Hi,
Lustre stripes in round robin manner. So let say that you have stripe
count set to 2 and stripe size set to 1MB. When you start write 3GB
file from a client to lustre it will send 1MB piece to OST1 and then
1MB piece to OST2 and it will keep doing that until it send 3GB or
until there is no free space left on OST''s. From you description it
looks like you are not striping at all. use command `lfs getstripe
<path_to_file>` to get striping information. In order to stripe across
both OST in your case create new dir and then use command `lfs
setstripe -c 2 <path_to _new_dir>. If you now create a file under this
new directory it will be striped accross both OST''s
Cheers,
Wojciech
On 21 Feb 2008, at 10:21, Mailer PH wrote:
> Hello ,
> Just a questune , does single file stipes across few OTS''s ?
> I just run into strange behviour of lustre , i tested the way lustre
> stipes the data on 2 OST''s
> There are 2 OTS''s
> 1 is 5 gig with 50% left
> 2 is 3 gig with 90% left on it
> Im moving 3 gig file to lustre(from a client)
> it start wrting the file to OST 0 as it say on lfs getstripe
> filename.iso
> while the file is moving im watching the OST 0 with df -h
> OST 0 is starting to fill up and when getting to 100% the file
> transfer is stopping with an error
> I had the imression that it will continue wrting the file to OST 1
> when OST 0 run out of space
>
> Is this behaviour is ok ?
>
> Thanks ,
>
>
>
> ----------------------------------------------------------
> Outgoing messages are virus free checked by NOD32 system
>
> _______________________________________________
> Lustre-discuss mailing list
> Lustre-discuss at lists.lustre.org
> http://lists.lustre.org/mailman/listinfo/lustre-discuss
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://lists.lustre.org/pipermail/lustre-discuss/attachments/20080222/25ba61a8/attachment-0002.html