Re: [Moosefs-users] moosefs losing chunks

[Chris P. <ch...@ec...>]

On Wed, 2011-12-21 at 18:32 -0300, Ricardo J. Barberis wrote:
> El Martes 20 Diciembre 2011, Chris Picton escribió:
> > Hi List
> 
> Hi Chris,

> I grep'ed /var/log/messages for "currently unavailable file" and ran 
> mfsfileinfo on all the files with missing chunks (i.e.: chunks marked as "no 
> valid copies").
> 
> Then I tan mfsfilrepair on those files, expecting to get those missing
> chunks zeroed out but their version got downgraded instead.
> 

In my case, I had subsequently done a mfscheckfile recursively on my
entire filesystem, and noted the files with 0 chunks

I ran a mfsfilerepair on those (not checking my messages file too
closely, and expecting the blocks to be zeroed out).  My vms booted
correctly, and after running a forced fsck and rpm -Va, no errors were
detected.

I am assuming I had the same scenario as you, where the previous chunk
version was restored, instead of being zeroed out (or by a large
coincidence, all failed chunks had not yet been allocated in the VM
disks yet)

The odd thing is that I had done a search on the chunkservers for some
of the chunk names (ignoring version - find . -iname "*010B7E*" for
example), and didnt find the physical chunks on the chunkservers at all.

But all is running fine now - thanks

Chris

> I think this is because the master might have received an update operation but 
> the chunkservers didn't get a chance to complete the update, so the 
> master "restored" the last good version of the chunk.
> 
> Since (AFAIK) there is no way to know beforehand what mfsfilerepair is going 
> to do with the missing chunks, I'd recommend you to be careful.
> 
> Regards,

Disclaimer

The information contained in this communication from the sender is confidential. It is intended solely for use by the recipient and others authorized to receive it. If you are not the recipient, you are hereby notified that any disclosure, copying, distribution or taking action in relation of the contents of this information is strictly prohibited and may be unlawful.

This email has been scanned for viruses and malware, and automatically archived by Mimecast SA (Pty) Ltd, an innovator in Software as a Service (SaaS) for business. Mimecast Unified Email Management ™ (UEM) offers email continuity, security, archiving and compliance with all current legislation. To find out more, contact Mimecast.