[Gluster-devel] Unify/AFR crashes

Dmitriy Kotkin kotdv at intergam.com
Mon Aug 11 08:48:22 UTC 2008


Guys... 
Is there any chance to fix NS crashes, I/O errors (coz of NS) so far? 
We're in production... so I can't live with it till hash translator...
really. 
If it isn't possible to fix I'll switch to AFR... 

If you have a time to help me and fix this bug please do it. I'm in
#gluster.

Best regards, 
Dmitriy Kotkin
Intergam Technologies Corporation
Moscow, Russia
mailto: kotdv at intergam.com
-----Original Message-----
From: gluster-devel-bounces+kotdv=intergam.com at nongnu.org
[mailto:gluster-devel-bounces+kotdv=intergam.com at nongnu.org] On Behalf Of
Dmitriy Kotkin 
Sent: Thursday, August 07, 2008 11:54 AM
To: 'Krishna Srinivas'
Cc: 'Gluster Developers Discussion List'
Subject: RE: [Gluster-devel] Unify/AFR crashes

Hello Krishna. 

I got the same bug yesterday after you asked me to change transport timeout.

Namespace is activating bailing transport and so on... 

There are some files that I can open (cat) in /storage (i.e. export
directory) but I get I/O errors and NS crashes when I'm trying to open (cat)
it in the mount point. 
These files exist in only one AFR (so there's no bug with existing in 2 AFRs
at the same time for example). 
It's "Open success on child node, failed on namespace". 

I can reproduce the NS crash by trying to do some ops with these "bad
files".

I tried to make a copy of that dir with a fresh content and I got the same
behavior (hang on # cat, bailing) with the same file. 

P.S.: I'm in #gluster. 

Best regards, 
Dmitriy Kotkin
Intergam Technologies Corporation
Moscow, Russia
mailto: kotdv at intergam.com
-----Original Message-----
From: krishna.zresearch at gmail.com [mailto:krishna.zresearch at gmail.com] On
Behalf Of Krishna Srinivas
Sent: Wednesday, August 06, 2008 11:07 AM
To: Dmitriy Kotkin
Cc: Gluster Developers Discussion List
Subject: Re: [Gluster-devel] Unify/AFR crashes

Dmitriy,
Did you get any help on IRC? What kind of operations do you do
when you say "intense fops"? Does the first node crash? do you
have the core file? if yes can you get the backtrace?
Krishna

On Tue, Aug 5, 2008 at 7:23 PM, Dmitriy Kotkin <kotdv at intergam.com> wrote:
> Hello guys!
> I'm using glusterfs-1.3.10 (the same for 1.3.9tla787) and unify over afrs
> setup.
> The problem is that during intense fs ops every first node listed in AFRs
> crashes (activating boiling transport and so on).
>
> If you want me to debug it - I'll join IRC so you can tell me how to do
it,
> where to set breakpoint and so.
>
>
>
>
>
>
> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at nongnu.org
> http://lists.nongnu.org/mailman/listinfo/gluster-devel
>




_______________________________________________
Gluster-devel mailing list
Gluster-devel at nongnu.org
http://lists.nongnu.org/mailman/listinfo/gluster-devel







More information about the Gluster-devel mailing list