RASTELLI Alessandro
2015-Jan-07 14:15 UTC
[Gluster-users] Input/Output Error when deleting folder
Hi, we just did a clean reboot of the client. The config is as follows (2 bricks on each node): [root at gluster01-mi ~]# gluster volume info Volume Name: storage-recorder Type: Disperse Volume ID: 97587d68-3834-43cc-8b95-11996e013bf2 Status: Started Number of Bricks: 1 x (8 + 2) = 10 Transport-type: tcp Bricks: Brick1: gluster01-mi:/brick1/recorder Brick2: gluster01-mi:/brick2/recorder Brick3: gluster02-mi:/brick1/recorder Brick4: gluster02-mi:/brick2/recorder Brick5: gluster03-mi:/brick1/recorder Brick6: gluster03-mi:/brick2/recorder Brick7: gluster04-mi:/brick1/recorder Brick8: gluster04-mi:/brick2/recorder Brick9: gluster05-mi:/brick1/recorder Brick10: gluster05-mi:/brick2/recorder A. -----Original Message----- From: Xavier Hernandez [mailto:xhernandez at datalab.es] Sent: mercoled? 7 gennaio 2015 15:11 To: RASTELLI Alessandro Cc: gluster-users at gluster.org; CAZZANIGA Stefano; UBERTINI Gabriele; TECHNOLOGY - Supporto Sistemi OTT e Cloud; ORLANDO Luca Subject: Re: [Gluster-users] Input/Output Error when deleting folder Did you stopped the client or unmounted the volume while the application was still writing to it ? And what is the volume configuration ? (gluster volume info) Xavi On 01/07/2015 02:21 PM, RASTELLI Alessandro wrote:> Hi Xavier, > > nothing special happened to volumes and bricks, we just restarted the > client that writes into the folder Rec218. > > Before rebooting, the folder was OK. > > Thank you > > Alessandro > > *From:*Xavier Hernandez [mailto:xhernandez at datalab.es] > *Sent:* mercoled? 7 gennaio 2015 13:11 > *To:* RASTELLI Alessandro > *Cc:* gluster-users at gluster.org; CAZZANIGA Stefano; UBERTINI Gabriele; > TECHNOLOGY - Supporto Sistemi OTT e Cloud; ORLANDO Luca > *Subject:* Re: [Gluster-users] Input/Output Error when deleting folder > > Hi Alessandro, > > what is the volume configuration ? > did happen something special to the volume, bricks or that directory ? > did you directly removed or changed something in the bricks ? > did you replaced some brick ? > > Xavi > > On 01/07/2015 12:09 PM, RASTELLI Alessandro wrote: > > Hi, > > we encounter this error when I try to delete a folder on a > Gluster3.6.1 environment (dispersed volume): > > [2015-01-07 10:27:49.008999] W [fuse-bridge.c:483:fuse_entry_cbk] > 0-glusterfs-fuse: 10890: LOOKUP() /Rec218 => -1 (Input/output > error) > > [2015-01-07 10:27:49.009542] W [ec-common.c:164:ec_check_status] > 0-storage-recorder-disperse-0: Operation failed on some subvolumes > (up=3FF, mask=3FF, remaining=0, good=3CF, bad=30) > > [2015-01-07 10:27:50.326991] E > [ec-heal.c:656:ec_heal_prepare_others] > 0-storage-recorder-disperse-0: Don't know how to heal error 116 > > ls command gives the output: > > ?????????? ? ? ? ? ? Rec218 > > I can't do any operation on the folder (move, rename, delete) > > Can you please indicate how to fix? > > Thanks > > Alessandro > > > > > _______________________________________________ > > Gluster-users mailing list > > Gluster-users at gluster.org <mailto:Gluster-users at gluster.org> > > http://www.gluster.org/mailman/listinfo/gluster-users >
Xavier Hernandez
2015-Jan-07 14:22 UTC
[Gluster-users] Input/Output Error when deleting folder
Can you send me the result of the following command on all bricks ? getfattr -m. -e hex -d <brick path>/Rec218 On 01/07/2015 03:15 PM, RASTELLI Alessandro wrote:> Hi, > we just did a clean reboot of the client. > > The config is as follows (2 bricks on each node): > > [root at gluster01-mi ~]# gluster volume info > Volume Name: storage-recorder > Type: Disperse > Volume ID: 97587d68-3834-43cc-8b95-11996e013bf2 > Status: Started > Number of Bricks: 1 x (8 + 2) = 10 > Transport-type: tcp > Bricks: > Brick1: gluster01-mi:/brick1/recorder > Brick2: gluster01-mi:/brick2/recorder > Brick3: gluster02-mi:/brick1/recorder > Brick4: gluster02-mi:/brick2/recorder > Brick5: gluster03-mi:/brick1/recorder > Brick6: gluster03-mi:/brick2/recorder > Brick7: gluster04-mi:/brick1/recorder > Brick8: gluster04-mi:/brick2/recorder > Brick9: gluster05-mi:/brick1/recorder > Brick10: gluster05-mi:/brick2/recorder > > A. > > -----Original Message----- > From: Xavier Hernandez [mailto:xhernandez at datalab.es] > Sent: mercoled? 7 gennaio 2015 15:11 > To: RASTELLI Alessandro > Cc: gluster-users at gluster.org; CAZZANIGA Stefano; UBERTINI Gabriele; TECHNOLOGY - Supporto Sistemi OTT e Cloud; ORLANDO Luca > Subject: Re: [Gluster-users] Input/Output Error when deleting folder > > Did you stopped the client or unmounted the volume while the application was still writing to it ? > > And what is the volume configuration ? (gluster volume info) > > Xavi > > On 01/07/2015 02:21 PM, RASTELLI Alessandro wrote: >> Hi Xavier, >> >> nothing special happened to volumes and bricks, we just restarted the >> client that writes into the folder Rec218. >> >> Before rebooting, the folder was OK. >> >> Thank you >> >> Alessandro >> >> *From:*Xavier Hernandez [mailto:xhernandez at datalab.es] >> *Sent:* mercoled? 7 gennaio 2015 13:11 >> *To:* RASTELLI Alessandro >> *Cc:* gluster-users at gluster.org; CAZZANIGA Stefano; UBERTINI Gabriele; >> TECHNOLOGY - Supporto Sistemi OTT e Cloud; ORLANDO Luca >> *Subject:* Re: [Gluster-users] Input/Output Error when deleting folder >> >> Hi Alessandro, >> >> what is the volume configuration ? >> did happen something special to the volume, bricks or that directory ? >> did you directly removed or changed something in the bricks ? >> did you replaced some brick ? >> >> Xavi >> >> On 01/07/2015 12:09 PM, RASTELLI Alessandro wrote: >> >> Hi, >> >> we encounter this error when I try to delete a folder on a >> Gluster3.6.1 environment (dispersed volume): >> >> [2015-01-07 10:27:49.008999] W [fuse-bridge.c:483:fuse_entry_cbk] >> 0-glusterfs-fuse: 10890: LOOKUP() /Rec218 => -1 (Input/output >> error) >> >> [2015-01-07 10:27:49.009542] W [ec-common.c:164:ec_check_status] >> 0-storage-recorder-disperse-0: Operation failed on some subvolumes >> (up=3FF, mask=3FF, remaining=0, good=3CF, bad=30) >> >> [2015-01-07 10:27:50.326991] E >> [ec-heal.c:656:ec_heal_prepare_others] >> 0-storage-recorder-disperse-0: Don't know how to heal error 116 >> >> ls command gives the output: >> >> ?????????? ? ? ? ? ? Rec218 >> >> I can't do any operation on the folder (move, rename, delete) >> >> Can you please indicate how to fix? >> >> Thanks >> >> Alessandro >> >> >> >> >> _______________________________________________ >> >> Gluster-users mailing list >> >> Gluster-users at gluster.org <mailto:Gluster-users at gluster.org> >> >> http://www.gluster.org/mailman/listinfo/gluster-users >>