[lustre-discuss] varying sequential read performance.
John Bauer
bauerj at iodoctors.com
Thu Apr 5 17:22:53 PDT 2018
One last email on this. Creating 4 files to read, each using one of the
OSC that the stripeCount=4 file is using, and reading in a round
robin fashion, is what I was working on when I got distracted by the
numctl notion. I just finished up the 4 file read round robin read.
Nothing terribly surprising
except that reading the same amount of data (16GiB per OSC) from the 4
OSCs is about 10% faster ( max of 2.5GiB/s ) than
reading from a 64GiB 4 way striped file. In the table farther below,
the amount of blocked time for the individual files does point to 2
OSC's being responsible
for the lion's share of blocked I/O time. ( I named the files with the
OSC that they resides on ).
Again, thanks for your input.
John
Sorted by Blocked.
Code for reading in round robin fashion
*#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#define BSIZE (512*1024)
#define NREC 128000
int main( int argc, char **argv ) {
int fd[16] ;
int i ;
int nfile = argc -1 ;
for(i=0;i<nfile;i++){
fd[i] = open64( argv[i+1] , O_RDONLY|O_LARGEFILE ) ;
fprintf(stderr,"%s() fs[%d]=%d\n",__func__,i,fd[i]);
if( fd[i] < 0 ) exit(-1) ;
}
char *buff = malloc(BSIZE) ;
for(i=0;i<NREC;i++){
int f = fd[i%nfile] ;
off64_t off = (off64_t)(i/nfile) * BSIZE ;
ssize_t ret = pread64(f,buff,BSIZE,off) ;
if( ret < 0 ) break ;
}
for(i=0;i<nfile;i++){
close( fd[i] ) ;
}
}*
On 4/5/2018 12:33 PM, John Bent wrote:
> "I suspect that this OSC is using an OSS that is under heavier load."
>
> If you want to confirm this, it seems like you could create files with
> striping parameters such that you have a single file on each OSS.
> Well, I know you can make stripe=1 so it's only on one OSS but can you
> control/query on *which* OSS is the stripe? Assuming you can, then
> you just benchmark performance for each file (i.e. OSS) and you can
> discover more explicitly whether you have a slow OSS.
>
> On Thu, Apr 5, 2018 at 9:31 AM, John Bauer <bauerj at iodoctors.com
> <mailto:bauerj at iodoctors.com>> wrote:
>
> Rick,
>
> Thanks for reply. Also thanks to Patrick Farrell for making me
> rethink this.
>
> I am coming to believe that it is an OSS issue. Every time I run
> this job, the first pass of dd is slow, which I now attribute to
> all the OSSs
> needing to initially read the data in from disk to OSS cache. If
> the subsequent passes of dd get back soon enough I then observe
> good performance.
> If not, performance goes back to initial rates.
>
> Inspecting the individual wait times for each of the dd reads for
> one of the poor performing dd passes,
> and correlating them to the OSC that fulfills each individual dd
> read, I see that 75% of the wait time is from the a single OSC. I
> suspect that this OSC is
> using an OSS that is under heavier load.
>
> I don't have access to the OSS so I cant report on the Lustre
> settings. I think the client side max cached is 50% of memory.
>
> After speaking with Doug Petesch of Cray, I though I would look
> into numa effects on this job. I now also monitor the contents of
> */sys/devices/system/node/node?/meminfo *
> and ran the job with *numactl --cpunodebind=0*
> Interestingly enough, I now sometimes get dd transfer rates of
> 2.2GiB/s. Plotting the .../node?/meminfo[FilePages] value versus
> time for the 2 cpunodes shows that the
> data is now mostly placed on node0. Unfortunately, the variable
> rates still remain, as one would expect if it is an OSS caching
> issue, but the poor performance is also better.
>
> Resulting plot with all *numactl --cpunodebind=0*
>
>
> Resulting plots with *numactl --cpunodebind=x* where x alternates
> between 0 and 1 for each subsequent dd pass. And indeed, the file
> pages migrate between cpunodes.
>
>
>
> On 4/5/2018 9:22 AM, Mohr Jr, Richard Frank (Rick Mohr) wrote:
>> John,
>>
>> I had a couple of thoughts (though not sure if they are directly relevant to your performance issue):
>>
>> 1) Do you know what caching settings are applied on the lustre servers? This could have an impact on performance, especially if your tests are being run while others are doing IO on the system.
>>
>> 2) It looks like there is a parameter called llite.<fsname>.max_cached_mb that controls how much client side data is cached. According to the manual, the default value is 3/4 of the host’s RAM (which would be 48GB in your case). I don’t know why the cache seems to be used unevenly between your 4 OSTs, but it might explain why the cache for some OSTs decrease when others increase.
>>
>> --
>> Rick Mohr
>> Senior HPC System Administrator
>> National Institute for Computational Sciences
>> http://www.nics.tennessee.edu
>>
>>
>>> On Apr 2, 2018, at 8:06 PM, John Bauer<bauerj at iodoctors.com> <mailto:bauerj at iodoctors.com> wrote:
>>>
>>> I am running dd 10 times consecutively to read a 64GB file ( stripeCount=4 stripeSize=4M ) on a Lustre client(version 2.10.3) that has 64GB of memory.
>>> The client node was dedicated.
>>>
>>> for pass in 1 2 3 4 5 6 7 8 9 10
>>> do
>>> of=/dev/null if=${file} count=128000 bs=512K
>>> done
>>>
>>> Instrumentation of the I/O from dd reveals varying performance. In the plot below, the bottom frame has wall time
>>> on the X axis, and file position of the dd reads on the Y axis, with a dot plotted at the wall time and starting file position of every read.
>>> The slopes of the lines indicate the data transfer rate, which vary from 475MB/s to 1.5GB/s. The last 2 passes have sharp breaks
>>> in the performance, one with increasing performance, and one with decreasing performance.
>>>
>>> The top frame indicates the amount of memory used by each of the file's 4 OSCs over the course of the 10 dd runs. Nothing terribly odd here except that
>>> one of the OSC's eventually has its entire stripe ( 16GB ) cached and then never gives any up.
>>>
>>> I should mention that the file system has 320 OSTs. I found LU-6370 which eventually started discussing LRU management issues on systems with high
>>> numbers of OST's leading to reduced RPC sizes.
>>>
>>> Any explanations for the varying performance?
>>> Thanks,
>>> John
>>>
>>> <johbmffmkkegkbkh.png>
>>> --
>>> I/O Doctors, LLC
>>> 507-766-0378
>>>
>>> bauerj at iodoctors.com <mailto:bauerj at iodoctors.com>
>>> _______________________________________________
>>> lustre-discuss mailing list
>>> lustre-discuss at lists.lustre.org
>>> <mailto:lustre-discuss at lists.lustre.org>
>>> http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
>>> <http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org>
>
> --
> I/O Doctors, LLC
> 507-766-0378
> bauerj at iodoctors.com <mailto:bauerj at iodoctors.com>
>
>
> _______________________________________________
> lustre-discuss mailing list
> lustre-discuss at lists.lustre.org
> <mailto:lustre-discuss at lists.lustre.org>
> http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
> <http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org>
>
>
--
I/O Doctors, LLC
507-766-0378
bauerj at iodoctors.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20180405/b491a9ac/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: dfcabjmonfdkhpda.png
Type: image/png
Size: 25541 bytes
Desc: not available
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20180405/b491a9ac/attachment-0004.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: mnebiinlmiknodcc.png
Type: image/png
Size: 25777 bytes
Desc: not available
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20180405/b491a9ac/attachment-0005.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: dmnkhfdbfaoanfoi.png
Type: image/png
Size: 32829 bytes
Desc: not available
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20180405/b491a9ac/attachment-0006.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: bcmgmmocefcclfeb.png
Type: image/png
Size: 26211 bytes
Desc: not available
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20180405/b491a9ac/attachment-0007.png>
More information about the lustre-discuss
mailing list