<div dir="ltr">Hi, <div><br></div><div>Any news about this? I provided very detailed test results and proof of the issue <a href="https://github.com/gluster/glusterfs/issues/3206">https://github.com/gluster/glusterfs/issues/3206</a> on 6 February 2022 but haven't heard back after that. </div><div><br></div><div>Best regards, </div><div>Zakhar</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, Feb 8, 2022 at 7:14 AM Zakhar Kirpichenko <<a href="mailto:zakhar@gmail.com">zakhar@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div>Hi, <br></div><div><br></div><div>I've updated the github issue with more details: <a href="https://github.com/gluster/glusterfs/issues/3206#issuecomment-1030770617" target="_blank">https://github.com/gluster/glusterfs/issues/3206#issuecomment-1030770617</a></div><div><br></div><div>Looks like there's a memory leak. <br></div><div><br></div><div>/Z<br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sat, Feb 5, 2022 at 8:45 PM Zakhar Kirpichenko <<a href="mailto:zakhar@gmail.com" target="_blank">zakhar@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div>Hi Strahil,</div><div><br></div><div>Many thanks for your reply! I've updated the Github issue with statedump files taken before and after the tar operation: <a href="https://github.com/gluster/glusterfs/files/8008635/glusterdump.19102.dump.zip" target="_blank">https://github.com/gluster/glusterfs/files/8008635/glusterdump.19102.dump.zip</a> <br></div><div></div><div><br></div><div>Please disregard that path= entries are empty, in the original dumps there are real paths but I deleted them as they might contain sensitive information. <br><br>The odd thing is that the dump file is full of:<br><br>1) xlator.performance.write-behind.wb_inode entries, but the tar operation does not write to these files. The whole backup process is read-only. <br><br>2) xlator.performance.quick-read.inodectx entries, which never go away. <br><br>None of this happens on other clients, which read and write from/to the same volume in a much more intense manner. <br></div><div><br></div><div>Best regards, <br></div><div>Z<br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sat, Feb 5, 2022 at 11:23 AM Strahil Nikolov <<a href="mailto:hunter86_bg@yahoo.com" target="_blank">hunter86_bg@yahoo.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div> Can you generate a statedump before and after the tar ?<br>For statedump generation , you can follow <a href="https://github.com/gluster/glusterfs/issues/1440#issuecomment-674051243" target="_blank">https://github.com/gluster/glusterfs/issues/1440#issuecomment-674051243</a> .<br><br>Best Regards,<br>Strahil Nikolov<br><br><br> </div> <div style="margin:10px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"> <div style="font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:13px;color:rgb(38,40,42)"> <div> В събота, 5 февруари 2022 г., 07:54:22 Гринуич+2, Zakhar Kirpichenko <<a href="mailto:zakhar@gmail.com" target="_blank">zakhar@gmail.com</a>> написа: </div> <div><br></div> <div><br></div> <div><div id="gmail-m_2874209313559434708gmail-m_5389408207390456313gmail-m_-6297271345084962301yiv0808002028"><div dir="ltr"><div>Hi! <br></div><div><br></div><div>I opened a Github issue <a rel="nofollow noopener noreferrer" href="https://github.com/gluster/glusterfs/issues/3206" target="_blank">https://github.com/gluster/glusterfs/issues/3206</a> but not sure how much attention they get there, so re-posting here just in case someone has any ideas. <br></div><div><br></div><div>Description of problem:<br><br>GlusterFS 9.5, 3-node cluster (2 bricks + arbiter), an attempt to tar the whole filesystem (35-40 GB, 1.6 million files) on a client succeeds but causes the glusterfs fuse mount process to consume 0.5+ GB of RAM. The usage never goes down after tar exits.<br><br>The exact command to reproduce the issue:<br><br>/usr/bin/tar --use-compress-program="/bin/pigz" -cf /path/to/archive.tar.gz --warning=no-file-changed /glusterfsmount<br></div><div><br></div><div>The output of the gluster volume info command:</div><div><br>Volume Name: gvol1<br>Type: Replicate<br>Volume ID: 0292ac43-89bd-45a4-b91d-799b49613e60<br>Status: Started<br>Snapshot Count: 0<br>Number of Bricks: 1 x (2 + 1) = 3<br>Transport-type: tcp<br>Bricks:<br>Brick1: 192.168.0.31:/gluster/brick1/gvol1<br>Brick2: 192.168.0.32:/gluster/brick1/gvol1<br>Brick3: 192.168.0.5:/gluster/brick1/gvol1 (arbiter)<br>Options Reconfigured:<br>performance.open-behind: off<br>cluster.readdir-optimize: off<br>cluster.consistent-metadata: on<br>features.cache-invalidation: on<br>diagnostics.count-fop-hits: on<br>diagnostics.latency-measurement: on<br>storage.fips-mode-rchecksum: on<br>performance.cache-size: 256MB<br>client.event-threads: 8<br>server.event-threads: 4<br>storage.reserve: 1<br>performance.cache-invalidation: on<br>cluster.lookup-optimize: on<br>transport.address-family: inet<br>nfs.disable: on<br>performance.client-io-threads: on<br>features.cache-invalidation-timeout: 600<br>performance.md-cache-timeout: 600<br>network.inode-lru-limit: 50000<br>cluster.shd-max-threads: 4<br>cluster.self-heal-window-size: 8<br>performance.enable-least-priority: off<br>performance.cache-max-file-size: 2MB<br><br>The output of the gluster volume status command:<br><br>Status of volume: gvol1<br>Gluster process TCP Port RDMA Port Online Pid<br>------------------------------------------------------------------------------<br>Brick 192.168.0.31:/gluster/brick1/gvol1 49152 0 Y 1767<br>Brick 192.168.0.32:/gluster/brick1/gvol1 49152 0 Y 1696<br>Brick 192.168.0.5:/gluster/brick1/gvol1 49152 0 Y 1318<br>Self-heal Daemon on localhost N/A N/A Y 1329<br>Self-heal Daemon on 192.168.0.31 N/A N/A Y 1778<br>Self-heal Daemon on 192.168.0.32 N/A N/A Y 1707<br><br>Task Status of Volume gvol1<br>------------------------------------------------------------------------------<br>There are no active volume tasks<br><br>The output of the gluster volume heal command:<br><br>Brick 192.168.0.31:/gluster/brick1/gvol1<br>Status: Connected<br>Number of entries: 0<br><br>Brick 192.168.0.32:/gluster/brick1/gvol1<br>Status: Connected<br>Number of entries: 0<br><br>Brick 192.168.0.5:/gluster/brick1/gvol1<br>Status: Connected<br>Number of entries: 0<br></div><div><br></div><div>The operating system / glusterfs version:<br><br>CentOS Linux release 7.9.2009 (Core), fully up to date<br>glusterfs 9.5<br>kernel 3.10.0-1160.53.1.el7.x86_64</div><div><br>The logs are basically empty since the last mount except for the mount-related messages.<br></div><div><br></div><div>Additional info: a statedump from the client is attached to the Github issue, <a rel="nofollow noopener noreferrer" href="https://github.com/gluster/glusterfs/files/8004792/glusterdump.18906.dump.1643991007.gz" target="_blank">https://github.com/gluster/glusterfs/files/8004792/glusterdump.18906.dump.1643991007.gz</a>, in case someone wants to have a look.<br><br>There was also an issue with other clients, running PHP applications with lots of small files, where glusterfs fuse mount process would very quickly balloon to ~2 GB over the course of 24 hours and its performance would slow to a crawl. This happened very consistently with glusterfs 8.x and 9.5, I managed to resolve it at least partially with disabling performance.open-behind: the memory usage either remains consistent or increases at a much slower rate, which is acceptable for this use case.<br><br>Now the issue remains on this single client, which doesn't do much other than reading and archiving all files from the gluster volume once per day. The glusterfs fuse mount process balloons to 0.5+ GB during the first tar run and remains more or less consistent afterwards, including subsequent tar runs.</div><div><br></div><div>I would very much appreciate any advice or suggestions. <br></div><div><br></div><div>Best regards, <br></div><div>Zakhar<br></div></div></div>________<br><br><br><br>Community Meeting Calendar:<br><br>Schedule -<br>Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC<br>Bridge: <a href="https://meet.google.com/cpu-eiue-hvk" target="_blank">https://meet.google.com/cpu-eiue-hvk</a><br>Gluster-users mailing list<br><a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br><a href="https://lists.gluster.org/mailman/listinfo/gluster-users" target="_blank">https://lists.gluster.org/mailman/listinfo/gluster-users</a><br></div> </div> </div></blockquote></div>
</blockquote></div>
</blockquote></div>