I believe each iozone process is writing its own file...

Im curious to see if  pvfs2.8.2 addresses any of this, would it be
possible to try it out ?

As a general note with IB hardware - and it probably wont help with
this specific problem - you may also want to set FlowBufferSizeBytes
in your config file up to 1MB from 64k.

Best,

Kyle Schochenmaier



On Fri, Apr 30, 2010 at 7:39 PM, neutron <[email protected]> wrote:
> Thanks Kyle!
>
> I disabled the "TroveSyncMeta" to "no", but it doesn't make a difference.
> The poster you mentioned said the problem occurs with serial programs,
> and parallel program wont' see such a hit.
> what's  serial/parallel here mean?   I let 8 iozone processes run on 8
> nodes and aggregate the bandwidth. Isn't it a parallel program?
>
> http://www.beowulf-underground.org/pipermail/pvfs2-users/2009-April/002770.html
>
>
>
> -Neutron
>
>
> On Fri, Apr 30, 2010 at 8:17 PM, Kyle Schochenmaier <[email protected]> 
> wrote:
>> Hi Neutron -
>>
>> Check out a very similar thread from about a year ago :
>> http://www.beowulf-underground.org/pipermail/pvfs2-users/2009-April/002770.html
>>
>> Im not sure if we found out what was actually causing the performance
>> differences..  but its probably a start to look into.
>>
>> Best,
>> Kyle Schochenmaier
>>
>>
>>
>> On Fri, Apr 30, 2010 at 7:08 PM, neutron <[email protected]> wrote:
>>> Hi all,
>>>
>>> I have a pvfs2-2.8.1 with 4 DS.  "BMIModules" is set to  "bmi_ib".  I
>>> use simple-tripe mode with stipe-size =1MB.
>>>
>>> 8 client nodes mount pvfs2, and I use iozone to measure the write
>>> throughput, with each client node runs one iozone process.
>>> Each process writes 1GB file with block size = 4MB.
>>>
>>> I got the following results:
>>>
>>>        Test running:
>>>
>>>        Children see throughput for  8 initial writers  =   98513.53 KB/sec
>>>        Min throughput per process                      =   11406.64 KB/sec
>>>        Max throughput per process                      =   12642.13 KB/sec
>>>        Avg throughput per process                      =   12314.19 KB/sec
>>>        Min xfer                                        =  946176.00 KB
>>>        CPU Utilization: Wall time   86.492    CPU time    6.355    CPU
>>> utilization   7.35 %
>>>
>>>
>>>        Test running:
>>>        Children see throughput for  8 rewriters        = 2499467.09 KB/sec
>>>        Min throughput per process                      =  289479.62 KB/sec
>>>        Max throughput per process                      =  321507.38 KB/sec
>>>        Avg throughput per process                      =  312433.39 KB/sec
>>>        Min xfer                                        =  946176.00 KB
>>>        CPU utilization: Wall time    3.272    CPU time    5.990    CPU
>>> utilization 183.08 %
>>>
>>>
>>> We can see the "initial write"  gets very low throughput, while the
>>> "rewrite" gives very high bandwidth.
>>> My questions are:
>>> 1. Why 8 client nodes  as a whole get low throughput?
>>> 2. Why at "rewrite" phase, the write bandwidth boosts ?
>>>
>>>
>>>
>>> -Neutron
>>> _______________________________________________
>>> Pvfs2-users mailing list
>>> [email protected]
>>> http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users
>>>
>>
>

_______________________________________________
Pvfs2-users mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users

Reply via email to