[Lustre-discuss] md and mdadm in 1.8.7-wc1

Samuel Aparicio saparicio at bccrc.ca
Tue Mar 20 21:13:26 PDT 2012


I appreciate your taking the time to do that. If it looks like it basically works we'll give it a try and see if the md issues go away.
we have a pair of OSS servers we can try this on with a 200Tb filesystem and not risk losing anything important,
so I think what we may do is compare the 1.8.7 build against a newer kernel, with the 2.1.1 release,
which looks like it is approaching stability for production environments and see how that fares with mdadm




Professor Samuel Aparicio BM BCh PhD FRCPath
Nan and Lorraine Robertson Chair UBC/BC Cancer Agency
675 West 10th, Vancouver V5Z 1L3, Canada.
office: +1 604 675 8200 lab website http://molonc.bccrc.ca







On Mar 20, 2012, at 2:53 PM, Joe Landman wrote:

> On 03/20/2012 02:42 PM, Samuel Aparicio wrote:
>> Thanks for this.
>> 
>> we have zero experience of patching lustre 1.8.7 against newer kernels,
>> are there any known pitfalls we should avoid.
> 
> I just completed a (completely untested at the moment) build of 
> 2.6.32.59.scalable with 1.8.7 patches.  We'll do some testing here 
> first, but if it looks like it works well, we'll put a pointer to the 
> RPM.  Or if you want to risk your dog biting you while your servers 
> possibly exploding, strafing your data center with untold numbers of 
> bits, and a diskful or two of lost metadata, I'd be happy to make it 
> available before our testing (we don't care if we lose data on our test 
> rigs) begins.
> 
> Regards,
> 
> Joe
> 
> 
> 
> -- 
> Joseph Landman, Ph.D
> Founder and CEO
> Scalable Informatics Inc.
> email: landman at scalableinformatics.com
> web  : http://scalableinformatics.com
>        http://scalableinformatics.com/sicluster
> phone: +1 734 786 8423 x121
> fax  : +1 866 888 3112
> cell : +1 734 612 4615

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20120320/e233a044/attachment.htm>


More information about the lustre-discuss mailing list