Hi,
Can you send us glusterfs log files?
regards,
On Mon, Nov 24, 2008 at 7:32 PM, Enrico Valsecchi [EMAIL PROTECTED] wrote:
Dear All,
I have installed Gluster FS v. 1.3.12 on 2 server with Debian 4.05,
in AFR with client side replication, explained in this page:
Hi devels!
We consider GlusterFS as parallel file server (8 server nodes) for our
parallel Opteron cluster (88 nodes, ~500 cores), as well as for a
unified nufa /scratch distributed over all nodes. We use the cluster
within a scientific environment (theoretical physics) and use
Fred,
Can you also provide us server logs?
--
gowda
On Tue, Nov 25, 2008 at 4:57 PM, Fred Hucht [EMAIL PROTECTED] wrote:
Hi devels!
We consider GlusterFS as parallel file server (8 server nodes) for our
parallel Opteron cluster (88 nodes, ~500 cores), as well as for a unified
nufa
Hi!
The glusterfsd.log on all nodes are virtually empty, the only entry on
2008-11-25 reads
2008-11-25 03:13:48 E [io-threads.c:273:iot_flush] sc1-ioth: fd
context is NULL, returning EBADFD
on all nodes. I don't think that this is related to our problems.
Regards,
Fred
On
Fred Hucht wrote:
Hi!
The glusterfsd.log on all nodes are virtually empty, the only entry on
2008-11-25 reads
2008-11-25 03:13:48 E [io-threads.c:273:iot_flush] sc1-ioth: fd context
is NULL, returning EBADFD
on all nodes. I don't think that this is related to our problems.
Regards,
Hello Harald!
I didn't test Infiniband transport until now, as I don't want to
interfere with the parallel applications which are running over
Infiniband. Gigabit Ethernet throughput would be sufficient for us at
the moment.
Today only three nodes were affected, yesterday it were nine
Hi,
crawling through all /var/log/messages, I found on one of the failing
nodes (node68)
Nov 25 04:04:12 node68 kernel: INFO: task pw.x:20052 blocked for more
than 120 seconds.
Nov 25 04:04:12 node68 kernel: echo 0 /proc/sys/kernel/
hung_task_timeout_secs disables this message.
Nov 25
Hi,
I forgot to say: A
# umount -f /scratch; umount /scratch; mount /scratch
resolves the problems. No need to reload fuse.
Fred
On 25.11.2008, at 13:42, Joe Landman wrote:
Fred Hucht wrote:
Hi!
The glusterfsd.log on all nodes are virtually empty, the only entry
on 2008-11-25 reads
Hello!
2008/11/25 Fred Hucht [EMAIL PROTECTED]:
Hello Harald!
I didn't test Infiniband transport until now, as I don't want to interfere
with the parallel applications which are running over Infiniband. Gigabit
Ethernet throughput would be sufficient for us at the moment.
Today only three
Fred Hucht wrote:
Hi,
crawling through all /var/log/messages, I found on one of the failing
nodes (node68)
Does your setup use local disk? Is it possible that the backing store
is failing?
If you run
mcelog /tmp/mce.log 21
on the failing node, do you get any output in
Hey yall,
I had a bunch of problems here that delayed my tests. Hardware problems,
other systems and so. Yesterday I started the tests and what I'm learning is
really making it worth. I will send all the results latter but for now the
biggest find is that the XFS filesystem of *the* best for
Hi,
I installed and ran mcelog and only found DIMM problems on one node
which is not related to our problems.
I don't think that the problems are related to only a few nodes. The
problems occur on the nodes where the test job runs, and the queue
scheduler always selects different nodes.
Hello,
I'm sorry for the noise. The problem seems to be completely unrelated to
GlusterFS. An upgrade of lib pyxattr 0.2 to 0.4 fixed everything. So the
problem was between rdiff-backup 1.2.2 and pyxattr 0.2.
I'm sorry for blaming GlusterFS without proper debugging.
Hannes Dorbath wrote:
Hi Daniel,
2008/11/25 Daniel van Ham Colchete [EMAIL PROTECTED]
Yesterday I started the tests and what I'm learning is really making it
worth. I will send all the results latter but for now the biggest find is
that the XFS filesystem of *the* best for maildir storage in comprassion
from
14 matches
Mail list logo