[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: Re: [Linux-cluster] GFS umount hang after heavy read/write from NFS client



>On Sun, Feb 27, 2005 at 10:54:01PM +0800, ?????? wrote:
>> Hello,all
>> 
>> I got messages as follows:
>> 	
>> GFS: fsid=MyTest:vgtest.2: Unmount seems to be stalled. Dumping lock state...
>
>> What's the meaning ? GFS lock out,or NFS lock out?
>
>GFS can't unlock those two locks for some reason; it's probably a dlm bug.
>We saw this in the past, but not recently.  Maybe we're not running enough
>GFS/NFS tests.
>
>https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=142993
>
>> And the "umount" process occupied 99.9% of CPU.
>> The status of the "umount" process was 
>> "29121 ?        R     74:08 umount /mnt/gfs/10".
>> 
>> I use the kernel 2.6.9.
>
>It would be helpful to know if you see this with the current code in cvs
>(which needs 2.6.10) and if it happens often.
I checked out the cluster's code on 2005-02-25 with tag RHEL4.
My program opened many files(such as 300) and readed/writed them concurrently,
Sometimes I got error messages as "Stale NFS file handle ".
to reproduce it, I just do:
	.mount GFS
	.start NFS service
	.mount NFS client
	.read from NFS
	.stop NFS service
	.umount GFS
	.mount the same GFS
	.start NFS service
	.read the same files from NFS
	.umount NFS
	.stop NFS service
	.umount GFS 
Then, after some minutes, I got things above.
The process status of "umount" is "R",particular as:
29053 ?        S<     0:00  \_ [lock_dlm1]
   11 ?        S<     0:00 [events/1]
 4051 ?        S<     0:00  \_ [cman_serviced]
29052 ?        S<     0:00  \_ [dlm_recoverd]
29054 ?        S<     0:00  \_ [lock_dlm2]
   12 ?        S<     0:00 [events/2]
 4066 ?        S<     0:01  \_ [dlm_astd]
 4068 ?        S<     0:00  \_ [dlm_sendd]
29543 ?        S<     0:00  \_ [dlm_recoverd]
29545 ?        S<     0:00  \_ [lock_dlm2]
   13 ?        S<     0:00 [events/3]
 4067 ?        S<     0:01  \_ [dlm_recvd]
 4069 ?        S<     0:00  \_ [dlm_recoverd]
29544 ?        S<     0:00  \_ [lock_dlm1]
29611 ?        R    1017:42 umount /mnt/gfs/11



[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]