similar to: OCFS2 performance - disk random access time problem

Hello. What we have: 2x Debian 5.0 x64 - 2.6.32-20~bpo50+1 from backports DRBD + OCFS2 1.4.1-1 I have both node reboot every day on my tests. On heavy load it have to 1-3 hour to reboot, on idle about 20 hours. I not sure what it is a OCFS2 related but if I not mount OCFS2 partition - I don`t get this reboot. In attach screenshoot with system console on what error. Nothing special in logs.

One more follow on, The combination of kernel.panic=60 and kernel.printk=7 4 1 7 seems to have netted the culrptit: E01-netconsole.log:Jan 18 09:45:10 E01 (10,0):o2hb_write_timeout:137 ERROR: Heartbeat write timeout to device dm-12 after 60000 milliseconds E01-netconsole.log:Jan 18 09:45:10 E01 (10,0):o2hb_stop_all_regions:1517 ERROR: stopping heartbeat on all active regions.

In upstream ocfs2 code, /proc interface for mask log is updated into files under /sys/fs/o2cb/masklog, comments in fs/ocfs2/cluster/masklog.h are out of date. This patch modifies the commens in cluster/masklog.h, which also provides a bash script example on how to change the log mask bits. Signed-off-by: Coly Li <coly.li at suse.de> --- fs/ocfs2/cluster/masklog.h | 33

Currently f_fsid of struct kstatfs returned from ocfs2_statfs() is undefined (at least it should be filled with 0). Since in some conditions, f_fsid value might be used as (f_fsid, ino) pare to uniquely identify a file, ocfs2 should return a defined unique f_fsid value from ocfs2_statfs(). This patch uses uuid_hash as a unique ID to initiate f_fsid value, the 32bits width is enough for ocfs2

All, Please review the patches backported to 1.4 from mainline. Sunil

Hi there I recently installed an OCFS2 filesystem on our FC-SAN. Everything seemed to work fine and I could read & write the filesystem from both servers that are mounting it. After a while though, writes coming from one node do not appear on the other node and vice versa. I am not sure what's causing this, and not very experienced at debugging filesystems. If anybody has any

Currently f_fsid of struct kstatfs returned from ocfs2_statfs() is undefined (vfs layer fills 0 as default). Since in some conditions, f_fsid value might be used as (f_fsid, ino) pair to uniquely identify a file, ocfs2 should return a unique defined f_fsid value from ocfs2_statfs(). Because uuid_str is identified no mater on big or litlle endian machine, it's also endian consistent to use

Now the discussion moves to kernel space, I move the email from ocfs2-tools-devel to ocfs2-devel. The original discussion can be found from http://oss.oracle.com/pipermail/ocfs2-tools-devel/2009-June/001891.html Joel Becker Wrote: > On Sat, Jun 27, 2009 at 03:46:04AM +0800, Coly Li wrote: >> Joel Becker Wrote: >>> On Sat, Jun 27, 2009 at 03:00:05AM +0800, Coly Li wrote: >>

In fs/ocfs2/dlmglue.c:ocfs2_cluster_lock(), after label 'out:' the code is: 1373 if (wait && arg_flags & OCFS2_LOCK_NONBLOCK && 1374 mw.mw_mask & (OCFS2_LOCK_BUSY|OCFS2_LOCK_BLOCKED)) { 1375 wait = 0; 1376 if (lockres_remove_mask_waiter(lockres, &mw)) 1377 ret = -EAGAIN; 1378

This email is also sent to cluster-devel at redhat.com. Since this issue is about both dlm and ocfs2, I send the email here to look for help from upstream. This is an already known issue. on ocfs2 with user space cluster stack, run the test script from http://people.redhat.com/~teigland/make_panic on the mounted ocfs2 volume from 2 nodes simultaneously, the access to ocfs2 volume on both nodes

It is obsoleted since Dec 2005. Signed-off-by: WANG Cong <amwang at redhat.com> --- Documentation/ABI/obsolete/o2cb | 11 ----------- Documentation/ABI/removed/o2cb | 10 ++++++++++ Documentation/feature-removal-schedule.txt | 10 ---------- fs/ocfs2/cluster/sys.c | 9 --------- 4 files changed, 10 insertions(+), 30 deletions(-) --- diff

Seems RPM compatibility issue with OS Kernel. Check OS Kernel and download RPM (4 Nos) for same kernel. Regards, Yuvrajsinh Chauhan || Sr. DBA || CRESTEL-PSG Elitecore Technologies Pvt. Ltd. 904, Silicon Tower || Off C.G.Road Behind Pariseema Building || Ahmedabad || INDIA [GSM]: +91 9727746022 -----Original Message----- From: ocfs2-users-bounces at oss.oracle.com [mailto:ocfs2-users-bounces

Hi, I might be overlooking the obvious, but I have yet to find "/etc/init.d/o2cb" however, I read that configuration uses this init script. Where is it? From: ocfs2-tools-1.2.4/README.O2CB [Starting the OCFS2 Clustering Services] O2CB is comprised of a simple node manager, heartbeat, TCP protocol, and DLM. The basic steps in startup are as follows: 1) Load the nodemanager,

Hi Yuvrajsinh, thank you for the reply, yes it was a kernel issue and we have done an upgrade to 2.6.18.308 and used the packges that match the version number, and I have done a update post this evening as below Hi All, since the post I have made some kind of a progress 1. I upgraded the kernel to 2.6.18-308.1.1.el5 same I was able to download the ocfs2 module is

Hi I have: SLES 10 SP2 (2.6.16.60-0.21-smp) ocfs2-tools-1.4.0-0.3 ocfs2console-1.4.0-0.3 and I can't change "heartbeat dead threshold" value. Content of /etc/sysconfig/o2cb: # O2CB_ENABLED: 'true' means to load the driver on boot. O2CB_ENABLED=true # O2CB_BOOTCLUSTER: If not empty, the name of a cluster to start. O2CB_BOOTCLUSTER=ocfs2 # O2CB_HEARTBEAT_THRESHOLD:

I observer interesting dentry number during the dlm stress testing. The ocfs2 cluster stack is user space "pcmk". creating a empty directory, ls -al: total 8 drwxr-xr-x 2 root root 4096 2009-05-08 15:29 . drwxr-xr-x 4 root root 4096 2009-05-08 15:29 .. run script make_panic on single node, for 10 seconds, ls -al: total 12 drwxr-xr-x 2 root root 4096 2009-05-08 15:33 . drwxr-xr-x

Hi list, Here is a bug report on novell bugzilla (https://bugzilla.novell.com/show_bug.cgi?id=456280) that mount point inside node A can be removed from node B. The problem is, node B does not know an empty dir is be using as mount point on another node. Is there any solution to return -EBUSY when a dir is be using as mount point on another node ? Thanks in advance. -- Coly Li SuSE Labs

Hi Greg, The following two patches move /sys/o2cb into /sys/fs/o2cb as we previously discussed. A symlink is created to maintain compatibility with existing versions of ocfs2-tools. A patch to automatically search /sys/fs/o2cb has been committed to the ocfs2-tools repo and a release with that code shouldn't be too far out. Old versions of ocfs2-tools have been tested and work fine with the

Hi, I have installed and configured ocfs2 as per the given guidelines on two nodes. The output of the service status of o2cb and ocfs2 is as under: Node: rashida1 -------------------------------------------------- [root at rashida1 ~]# service o2cb status Driver for "configfs": Loaded Filesystem "configfs": Mounted Driver for "ocfs2_dlmfs": Loaded Filesystem

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hi everyone, another problem I did not find a solution for... I ran "o2cb configure" and configured a cluster named "ocfs2". Lazy me, I did not invent a new name. Now this cluster must be renamed to avoid confusion, the name has to change to "sapcluster". I changed /etc/ocfs2/cluster.conf to the new name and ran