<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">Hi Ben,<div><br></div><div>I just check my messages log files, both on client and server, and I dont find any hung task you notice on yours.. </div><div><br></div><div>As you can read below, i dont note the performance issue in a simple DD but I think my issue is concerning a set of small files (tens of thousands nay more)…</div><div><br></div><div><div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">[root@nisus test]# ddt -t 10g /mnt/test/</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Writing to /mnt/test/ddt.8362 ... syncing ... done.</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">sleeping 10 seconds ... done.</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Reading from /mnt/test/ddt.8362 ... done.</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">10240MiB KiB/s CPU%</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Write 114770 4</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Read 40675 4</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);"><br></div></div><div>for info: /mnt/test concerns the single v2 GlFS volume</div><div><br></div><div apple-content-edited="true"><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">[root@nisus test]# ddt -t 10g /mnt/fhgfs/</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Writing to /mnt/fhgfs/ddt.8380 ... syncing ... done.</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">sleeping 10 seconds ... done.</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Reading from /mnt/fhgfs/ddt.8380 ... done.</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">10240MiB KiB/s CPU%</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Write 102591 1</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">Read 98079 2</div><div><br></div></div></div><div>Do you have a idea how to tune/optimize performance settings? and/or TCP settings (MTU, etc.)?</div><div><br></div><div><div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| | UNTAR | DU | FIND | TAR | RM |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| single | ~3m45s | ~43s | ~47s | ~3m10s | ~3m15s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| replicated | ~5m10s | ~59s | ~1m6s | ~1m19s | ~1m49s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| distributed | ~4m18s | ~41s | ~57s | ~2m24s | ~1m38s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| dist-repl | ~8m18s | ~1m4s | ~1m11s | ~1m24s | ~2m40s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| native FS | ~11s | ~4s | ~2s | ~56s | ~10s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| BeeGFS | ~3m43s | ~15s | ~3s | ~1m33s | ~46s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">| single (v2) | ~3m6s | ~14s | ~32s | ~1m2s | ~44s |</div><div style="margin: 0px; font-size: 10px; font-family: Menlo; color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);">---------------------------------------------------------------</div></div><div>for info: </div><div><span class="Apple-tab-span" style="white-space: pre;"> </span>-BeeGFS is a distributed FS (4 bricks, 2 bricks per server and 2 servers)</div><div><span class="Apple-tab-span" style="white-space: pre;"> </span>- single (v2): simple gluster volume with default settings</div></div><div><br></div><div>I also note I obtain the same tar/untar performance issue with FhGFS/BeeGFS but the rest (DU, FIND, RM) looks like to be OK.</div><div><br></div><div>Thank you very much for your reply and help.</div><div>Geoffrey<br><div apple-content-edited="true">
<div style="color: rgb(0, 0, 0); letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">-----------------------------------------------<br>Geoffrey Letessier<br><br>Responsable informatique & ingénieur système<br>CNRS - UPR 9080 - Laboratoire de Biochimie Théorique<br>Institut de Biologie Physico-Chimique<br>13, rue Pierre et Marie Curie - 75005 Paris<br>Tel: 01 58 41 50 93 - eMail: <a href="mailto:geoffrey.letessier@cnrs.fr">geoffrey.letessier@cnrs.fr</a></div>
</div>
<br><div><div>Le 2 juin 2015 à 21:53, Ben Turner <<a href="mailto:bturner@redhat.com">bturner@redhat.com</a>> a écrit :</div><br class="Apple-interchange-newline"><blockquote type="cite"><div style="font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;">I am seeing problems on 3.7 as well. Can you check /var/log/messages on both the clients and servers for hung tasks like:<br><br>Jun 2 15:23:14 gqac006 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.<br>Jun 2 15:23:14 gqac006 kernel: iozone D 0000000000000001 0 21999 1 0x00000080<br>Jun 2 15:23:14 gqac006 kernel: ffff880611321cc8 0000000000000082 ffff880611321c18 ffffffffa027236e<br>Jun 2 15:23:14 gqac006 kernel: ffff880611321c48 ffffffffa0272c10 ffff88052bd1e040 ffff880611321c78<br>Jun 2 15:23:14 gqac006 kernel: ffff88052bd1e0f0 ffff88062080c7a0 ffff880625addaf8 ffff880611321fd8<br>Jun 2 15:23:14 gqac006 kernel: Call Trace:<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffffa027236e>] ? rpc_make_runnable+0x7e/0x80 [sunrpc]<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffffa0272c10>] ? rpc_execute+0x50/0xa0 [sunrpc]<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff810aaa21>] ? ktime_get_ts+0xb1/0xf0<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff811242d0>] ? sync_page+0x0/0x50<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8152a1b3>] io_schedule+0x73/0xc0<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8112430d>] sync_page+0x3d/0x50<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8152ac7f>] __wait_on_bit+0x5f/0x90<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff81124543>] wait_on_page_bit+0x73/0x80<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8109eb80>] ? wake_bit_function+0x0/0x50<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8113a525>] ? pagevec_lookup_tag+0x25/0x40<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8112496b>] wait_on_page_writeback_range+0xfb/0x190<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff81124b38>] filemap_write_and_wait_range+0x78/0x90<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff811c07ce>] vfs_fsync_range+0x7e/0x100<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff811c08bd>] vfs_fsync+0x1d/0x20<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff811c08fe>] do_fsync+0x3e/0x60<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff811c0950>] sys_fsync+0x10/0x20<br>Jun 2 15:23:14 gqac006 kernel: [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b<br><br>Do you see a perf problem with just a simple DD or do you need a more complex workload to hit the issue? I think I saw an issue with metadata performance that I am trying to run down, let me know if you can see the problem with simple DD reads / writes or if we need to do some sort of dir / metadata access as well.<br><br>-b<br><br>----- Original Message -----<br><blockquote type="cite">From: "Geoffrey Letessier" <<a href="mailto:geoffrey.letessier@cnrs.fr">geoffrey.letessier@cnrs.fr</a>><br>To: "Pranith Kumar Karampuri" <<a href="mailto:pkarampu@redhat.com">pkarampu@redhat.com</a>><br>Cc:<span class="Apple-converted-space"> </span><a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>Sent: Tuesday, June 2, 2015 8:09:04 AM<br>Subject: Re: [Gluster-users] GlusterFS 3.7 - slow/poor performances<br><br>Hi Pranith,<br><br>I’m sorry but I cannot bring you any comparison because comparison will be<br>distorted by the fact in my HPC cluster in production the network technology<br>is InfiniBand QDR and my volumes are quite different (brick in RAID6<br>(12x2TB), 2 bricks per server and 4 servers into my pool)<br><br>Concerning your demand, in attachments you can find all expected results<br>hoping it can help you to solve this serious performance issue (maybe I need<br>play with glusterfs parameters?).<br><br>Thank you very much by advance,<br>Geoffrey<br>------------------------------------------------------<br>Geoffrey Letessier<br>Responsable informatique & ingénieur système<br>UPR 9080 - CNRS - Laboratoire de Biochimie Théorique<br>Institut de Biologie Physico-Chimique<br>13, rue Pierre et Marie Curie - 75005 Paris<br>Tel: 01 58 41 50 93 - eMail: <a href="mailto:geoffrey.letessier@ibpc.fr">geoffrey.letessier@ibpc.fr</a><br><br><br><br><br>Le 2 juin 2015 à 10:09, Pranith Kumar Karampuri < <a href="mailto:pkarampu@redhat.com">pkarampu@redhat.com</a> > a<br>écrit :<br><br>hi Geoffrey,<br>Since you are saying it happens on all types of volumes, lets do the<br>following:<br>1) Create a dist-repl volume<br>2) Set the options etc you need.<br>3) enable gluster volume profile using "gluster volume profile <volname><br>start"<br>4) run the work load<br>5) give output of "gluster volume profile <volname> info"<br><br>Repeat the steps above on new and old version you are comparing this with.<br>That should give us insight into what could be causing the slowness.<br><br>Pranith<br>On 06/02/2015 03:22 AM, Geoffrey Letessier wrote:<br><br><br>Dear all,<br><br>I have a crash test cluster where i’ve tested the new version of GlusterFS<br>(v3.7) before upgrading my HPC cluster in production.<br>But… all my tests show me very very low performances.<br><br>For my benches, as you can read below, I do some actions (untar, du, find,<br>tar, rm) with linux kernel sources, dropping cache, each on distributed,<br>replicated, distributed-replicated, single (single brick) volumes and the<br>native FS of one brick.<br><br># time (echo 3 > /proc/sys/vm/drop_caches; tar xJf ~/linux-4.1-rc5.tar.xz;<br>sync; echo 3 > /proc/sys/vm/drop_caches)<br># time (echo 3 > /proc/sys/vm/drop_caches; du -sh linux-4.1-rc5/; echo 3 ><br>/proc/sys/vm/drop_caches)<br># time (echo 3 > /proc/sys/vm/drop_caches; find linux-4.1-rc5/|wc -l; echo 3<br><blockquote type="cite">/proc/sys/vm/drop_caches)<br></blockquote># time (echo 3 > /proc/sys/vm/drop_caches; tar czf linux-4.1-rc5.tgz<br>linux-4.1-rc5/; echo 3 > /proc/sys/vm/drop_caches)<br># time (echo 3 > /proc/sys/vm/drop_caches; rm -rf linux-4.1-rc5.tgz<br>linux-4.1-rc5/; echo 3 > /proc/sys/vm/drop_caches)<br><br>And here are the process times:<br><br>---------------------------------------------------------------<br>| | UNTAR | DU | FIND | TAR | RM |<br>---------------------------------------------------------------<br>| single | ~3m45s | ~43s | ~47s | ~3m10s | ~3m15s |<br>---------------------------------------------------------------<br>| replicated | ~5m10s | ~59s | ~1m6s | ~1m19s | ~1m49s |<br>---------------------------------------------------------------<br>| distributed | ~4m18s | ~41s | ~57s | ~2m24s | ~1m38s |<br>---------------------------------------------------------------<br>| dist-repl | ~8m18s | ~1m4s | ~1m11s | ~1m24s | ~2m40s |<br>---------------------------------------------------------------<br>| native FS | ~11s | ~4s | ~2s | ~56s | ~10s |<br>---------------------------------------------------------------<br><br>I get the same results, whether with default configurations with custom<br>configurations.<br><br>if I look at the side of the ifstat command, I can note my IO write processes<br>never exceed 3MBs...<br><br>EXT4 native FS seems to be faster (roughly 15-20% but no more) than XFS one<br><br>My [test] storage cluster config is composed by 2 identical servers (biCPU<br>Intel Xeon X5355, 8GB of RAM, 2x2TB HDD (no-RAID) and Gb ethernet)<br><br>My volume settings:<br>single: 1server 1 brick<br>replicated: 2 servers 1 brick each<br>distributed: 2 servers 2 bricks each<br>dist-repl: 2 bricks in the same server and replica 2<br><br>All seems to be OK in gluster status command line.<br><br>Do you have an idea why I obtain so bad results?<br>Thanks in advance.<br>Geoffrey<br>-----------------------------------------------<br>Geoffrey Letessier<br><br>Responsable informatique & ingénieur système<br>CNRS - UPR 9080 - Laboratoire de Biochimie Théorique<br>Institut de Biologie Physico-Chimique<br>13, rue Pierre et Marie Curie - 75005 Paris<br>Tel: 01 58 41 50 93 - eMail: <a href="mailto:geoffrey.letessier@cnrs.fr">geoffrey.letessier@cnrs.fr</a><br><br><br><br>_______________________________________________<br>Gluster-users mailing list <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br><a href="http://www.gluster.org/mailman/listinfo/gluster-users">http://www.gluster.org/mailman/listinfo/gluster-users</a><br><br><br><br><br>_______________________________________________<br>Gluster-users mailing list<br><a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br><a href="http://www.gluster.org/mailman/listinfo/gluster-users">http://www.gluster.org/mailman/listinfo/gluster-users</a></blockquote></div></blockquote></div><br></div></body></html>