[Lustre-discuss] Enqueue wait from MDS log

[Andreas Dilger]

On 2010-01-06, at 03:49, Tung Dam wrote:
> The bad news is that i'm using lustre 1.8, do you have any idea ?  
> Could you tell me that how it could affect to our system or it's  
> just a harmless warning ?

It is just a harmless warning.  The message is gone in CVS, err Git,  
but I don't know when that was done, so it might not appear until 1.8.2.

> On Wed, Jan 6, 2010 at 5:22 PM, Andreas Dilger <adilger at sun.com>  
> wrote:
>> On 2010-01-06, at 01:42, Tung Dam wrote:
>> I have an issue with lustre log from our MDS, like this:
>>
>> Jan  6 14:00:49 MDS1 kernel: Lustre: 19141:0:(ldlm_lockd.c: 
>> 808:ldlm_server_completion_ast()) ### enqueue wait took 164s from  
>> 1262761084 ns: mds-lustre-MDT0000_UUID lock:  
>> ffff8101b6265a00/0x874ddc3670da987c lrc: 3/0,0 mode: PW/PW res:  
>> 28739811/1154690434 rrc: 3 type: FLK pid: 2393 [0- 
>> >9223372036854775807] flags: 0x0 remote: 0x49437cb8a7f893b2 expref:  
>> 7527 pid: 19134 timeout: 0
>>
>>
>> This warning has been removed in the 1.8 release of Lustre.  In  
>> particular, with FLK (flock) type locks, they can be held  
>> indefinitely, so there is no reason to print a message at all.
>>


Cheers, Andreas
--
Andreas Dilger
Sr. Staff Engineer, Lustre Group
Sun Microsystems of Canada, Inc.