding to the list.
Lawrence, You may want to consider, if you haven't already, signing up
for the list so that your emails are automatically approved.
http://lists.lustre.org/mailman/listinfo/lustre-discuss
To:
Nicola
On Thu, Mar 11, 2010 at 10:43:28AM -0600, Hendelman, Rob wrote:
> I'd like to make sure that I understand these 2 module options.
>
> >From googling a bit & searching bugzilla, here is my understanding:
>
> oss_num_threads = Maximum number of service threads across all ost's on a
> single OSS.
>
I'd like to make sure that I understand these 2 module options.
>From googling a bit & searching bugzilla, here is my understanding:
oss_num_threads = Maximum number of service threads across all ost's on a
single OSS.
oss_num_create_threads = minimum number of threads across all ost's on a sing
Does anyone monitor this list?
___
Lustre-discuss mailing list
Lustre-discuss@lists.lustre.org
http://lists.lustre.org/mailman/listinfo/lustre-discuss
Hello,
New(ish) to lustre, but have a quick question that I cannot seem to find
anything about.
In version 1.6, 'lfs df ' shows *all* mounted lustre filesystems.
On a box that I put the 1.8 client/modules, it only shows the last
filesystem mounted unless I specifically request it (eg: df /work).
On Thu, 2010-03-11 at 16:55 +0530, Vineet ghatge wrote:
> Hi all,
Hi,
> I tried running lustre on Red hat linux 9 i got a list of errors as
> shown below:-
What is Red Hat linux 9? Red Hat Enterprise Linux is only at "5"
currently with 6 coming shortly, AFAIU.
> [r...@localhost software]# rpm
Hi all,
I tried running lustre on Red hat linux 9 i got a list of errors as shown
below:-
[r...@localhost software]# rpm -ivh
kernel-2.6.18-164.11.1.el5_lustre.1.8.2.i686.rpm
error: Failed dependencies:
module-init-tools is needed by kernel-2.6.18-164.11.1.el5_lustre.1.8.2
initscripts >= 8.11.1-1
12 matches
Mail list logo