[robinhood-support] Robinhood 3.0.1 rebooting unexpectedly on initial scan with Lustre 2.8.0.8
Hello, I have a problem similar to https://sourceforge.net/p/robinhood/mailman/message/35883907/ in which the robinhood server running mariadb-5.5.52-1.el7.x86_64 and lustre 2.8.0.8 client will reboot when the initial scan is run. I am running this in a testbed environment prior to deployment on our production system because I want to get a complete handle on it before I commit to the deployment. I have 2 separate lustre file systems that I am running against: One is a 408TB lustre 2.8 file system with ~16M inodes, the other is a 204TB lustre 2.5.5 file system with ~3M inodes. The curious thing is that I had successfully scanned both file systems independently on the system with everything working (including web-gui) and then basically blew away the databases to get a datapoint on how the system performed and the time it took if I ran a scan on both file systems simultaneously. It appears that it is only impacting the 2.8 file system database. I just ran a fresh scan against the 2.5.5 file system without problem. I then stated a new scan against the 2.8 file system an once again it rebooted. Like the other support ticket above, when I ran the scan only on the 2.8 file system in debug mode it also reported messages similar to “2017/07/10 15:44:58 [15191/6] FS_Scan | openat failed on
Re: [robinhood-support] Updating access times in Robinhood
On 07/11/17 16:35, Hoolihan, Joe (US) wrote: All, I am seeing an odd behavior with Robinhood and MySQL when tracking Lustre file system access times. Here is my test: I created a file on my Lustre file system. It created a record in the robinhood database, in the ENTRIES table, and a rbh-report --entry-info filename returned the info. I then added a text line to the file (echo "ADDED STRING" >> filename). an ls -l of the file revealed it had been modified, but the rbh-report --entry-info and direct query of the database showed that the last_access and last_mod fields had not updated. This did not change over time. Hello Hoolihan, You did not give much details about your robinhood configuration. * Is a changelog reader properly registered to the filesystem? (cat /proc/fs/lustre/mdd/*/changelog_users on the MDS) Does the changelog mask include OPEN, CLOSE, MTIME (cat /proc/fs/lustre/mdd/*/changelog_mask on the MDS) * Do you have a robinhood daemon running with the --readlog option? Depending on your configuration and the system load, there may be a delay between the action on the filesystem and the update of the robinhood DB. Posting your robinhood configuration may help troubleshooting. When the file permissions were changed (chmod 640 filename) that forced an update to the database and both direct query and rbh-report --entry-info were correct. Each time value was correct (last_access time was different from last_mod, reflecting the correct values). It sounds like your changelog mask is incomplete, as robinhood seams to react on SETATTR but not on OPEN/MTIME/CLOSE So, my question is: Is there something I did wrong that would cause the database not to get updated when a lustre file changed (some config value or other setting), or is this a possible bug (or maybe a feature) ? Also take care that access time (POSIX' atime) is different from last modification time (mtime) and change time (ctime). By default, the changelog mask include events that modify mtime and ctime, but not atime. HTH Thomas. Joseph P. Hoolihan BAE Systems, Inc. 443-654-9701 onsite number 301-974-9033 cell -- Check out the vibrant tech community on one of the world's most engaging tech sites, Slashdot.org! http://sdm.link/slashdot ___ robinhood-devel mailing list robinhood-de...@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/robinhood-devel -- Check out the vibrant tech community on one of the world's most engaging tech sites, Slashdot.org! http://sdm.link/slashdot___ robinhood-support mailing list robinhood-support@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/robinhood-support
[robinhood-support] Robinhood User Group 2017
Robinhood User Group 2017 = This year's Robinhood User Group will take place the afternoon before LAD[1], on Tuesday, October 3rd, 2017, in Paris. This meeting is the occasion for users, developers and vendors to share experiences and future plans about RobinHood Policy Engine. For more details about the event, see: https://github.com/cea-hpc/robinhood/wiki/RUG2017 Registration Even if it is co-located with LAD, organization of RUG is independent so you need to register separately to the 2 meetings. It makes it possible for us to plan enough room and food for participants. Registration form: https://rug2017.wufoo.com/forms/robinhood-user-group-registration-form/ Registration is free. Call for presentations == We invite attendees to submit a presentation when they register to the workshop (there is a dedicated field in the submission form). Typical presentation length is 20 to 30 min. Topics of interest include (but are not limited to): - Specific usages and implementations, site reports - Contributions, and annex tools - Performance and tunings (robinhood, database, kernel, filesystem...) - Dashboards, integration to site monitoring and accounting systems - Vendors integration and support Last year's presentations are available here: https://github.com/cea-hpc/robinhood/wiki/RUG2016#agenda--slide-decks See you soon in Paris! [1] https://www.eofs.eu/events/lad17 -- Check out the vibrant tech community on one of the world's most engaging tech sites, Slashdot.org! http://sdm.link/slashdot ___ robinhood-support mailing list robinhood-support@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/robinhood-support
