On 15/03/12 19:51, Joshua Walgenbach wrote:
For my part, a Lustre client on Windows or OS X would be used mostly
for visualization of data, rather than being computed against so a
slower user space implementation would be more than sufficient.
There are a few applications that are using an SMB
Johann Lombardi wrote:
On Fri, Mar 11, 2011 at 04:52:21PM +, Gregory Matthews wrote:
That sounds to me like it is only hitting the MDT and not the OSTs.
No, it hits both. Fortunately, quotacheck is run in parallel on the
MDT and the OSTs, that's why it scales well.
ah ok. thanks
That sounds to me like it is only hitting the MDT and not the OSTs.
which would mean if you have a lustre system that has been upgraded from
an older version, most of the file sizes reported on the MDT will be
zero and this must affect the validity of the quotacheck...
GREG
Johann Lombardi
We've had problems with suse in the past. These were avoided by creating
/etc/rc.d/after.local containing:
modprobe lustre
mount -a
not pretty, but effective.
GREG
liang.whamcloud wrote:
Hi Prasad,
I'm not a SuSe user but I think it's because your system is trying to
load lustre modules
Article by Jeff Layton:
http://www.linux-mag.com/id/7839
anyone have views on whether this sort of caching would be useful for
the MDT? My feeling is that MDT reads are probably pretty random but
writes might benefit...?
GREG
--
Greg Matthews01235 778658
Senior Computer Systems
Does anyone recognise the following logs:
Jul 15 18:24:40 cs04r-sc-mds01-01 kernel: LustreError:
17241:0:(mds_open.c:1053:mds_open()) parent 121938276/854916762
lookup/take lock error -13
Jul 15 18:24:40 cs04r-sc-mds01-01 kernel: LustreError:
17241:0:(mds_open.c:1053:mds_open()) Skipped 5
Guy Coates wrote:
One thing to watch out for in your kernel configs is to make sure that:
CONFIG_SECURITY_FILE_CAPABILITIES=N
I hope this is not the case for the now obsolete:
CONFIG_EXT3_FS_SECURITY=y
which appears to be enabled by default on RHEL5.x
Its not entirely clear to me what this
Gary Brooks wrote:
Then, all of the sudden the MDS stops responding, ssh sessions die and
only hard restart helps. After the restart, /var/log/messages contains
normal information (some timeout chit-chat).
is your hardware using the bnx2 NIC driver? We've just been seeing very
similar
oops... this was meant for the list...
Original Message
Subject: Re: [Lustre-discuss] Problems with fstab entry on sles11
Date: Tue, 04 May 2010 08:42:37 +0100
From: Gregory Matthews greg.matth...@diamond.ac.uk
To: Brian J. Murrell brian.murr...@oracle.com
References
if it helps, I have longer stack traces...
Mar 21 05:31:42 dec055 kernel: BUG: scheduling while atomic:
cat/4439/0x0002
Mar 21 05:31:42 dec055 kernel: Modules linked in:3BUG: scheduling
while atomic: cat/4508/0x0002
Mar 21 05:31:42 dec055 kernel: mgc lustre lov mdc lquotaModules linked
Andreas...
Andreas Dilger wrote:
On 2010-03-17, at 02:59, Gregory Matthews wrote:
Gregory Matthews wrote:
BUG: using smp_processor_id() in preemptible [] code:
modprobe/6024
caller is set_ptldebug_header+0x41/0xa0 [libcfs]
Pid: 6024, comm: modprobe Not tainted 2.6.27.39-default #2
Well, I'm no expert at reading the the kernel bugzilla but...
Gregory Matthews wrote:
BUG: using smp_processor_id() in preemptible [] code: modprobe/6024
caller is set_ptldebug_header+0x41/0xa0 [libcfs]
Pid: 6024, comm: modprobe Not tainted 2.6.27.39-default #2
Call Trace
I get lots of these errors when using Lustre with a preempt kernel.
Earlier discussions on this list suggested that preempt should work even
tho it used to be blocked during the build process.
This is with freshly compiled 1.8.2 patchless clients, vanilla 2.6.27.39
kernel on OpenSuse 10.3. The
We had an LBUG on our MDS (on 15th Feb) and so attempted a failover to
the 2nd MGS/MDS server. This mounted the MGT fine but hung while
mounting the MDT (longer than 5 minutes).
To resolve the problem I unmounted the MGT and the MDT on a freshly
booted MDS/MGS and mounted the MDT as ldiskfs.
Adeyemi Adesanya wrote:
Does anyone know if Sun offer support agreements for Lustre? We would
consider paying for up-to-date RHEL5 patched kernel builds and RPMs.
I tried to get information on Lustre support from Sun and having rung
many different numbers and been passed between many
15 matches
Mail list logo