Re: [ceph-users] CephFS client issue
Hello, On Tue, 16 Jun 2015 07:21:54 + Matteo Dacrema wrote: Hi, I've shutoff the node without take any cautions for simulate a real case. Normal shutdown (as opposed to simulating a crash by pulling cables) should not result in any delays due to Ceph timeouts. The osd_pool_default_min_size is 2 . This on the other is most likely your problem. It would have to be 1 for things to work in your case. Verify it with ceph osd pool get poolname min_size for your actual pool(s). Christian Regards, Matteo Da: Christian Balzer ch...@gol.com Inviato: martedì 16 giugno 2015 01:44 A: ceph-users Cc: Matteo Dacrema Oggetto: Re: [ceph-users] CephFS client issue Hello, On Mon, 15 Jun 2015 23:11:07 + Matteo Dacrema wrote: With 3.16.3 kernel it seems to be stable but I've discovered one new issue. If I take down one of the two osd node all the client stop to respond. How did you take the node down? What is your osd_pool_default_min_size? Penultimately, you wouldn't deploy a cluster with just 2 storage nodes in production anyway. Christian Here the output of ceph -s ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN 256 pgs degraded 127 pgs stuck inactive 127 pgs stuck unclean 256 pgs undersized recovery 1457662/2915324 objects degraded (50.000%) 4/8 in osds are down clock skew detected on mon.cephmds01, mon.ceph-mon1 monmap e5: 3 mons at {ceph-mon1=10.29.81.184:6789/0,cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 64, quorum 0,1,2 cephmds02,cephmds01,ceph-mon1 mdsmap e176: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e712: 8 osds: 4 up, 8 in pgmap v420651: 256 pgs, 2 pools, 133 GB data, 1423 kobjects 289 GB used, 341 GB / 631 GB avail 1457662/2915324 objects degraded (50.000%) 256 undersized+degraded+peered client io 86991 B/s wr, 0 op/s When I take UP the node all clients resume to work. Thanks, Matteo ? Da: ceph-users ceph-users-boun...@lists.ceph.com per conto di Matteo Dacrema mdacr...@enter.it Inviato: luned? 15 giugno 2015 12:37 A: John Spray; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo Da: John Spray john.sp...@redhat.com Inviato: luned? 15 giugno 2015 10:51 A: Matteo Dacrema; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=DBA3140262.AE1FB Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=DBA3140262.AE1FB -- Christian BalzerNetwork/Systems Engineer ch...@gol.com Global OnLine Japan/Fusion Communications http://www.gol.com/ -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Seguire il link qui sotto per segnalarlo come spam: http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=03A5340264.ADC79 -- Christian BalzerNetwork/Systems Engineer ch...@gol.com Global OnLine Japan/Fusion Communications http://www.gol.com/ ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
Hi, I've shutoff the node without take any cautions for simulate a real case. The osd_pool_default_min_size is 2 . Regards, Matteo Da: Christian Balzer ch...@gol.com Inviato: martedì 16 giugno 2015 01:44 A: ceph-users Cc: Matteo Dacrema Oggetto: Re: [ceph-users] CephFS client issue Hello, On Mon, 15 Jun 2015 23:11:07 + Matteo Dacrema wrote: With 3.16.3 kernel it seems to be stable but I've discovered one new issue. If I take down one of the two osd node all the client stop to respond. How did you take the node down? What is your osd_pool_default_min_size? Penultimately, you wouldn't deploy a cluster with just 2 storage nodes in production anyway. Christian Here the output of ceph -s ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN 256 pgs degraded 127 pgs stuck inactive 127 pgs stuck unclean 256 pgs undersized recovery 1457662/2915324 objects degraded (50.000%) 4/8 in osds are down clock skew detected on mon.cephmds01, mon.ceph-mon1 monmap e5: 3 mons at {ceph-mon1=10.29.81.184:6789/0,cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 64, quorum 0,1,2 cephmds02,cephmds01,ceph-mon1 mdsmap e176: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e712: 8 osds: 4 up, 8 in pgmap v420651: 256 pgs, 2 pools, 133 GB data, 1423 kobjects 289 GB used, 341 GB / 631 GB avail 1457662/2915324 objects degraded (50.000%) 256 undersized+degraded+peered client io 86991 B/s wr, 0 op/s When I take UP the node all clients resume to work. Thanks, Matteo ? Da: ceph-users ceph-users-boun...@lists.ceph.com per conto di Matteo Dacrema mdacr...@enter.it Inviato: luned? 15 giugno 2015 12:37 A: John Spray; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo Da: John Spray john.sp...@redhat.com Inviato: luned? 15 giugno 2015 10:51 A: Matteo Dacrema; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=DBA3140262.AE1FB Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=DBA3140262.AE1FB -- Christian BalzerNetwork/Systems Engineer ch...@gol.com Global OnLine Japan/Fusion Communications http://www.gol.com/ -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Seguire il link qui sotto per segnalarlo come spam: http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=03A5340264.ADC79 ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
Hello, you're right. I misunderstood the meaning of the two configuration params: size and min_size. Now it works correctly. Thanks, Matteo Da: Christian Balzer ch...@gol.com Inviato: martedì 16 giugno 2015 09:42 A: ceph-users Cc: Matteo Dacrema Oggetto: Re: [ceph-users] CephFS client issue Hello, On Tue, 16 Jun 2015 07:21:54 + Matteo Dacrema wrote: Hi, I've shutoff the node without take any cautions for simulate a real case. Normal shutdown (as opposed to simulating a crash by pulling cables) should not result in any delays due to Ceph timeouts. The osd_pool_default_min_size is 2 . This on the other is most likely your problem. It would have to be 1 for things to work in your case. Verify it with ceph osd pool get poolname min_size for your actual pool(s). Christian Regards, Matteo Da: Christian Balzer ch...@gol.com Inviato: martedì 16 giugno 2015 01:44 A: ceph-users Cc: Matteo Dacrema Oggetto: Re: [ceph-users] CephFS client issue Hello, On Mon, 15 Jun 2015 23:11:07 + Matteo Dacrema wrote: With 3.16.3 kernel it seems to be stable but I've discovered one new issue. If I take down one of the two osd node all the client stop to respond. How did you take the node down? What is your osd_pool_default_min_size? Penultimately, you wouldn't deploy a cluster with just 2 storage nodes in production anyway. Christian Here the output of ceph -s ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN 256 pgs degraded 127 pgs stuck inactive 127 pgs stuck unclean 256 pgs undersized recovery 1457662/2915324 objects degraded (50.000%) 4/8 in osds are down clock skew detected on mon.cephmds01, mon.ceph-mon1 monmap e5: 3 mons at {ceph-mon1=10.29.81.184:6789/0,cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 64, quorum 0,1,2 cephmds02,cephmds01,ceph-mon1 mdsmap e176: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e712: 8 osds: 4 up, 8 in pgmap v420651: 256 pgs, 2 pools, 133 GB data, 1423 kobjects 289 GB used, 341 GB / 631 GB avail 1457662/2915324 objects degraded (50.000%) 256 undersized+degraded+peered client io 86991 B/s wr, 0 op/s When I take UP the node all clients resume to work. Thanks, Matteo ? Da: ceph-users ceph-users-boun...@lists.ceph.com per conto di Matteo Dacrema mdacr...@enter.it Inviato: luned? 15 giugno 2015 12:37 A: John Spray; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo Da: John Spray john.sp...@redhat.com Inviato: luned? 15 giugno 2015 10:51 A: Matteo Dacrema; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=DBA3140262.AE1FB Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=DBA3140262.AE1FB -- Christian BalzerNetwork/Systems Engineer ch...@gol.com Global OnLine Japan/Fusion Communications http://www.gol.com/ -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Seguire il link qui sotto per segnalarlo come spam: http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=03A5340264.ADC79 -- Christian BalzerNetwork/Systems Engineer ch...@gol.com Global OnLine Japan/Fusion Communications http://www.gol.com/ -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Seguire il link qui sotto per segnalarlo come spam: http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=3049340267.ACFBA ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
That's expected behaviour. If RADOS can't make your writes safe by replicating them (because no other OSD is available) then clients will pause their writes. See the min_size setting on a pool. John On 16/06/2015 00:11, Matteo Dacrema wrote: With 3.16.3 kernel it seems to be stable but I've discovered one new issue. If I take down one of the two osd node all the client stop to respond. Here the output of ceph -s ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN 256 pgs degraded 127 pgs stuck inactive 127 pgs stuck unclean 256 pgs undersized recovery 1457662/2915324 objects degraded (50.000%) 4/8 in osds are down clock skew detected on mon.cephmds01, mon.ceph-mon1 monmap e5: 3 mons at {ceph-mon1=10.29.81.184:6789/0,cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 64, quorum 0,1,2 cephmds02,cephmds01,ceph-mon1 mdsmap e176: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e712: 8 osds: 4 up, 8 in pgmap v420651: 256 pgs, 2 pools, 133 GB data, 1423 kobjects 289 GB used, 341 GB / 631 GB avail 1457662/2915324 objects degraded (50.000%) 256 undersized+degraded+peered client io 86991 B/s wr, 0 op/s When I take UP the node all clients resume to work. Thanks, Matteo *Da:* ceph-users ceph-users-boun...@lists.ceph.com per conto di Matteo Dacrema mdacr...@enter.it *Inviato:* lunedì 15 giugno 2015 12:37 *A:* John Spray; Lincoln Bryant; ceph-users *Oggetto:* Re: [ceph-users] CephFS client issue Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo *Da:* John Spray john.sp...@redhat.com *Inviato:* lunedì 15 giugno 2015 10:51 *A:* Matteo Dacrema; Lincoln Bryant; ceph-users *Oggetto:* Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam. http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklist http://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam. http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=DBA3140262.AE1FB Clicca qui per metterlo in blacklist http://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=DBA3140262.AE1FB ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo Da: John Spray john.sp...@redhat.com Inviato: luned? 15 giugno 2015 10:51 A: Matteo Dacrema; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
With 3.16.3 kernel it seems to be stable but I've discovered one new issue. If I take down one of the two osd node all the client stop to respond. Here the output of ceph -s ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN 256 pgs degraded 127 pgs stuck inactive 127 pgs stuck unclean 256 pgs undersized recovery 1457662/2915324 objects degraded (50.000%) 4/8 in osds are down clock skew detected on mon.cephmds01, mon.ceph-mon1 monmap e5: 3 mons at {ceph-mon1=10.29.81.184:6789/0,cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 64, quorum 0,1,2 cephmds02,cephmds01,ceph-mon1 mdsmap e176: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e712: 8 osds: 4 up, 8 in pgmap v420651: 256 pgs, 2 pools, 133 GB data, 1423 kobjects 289 GB used, 341 GB / 631 GB avail 1457662/2915324 objects degraded (50.000%) 256 undersized+degraded+peered client io 86991 B/s wr, 0 op/s When I take UP the node all clients resume to work. Thanks, Matteo ? Da: ceph-users ceph-users-boun...@lists.ceph.com per conto di Matteo Dacrema mdacr...@enter.it Inviato: luned? 15 giugno 2015 12:37 A: John Spray; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo Da: John Spray john.sp...@redhat.com Inviato: luned? 15 giugno 2015 10:51 A: Matteo Dacrema; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=DBA3140262.AE1FB Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=DBA3140262.AE1FB ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
Hello, On Mon, 15 Jun 2015 23:11:07 + Matteo Dacrema wrote: With 3.16.3 kernel it seems to be stable but I've discovered one new issue. If I take down one of the two osd node all the client stop to respond. How did you take the node down? What is your osd_pool_default_min_size? Penultimately, you wouldn't deploy a cluster with just 2 storage nodes in production anyway. Christian Here the output of ceph -s ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN 256 pgs degraded 127 pgs stuck inactive 127 pgs stuck unclean 256 pgs undersized recovery 1457662/2915324 objects degraded (50.000%) 4/8 in osds are down clock skew detected on mon.cephmds01, mon.ceph-mon1 monmap e5: 3 mons at {ceph-mon1=10.29.81.184:6789/0,cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 64, quorum 0,1,2 cephmds02,cephmds01,ceph-mon1 mdsmap e176: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e712: 8 osds: 4 up, 8 in pgmap v420651: 256 pgs, 2 pools, 133 GB data, 1423 kobjects 289 GB used, 341 GB / 631 GB avail 1457662/2915324 objects degraded (50.000%) 256 undersized+degraded+peered client io 86991 B/s wr, 0 op/s When I take UP the node all clients resume to work. Thanks, Matteo ? Da: ceph-users ceph-users-boun...@lists.ceph.com per conto di Matteo Dacrema mdacr...@enter.it Inviato: luned? 15 giugno 2015 12:37 A: John Spray; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue Ok, I'll update kernel to 3.16.3 version and let you know. Thanks, Matteo Da: John Spray john.sp...@redhat.com Inviato: luned? 15 giugno 2015 10:51 A: Matteo Dacrema; Lincoln Bryant; ceph-users Oggetto: Re: [ceph-users] CephFS client issue On 14/06/15 20:00, Matteo Dacrema wrote: Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? That's old by CephFS standards. It's likely that the issue you're seeing is one of the known bugs (which were actually the motivation for adding the warning message you're seeing). John -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=637D840263.A210F Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=637D840263.A210F -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=DBA3140262.AE1FB Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=DBA3140262.AE1FB -- Christian BalzerNetwork/Systems Engineer ch...@gol.com Global OnLine Japan/Fusion Communications http://www.gol.com/ ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
Hi Lincoln, I'm using the kernel client. Kernel version is: 3.13.0-53-generic? Thanks, Matteo Da: Lincoln Bryant linco...@uchicago.edu Inviato: domenica 14 giugno 2015 19:31 A: Matteo Dacrema; ceph-users Oggetto: Re: [ceph-users] CephFS client issue Hi Matteo, Are your clients using the FUSE client or the kernel client? If the latter, what kernel version? --Lincoln On 6/14/2015 10:26 AM, Matteo Dacrema wrote: ?Hi all, I'm using CephFS on Hammer and sometimes I need to reboot one or more clients because , as ceph -s tells me, it's failing to respond to capability release.After tha?t all clients stop to respond: can't access files or mount/umont cephfs. I've 1.5 million files , 2 metadata servers in active/standby configuration with 8 GB of RAM , 20 clients with 2 GB of RAM each and 2 OSD nodes with 4 80GB osd and 4GB of RAM. Here my configuration: [global] fsid = 2de7b17f-0a3e-4109-b878-c035dd2f7735 mon_initial_members = cephmds01 mon_host = 10.29.81.161 auth_cluster_required = cephx auth_service_required = cephx auth_client_required = cephx public network = 10.29.81.0/24 tcp nodelay = true tcp rcvbuf = 0 ms tcp read timeout = 600 #Capacity mon osd full ratio = .95 mon osd nearfull ratio = .85 [osd] osd journal size = 1024 journal dio = true journal aio = true osd op threads = 2 osd op thread timeout = 60 osd disk threads = 2 osd recovery threads = 1 osd recovery max active = 1 osd max backfills = 2 # Pool osd pool default size = 2 #XFS osd mkfs type = xfs osd mkfs options xfs = -f -i size=2048 osd mount options xfs = rw,noatime,inode64,logbsize=256k,delaylog #FileStore Settings filestore xattr use omap = false filestore max inline xattr size = 512 filestore max sync interval = 10 filestore merge threshold = 40 filestore split multiple = 8 filestore flusher = false filestore queue max ops = 2000 filestore queue max bytes = 536870912 filestore queue committing max ops = 500 filestore queue committing max bytes = 268435456 filestore op threads = 2 [mds] max mds = 1 mds cache size = 75 client cache size = 2048 mds dir commit ratio = 0.5 Here ceph -s output: root@service-new:~# ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN mds0: Client 94102 failing to respond to cache pressure monmap e2: 2 mons at {cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 34, quorum 0,1 cephmds02,cephmds01 mdsmap e79: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e669: 8 osds: 8 up, 8 in pgmap v339741: 256 pgs, 2 pools, 132 GB data, 1417 kobjects 288 GB used, 342 GB / 631 GB avail 256 active+clean client io 3091 kB/s rd, 342 op/s Thank you. Regards, Matteo ___ ceph-users mailing list ceph-users@lists.ceph.commailto:ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Questo messaggio e' stato analizzato con Libra ESVA ed e' risultato non infetto. Clicca qui per segnalarlo come spam.http://esva01.enter.it/cgi-bin/learn-msg.cgi?id=4F9DA41B1A.A3369 Clicca qui per metterlo in blacklisthttp://esva01.enter.it/cgi-bin/learn-msg.cgi?blacklist=1id=4F9DA41B1A.A3369 ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS client issue
Hi Matteo, Are your clients using the FUSE client or the kernel client? If the latter, what kernel version? --Lincoln On 6/14/2015 10:26 AM, Matteo Dacrema wrote: ?Hi all, I'm using CephFS on Hammer and sometimes I need to reboot one or more clients because , as ceph -s tells me, it's failing to respond to capability release.After tha?t all clients stop to respond: can't access files or mount/umont cephfs. I've 1.5 million files , 2 metadata servers in active/standby configuration with 8 GB of RAM , 20 clients with 2 GB of RAM each and 2 OSD nodes with 4 80GB osd and 4GB of RAM. Here my configuration: [global] fsid = 2de7b17f-0a3e-4109-b878-c035dd2f7735 mon_initial_members = cephmds01 mon_host = 10.29.81.161 auth_cluster_required = cephx auth_service_required = cephx auth_client_required = cephx public network = 10.29.81.0/24 tcp nodelay = true tcp rcvbuf = 0 ms tcp read timeout = 600 #Capacity mon osd full ratio = .95 mon osd nearfull ratio = .85 [osd] osd journal size = 1024 journal dio = true journal aio = true osd op threads = 2 osd op thread timeout = 60 osd disk threads = 2 osd recovery threads = 1 osd recovery max active = 1 osd max backfills = 2 # Pool osd pool default size = 2 #XFS osd mkfs type = xfs osd mkfs options xfs = -f -i size=2048 osd mount options xfs = rw,noatime,inode64,logbsize=256k,delaylog #FileStore Settings filestore xattr use omap = false filestore max inline xattr size = 512 filestore max sync interval = 10 filestore merge threshold = 40 filestore split multiple = 8 filestore flusher = false filestore queue max ops = 2000 filestore queue max bytes = 536870912 filestore queue committing max ops = 500 filestore queue committing max bytes = 268435456 filestore op threads = 2 [mds] max mds = 1 mds cache size = 75 client cache size = 2048 mds dir commit ratio = 0.5 Here ceph -s output: root@service-new:~# ceph -s cluster 2de7b17f-0a3e-4109-b878-c035dd2f7735 health HEALTH_WARN mds0: Client 94102 failing to respond to cache pressure monmap e2: 2 mons at {cephmds01=10.29.81.161:6789/0,cephmds02=10.29.81.160:6789/0} election epoch 34, quorum 0,1 cephmds02,cephmds01 mdsmap e79: 1/1/1 up {0=cephmds01=up:active}, 1 up:standby osdmap e669: 8 osds: 8 up, 8 in pgmap v339741: 256 pgs, 2 pools, 132 GB data, 1417 kobjects 288 GB used, 342 GB / 631 GB avail 256 active+clean client io 3091 kB/s rd, 342 op/s Thank you. Regards, Matteo ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com