Thanks a lot Sven. I was trying out all the scenarios that Ray mentioned, with respect to lroc and all flash GPFS cluster and nothing seemed to be effective.
As of now, we are deploying a new test cluster on GPFS 5.0 and it would be good to know the respective features that could be enabled and see if it improves anything. On the other side, i have seen various cases in my past 6 years with GPFS, where different tools do frequently use mmap. This dates back to 2013.. http://www.spectrumscale.org/pipermail/gpfsug-discuss/2013-May/000253.html when one of my colleagues asked the same question. At that time, it was a homegrown application that was using mmap, along with few other genomic pipelines. An year ago, we had issue with mmap and lot of threads where GPFS would just hang without any traces or logs, which was fixed recently. That was related to relion : https://sbgrid.org/software/titles/relion The issue that we are seeing now is ML/DL workloads, and is related to implementing external tools such as openslide (http://openslide.org/), pytorch (http://pytorch.org/) with field of application being deep learning for thousands of image patches. The IO is really slow when accessed from hard disk, and thus i was trying out other options such as LROC and flash cluster/afm cluster. But everything has a limitation as Ray mentioned. Thanks, Lohit On Feb 22, 2018, 3:59 PM -0500, Sven Oehme <oeh...@gmail.com>, wrote: > Hi Lohit, > > i am working with ray on a mmap performance improvement right now, which most > likely has the same root cause as yours , see --> > http://gpfsug.org/pipermail/gpfsug-discuss/2018-January/004411.html > the thread above is silent after a couple of back and rorth, but ray and i > have active communication in the background and will repost as soon as there > is something new to share. > i am happy to look at this issue after we finish with ray's workload if there > is something missing, but first let's finish his, get you try the same fix > and see if there is something missing. > > btw. if people would share their use of MMAP , what applications they use > (home grown, just use lmdb which uses mmap under the cover, etc) please let > me know so i get a better picture on how wide the usage is with GPFS. i know > a lot of the ML/DL workloads are using it, but i would like to know what else > is out there i might not think about. feel free to drop me a personal note, i > might not reply to it right away, but eventually. > > thx. sven > > > > On Thu, Feb 22, 2018 at 12:33 PM <vall...@cbio.mskcc.org> wrote: > > > Hi all, > > > > > > I wanted to know, how does mmap interact with GPFS pagepool with respect > > > to filesystem block-size? > > > Does the efficiency depend on the mmap read size and the block-size of > > > the filesystem even if all the data is cached in pagepool? > > > > > > GPFS 4.2.3.2 and CentOS7. > > > > > > Here is what i observed: > > > > > > I was testing a user script that uses mmap to read from 100M to 500MB > > > files. > > > > > > The above files are stored on 3 different filesystems. > > > > > > Compute nodes - 10G pagepool and 5G seqdiscardthreshold. > > > > > > 1. 4M block size GPFS filesystem, with separate metadata and data. Data > > > on Near line and metadata on SSDs > > > 2. 1M block size GPFS filesystem as a AFM cache cluster, "with all the > > > required files fully cached" from the above GPFS cluster as home. Data > > > and Metadata together on SSDs > > > 3. 16M block size GPFS filesystem, with separate metadata and data. Data > > > on Near line and metadata on SSDs > > > > > > When i run the script first time for “each" filesystem: > > > I see that GPFS reads from the files, and caches into the pagepool as it > > > reads, from mmdiag -- iohist > > > > > > When i run the second time, i see that there are no IO requests from the > > > compute node to GPFS NSD servers, which is expected since all the data > > > from the 3 filesystems is cached. > > > > > > However - the time taken for the script to run for the files in the 3 > > > different filesystems is different - although i know that they are just > > > "mmapping"/reading from pagepool/cache and not from disk. > > > > > > Here is the difference in time, for IO just from pagepool: > > > > > > 20s 4M block size > > > 15s 1M block size > > > 40S 16M block size. > > > > > > Why do i see a difference when trying to mmap reads from different > > > block-size filesystems, although i see that the IO requests are not > > > hitting disks and just the pagepool? > > > > > > I am willing to share the strace output and mmdiag outputs if needed. > > > > > > Thanks, > > > Lohit > > > > > > _______________________________________________ > > > gpfsug-discuss mailing list > > > gpfsug-discuss at spectrumscale.org > > > http://gpfsug.org/mailman/listinfo/gpfsug-discuss > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at spectrumscale.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss
_______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss
