[lustre-discuss] Unexpected result with overstriping

[bauerj at iodoctors.com]

Andreas,
Thanks for the update. I should point out that the documentation for -C is incorrect in that it states all the OSTs in the file system will be used, but in actuality it is all the OSTs in the selected  pool will be used. 
John

Sent from my iPhone

> On May 17, 2024, at 11:37 AM, Andreas Dilger <adilger at ddn.com> wrote:
> 
>  There is a patch inflight that adds "-C -N" -> "N stripes per OST", N <= 32.  This also changes "-C -1" to be the same as "-c -1" (ie. 1-stripe per OST), which was discussed and decided to be the more sensible option than using 2000 stripes for a file. If there is a need for a 2000-stripe file, "-C 2000" can still be used. 
> 
> https://review.whamcloud.com/54192
> 
> Cheers, Andreas
> 
>>> On May 17, 2024, at 17:32, Nathan Dauchy via lustre-discuss <lustre-discuss at lists.lustre.org> wrote:
>>> 
>> 
>> John,
>> 
>> I believe the lfs-setstripe man page is incorrect (or at least misleading) in this case. I recall seeing 2000 hardcoded as a maximum, so it appears to be picking that.
>> 
>> Using "-C -1" to put a single stripe on each OST wouldn't have any benefit over "-c -1".   IMHO, it would probably be more useful to have negative values represent number of stripes per OST. 🙂
>> 
>> -Nathan
>> From: lustre-discuss <lustre-discuss-bounces at lists.lustre.org> on behalf of John Bauer <bauerj at iodoctors.com>
>> Sent: Friday, May 17, 2024 8:48 AM
>> To: lustre-discuss <lustre-discuss at lists.lustre.org>
>> Subject: [lustre-discuss] Unexpected result with overstriping
>>  
>> External email: Use caution opening links or attachments
>> 
>> Good morning all,
>> 
>> I am playing around with overstriping a bit and I found a behavior that, to me, would seem unexpected.  The documentation for -C -1  indicates that the file should be striped over all available OSTs.  The pool, which happens to be the default, is ssd-pool which has 32 OSTs.  I got a stripeCount of 2000.  Is this as expected?
>> 
>> pfe20.jbauer2 213> rm -f /nobackup/jbauer2/ddd.dat
>> pfe20.jbauer2 214> lfs setstripe -C -1 /nobackup/jbauer2/ddd.dat
>> pfe20.jbauer2 215> lfs getstripe /nobackup/jbauer2/ddd.dat
>> /nobackup/jbauer2/ddd.dat
>> lmm_stripe_count:  2000
>> lmm_stripe_size:   1048576
>> lmm_pattern:       raid0,overstriped
>> lmm_layout_gen:    0
>> lmm_stripe_offset: 119
>> lmm_pool:          ssd-pool
>>     obdidx         objid         objid         group
>>        119          52386287        0x31f59ef                 0
>>        123          52347947        0x31ec42b                 0
>>        127          52734487        0x324aa17                 0
>>        121          52839396        0x32643e4                 0
>>        131          52742709        0x324ca35                 0
>>        116          52242659        0x31d28e3                 0
>>        117          51831125        0x316e155                 0
>>        124          52425218        0x31ff202                 0
>>        125          52402722        0x31f9a22                 0
>>        106          52700581        0x32425a5                 0
>> 
>> edited for brevity
>> 
>> 
>> _______________________________________________
>> lustre-discuss mailing list
>> lustre-discuss at lists.lustre.org
>> http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20240517/5b0cb3a7/attachment.htm>