<div dir="ltr"><div dir="ltr">Hi Mauro,<div><br></div><div><br></div><div>The rebalance code started using fallocate in 3.10.5 (<a href="https://bugzilla.redhat.com/show_bug.cgi?id=1473132">https://bugzilla.redhat.com/show_bug.cgi?id=1473132</a>) which works fine on replicated volumes. However, we neglected to test this with EC volumes on 3.10. Once we discovered the issue, the EC fallocate implementation was made available in 3.11.</div><div><br></div><div>At this point, I&#39;m afraid the only option I see is to upgrade to at least 3.12.</div><div><br></div><div>@Sunil, do you have anything to add?</div><div><br></div><div>Regards,</div><div>Nithya</div></div></div><div class="gmail_extra"><br><div class="gmail_quote">On 13 September 2018 at 18:34, Mauro Tridici <span dir="ltr">&lt;<a href="mailto:mauro.tridici@cmcc.it" target="_blank">mauro.tridici@cmcc.it</a>&gt;</span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><div><br></div><div>Hi Nithya,</div><div><br></div><div>thank you for involving EC group.</div><div>I will wait for your suggestions.</div><div><br></div><div>Regards,</div><div>Mauro</div><div><div class="h5"><br><div><blockquote type="cite"><div>Il giorno 13 set 2018, alle ore 13:38, Nithya Balachandran &lt;<a href="mailto:nbalacha@redhat.com" target="_blank">nbalacha@redhat.com</a>&gt; ha scritto:</div><br class="m_821703117890918883Apple-interchange-newline"><div><div dir="ltr">This looks like an issue because rebalance switched to using fallocate which EC did not have implemented at that point.<div><br></div><div>@Pranith, @Ashish, which version of gluster had support for fallocate in EC?</div><div><br></div><div><br></div><div>Regards,</div><div>Nithya</div></div><div class="gmail_extra"><br><div class="gmail_quote">On 12 September 2018 at 19:24, Mauro Tridici <span dir="ltr">&lt;<a href="mailto:mauro.tridici@cmcc.it" target="_blank">mauro.tridici@cmcc.it</a>&gt;</span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><div><div>Dear All,</div><div><br></div><div>I recently added 3 servers (each one with 12 bricks) to an existing Gluster Distributed Disperse Volume.</div><div>Volume extension has been completed without error and I already executed the rebalance procedure with fix-layout option with no problem.</div><div>I just launched the rebalance procedure without fix-layout option, but, as you can see in the output below, I noticed that some failures have been detected.</div><div><br></div><div><font face="Courier" size="2">[root@s01 glusterfs]# gluster v rebalance tier2 status</font></div><div><font face="Courier" size="2">                                    Node Rebalanced-files          size       scanned      failures       skipped               status  run time in h:m:s</font></div><div><font face="Courier" size="2">                               ---------      -----------   -----------   -----------   -----------   -----------         ------------     --------------</font></div><div><font face="Courier" size="2">                               localhost            71176         3.2MB       2137557       1530391          8128          in progress       13:59:05</font></div><div><font face="Courier" size="2">                                 s02-stg                0        0Bytes             0             0             0            completed       11:53:28</font></div><div><font face="Courier" size="2">                                 s03-stg                0        0Bytes             0             0             0            completed       11:53:32</font></div><div><font face="Courier" size="2">                                 s04-stg                0        0Bytes             0             0             0            completed        0:00:06</font></div><div><font face="Courier" size="2">                                 s05-stg               15        0Bytes         17055             0            18            completed       10:48:01</font></div><div><font face="Courier" size="2">                                 s06-stg                0        0Bytes             0             0             0            completed        0:00:06</font></div><div><font face="Courier" size="2">Estimated time left for rebalance to complete :        0:46:53</font></div><div><font face="Courier" size="2">volume rebalance: tier2: success</font></div><div><br></div><div>In the volume rebalance log file, I detected a lot of error messages similar to the following ones:</div><div><br></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.756703] E [MSGID: 0] [dht-rebalance.c:1696:dht_migr<wbr>ate_file] 0-tier2-dht: Create dst failed on - tier2-disperse-6 for file - /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2005-12_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2005-12_grid<wbr>.nc</a></font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.757025] E [MSGID: 109023] [dht-rebalance.c:2733:gf_defra<wbr>g_migrate_single_file] 0-tier2-dht: migrate-data failed for /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2005-12_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2005-12_grid<wbr>.nc</a></font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.759183] E [MSGID: 109023] [dht-rebalance.c:844:__dht_reb<wbr>alance_create_dst_file] 0-tier2-dht: fallocate failed for /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2005-09_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2005-09_grid<wbr>.nc</a> on tier2-disperse-9 (Operation not supported)</font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.759206] E [MSGID: 0] [dht-rebalance.c:1696:dht_migr<wbr>ate_file] 0-tier2-dht: Create dst failed on - tier2-disperse-9 for file - /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2005-09_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2005-09_grid<wbr>.nc</a></font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.759536] E [MSGID: 109023] [dht-rebalance.c:2733:gf_defra<wbr>g_migrate_single_file] 0-tier2-dht: migrate-data failed for /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2005-09_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2005-09_grid<wbr>.nc</a></font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.777219] E [MSGID: 109023] [dht-rebalance.c:844:__dht_reb<wbr>alance_create_dst_file] 0-tier2-dht: fallocate failed for /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2006-01_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2006-01_grid<wbr>.nc</a> on tier2-disperse-10 (Operation not supported)</font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.777241] E [MSGID: 0] [dht-rebalance.c:1696:dht_migr<wbr>ate_file] 0-tier2-dht: Create dst failed on - tier2-disperse-10 for file - /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2006-01_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2006-01_grid<wbr>.nc</a></font></div><div><font face="Courier" size="2">[2018-09-12 13:15:50.777676] E [MSGID: 109023] [dht-rebalance.c:2733:gf_defra<wbr>g_migrate_single_file] 0-tier2-dht: migrate-data failed for /CSP/sp1/CESM/archive/sps_2005<wbr>08_003/atm/hist/postproc/<a href="http://sps_200508_003.cam.h0.2006-01_grid.nc/" target="_blank">sps_<wbr>200508_003.cam.h0.2006-01_grid<wbr>.nc</a></font></div><div><br></div><div>Could you please help me to understand what is happening and how to solve it?</div><div><br></div><div>Our Gluster implementation is based on Gluster v.3.10.5</div><div><br></div><div>Thank you in advance,</div><div>Mauro</div>
</div>
<br></div><br>______________________________<wbr>_________________<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" rel="noreferrer" target="_blank">https://lists.gluster.org/mail<wbr>man/listinfo/gluster-users</a><br></blockquote></div><br></div>
</div></blockquote></div><br></div></div><div>
<span class="m_821703117890918883Apple-style-span" style="border-collapse:separate;color:rgb(0,0,0);font-family:Helvetica;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-align:-webkit-auto;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px"><span class="m_821703117890918883Apple-style-span" style="border-collapse:separate;color:rgb(0,0,0);font-family:Helvetica;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-align:-webkit-auto;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px"><div><br class="m_821703117890918883Apple-interchange-newline">-------------------------</div><div>Mauro Tridici</div><div><br></div><div>Fondazione CMCC</div><div>CMCC Supercomputing Center</div><div>presso Complesso Ecotekne - Università del Salento -</div><div>Strada Prov.le Lecce - Monteroni sn</div><div>73100 Lecce  IT</div><div><a href="http://www.cmcc.it" target="_blank">http://www.cmcc.it</a></div><div><br></div><div>mobile: (+39) 327 5630841</div><div>email: <a href="mailto:mauro.tridici@cmcc.it" target="_blank">mauro.tridici@cmcc.it</a></div></span></span>
</div>
<br></div></blockquote></div><br></div>