I've got configuration which in simple includes combination of afrs and
unify - servers exports n[1-3]-brick[12] and n[1-3]-ns and client got
cluster configuration:
volume afr-ns
type cluster/afr
subvolumes n1-ns n2-ns n3-ns
option data-self-heal on
option metadata-self-heal on
option entry-self-heal on
end-volume
volume afr1
type cluster/afr
subvolumes n1-brick2 n2-brick1
option data-self-heal on
option metadata-self-heal on
option entry-self-heal on
end-volume
volume afr2
type cluster/afr
subvolumes n2-brick2 n3-brick1
option data-self-heal on
option metadata-self-heal on
option entry-self-heal on
end-volume
volume unify
type cluster/unify
subvolumes afr1 afr2
option namespace afr-ns
option scheduler rr
end-volume
Unify is mounted on n3 (which is also a client) under /storage where
I've created directory and file:
n3:/storage# mkdir test
n3:/storage# cd test
n3:/storage/test# date > file
After I turned off n2, file was removed and I've checkd some attrs:
n3:/storage/test# getfattr -R -d -m ".*" /export/storage?/*
getfattr: Removing leading '/' from absolute path names
# file: export/storage1/brick
trusted.glusterfs.afr.entry-pending=0sAAAAAAAAAAAtrusted.glusterfs.test="working\000"
# file: export/storage1/ns
trusted.glusterfs.afr.entry-pending=0sAAAAAAAAAAAAAAAA
trusted.glusterfs.test="working\000"
# file: export/storage1/ns/test
trusted.glusterfs.afr.entry-pending=0sAAAAAAAAAAEAAAAA
# file: export/storage2/brick
trusted.glusterfs.test="working\000"
Then n2 was bring back, and after a while I was able to cat file:
n3:/storage/test# cat file
Wed Dec 10 16:59:00 CET 2008
n3:/storage/test# getfattr -R -d -m ".*" /export/storage?/*
getfattr: Removing leading '/' from absolute path names
# file: export/storage1/brick
trusted.glusterfs.afr.entry-pending=0sAAAAAAAAAAAtrusted.glusterfs.test="working\000"
# file: export/storage1/ns
trusted.glusterfs.afr.entry-pending=0sAAAAAAAAAAAAAAAA
trusted.glusterfs.test="working\000"
# file: export/storage1/ns/test
trusted.glusterfs.afr.entry-pending=0sAAAAAAAAAAEAAAAA
# file: export/storage1/ns/test/file
trusted.glusterfs.afr.data-pending=0sAAAAAAAAAAAAAAAA
trusted.glusterfs.afr.metadata-pending=0sAAAAAAAAAAAAAAAA
# file: export/storage2/brick
trusted.glusterfs.test="working\000"
I don't know why file was recreated. I've tasted without *-self-heal
options and the result was the same. Maybe using io-cache complicates
this issue (which is configured on both sides - server and client)? Has
anyone solution for this case?
Regards.
--
rash at konto pl
Anand Avati
2008-Dec-10 19:25 UTC
[Gluster-users] AFR healing problem after returning one node.
> I don't know why file was recreated. I've tasted without *-self-heal > options and the result was the same. Maybe using io-cache complicates > this issue (which is configured on both sides - server and client)? Has > anyone solution for this case? >Can you tell us the results of first performing an ls on the directory and then cat the file? thanks, avati
?ro, 10 gru 2008, 17:16:33 +0100, Rash napisa?(a):> I've got configuration which in simple includes combination of afrs and > unify - servers exports n[1-3]-brick[12] and n[1-3]-nsI forget to tell that my version of glusterfs is 1.4.0pre13. -- rash at konto pl
Raghavendra G
2008-Dec-11 10:54 UTC
[Gluster-users] Fwd: AFR healing problem after returning one node.
sending to gluster-users. ---------- Forwarded message ---------- From: Raghavendra G <raghavendra.hg at gmail.com> Date: 2008/12/11 Subject: Re: [Gluster-users] AFR healing problem after returning one node. To: Rash <rash at konto.pl> Hi Rash, self heal is triggered when a lookup from pathname to inode happens. Both ls and cat file dont result in lookup on the directoy test. Hence self-heal is not perfromed. Can you try the following sequence of commands on client? /home/raghu/mnt/# ls file /home/raghu/mnt # rm file /home/raghu/mnt #cd ../ /home/raghu # ls mnt/ when you cd to parent directory, lookup happens on mnt and self heal should work. regards, 2008/12/11 Rash <rash at konto.pl> czw, 11 gru 2008, 08:31:16 +0100, Rash napisa?(a):> > ?ro, 10 gru 2008, 17:16:33 +0100, Rash napisa?(a): > > > I've got configuration which in simple includes combination of afrs and > > > unify - servers exports n[1-3]-brick[12] and n[1-3]-ns > > I forget to tell that my version of glusterfs is 1.4.0pre13. > > There is debug log on moment when file is deleted, one node is back, and > cat file had been performed: > > 2008-12-11 11:26:15 D [inode.c:280:__inode_activate] fuse/inode: activating > inode(11157510), lru=0/0 active=2 purge=0 > 2008-12-11 11:26:15 D [fuse-bridge.c:610:fuse_getattr] glusterfs-fuse: 170: > GETATTR 11157510 (/a) > 2008-12-11 11:26:15 D [fuse-bridge.c:530:fuse_attr_cbk] glusterfs-fuse: > 170: STAT() /a => 11157510 > 2008-12-11 11:26:15 D [inode.c:299:__inode_passivate] fuse/inode: > passivating inode(11157510) lru=1/0 active=1 purge=0 > 2008-12-11 11:26:15 D [inode.c:280:__inode_activate] fuse/inode: activating > inode(11157510), lru=0/0 active=2 purge=0 > 2008-12-11 11:26:15 D [fuse-bridge.c:463:fuse_lookup] glusterfs-fuse: 171: > LOOKUP /a/file > 2008-12-11 11:26:15 D [inode.c:455:__inode_create] fuse/inode: create > inode(0) > 2008-12-11 11:26:15 D [inode.c:280:__inode_activate] fuse/inode: activating > inode(0), lru=0/0 active=3 purge=0 > 2008-12-11 11:26:15 W [afr-self-heal-common.c:955:afr_self_heal] afr1: > performing self heal on /a/file (metadata=1 data=1 entry=1) > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:910:afr_self_heal_missing_entries] afr1: attempting > to recreate missing entries for path=/a/file > 2008-12-11 11:26:15 W [afr-self-heal-common.c:955:afr_self_heal] afr-ns: > performing self heal on /a/file (metadata=1 data=1 entry=1) > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:910:afr_self_heal_missing_entries] afr-ns: > attempting to recreate missing entries for path=/a/file > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:851:sh_missing_entries_lookup] afr1: looking up > /a/file on subvolume n1-brick2 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:851:sh_missing_entries_lookup] afr1: looking up > /a/file on subvolume n2-brick1 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:851:sh_missing_entries_lookup] afr-ns: looking up > /a/file on subvolume n1-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:851:sh_missing_entries_lookup] afr-ns: looking up > /a/file on subvolume n2-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:851:sh_missing_entries_lookup] afr-ns: looking up > /a/file on subvolume n3-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:808:sh_missing_entries_lookup_cbk] afr1: path > /a/file on subvolume n2-brick1 is of mode 0100644 > 2008-12-11 11:26:15 W > [afr-self-heal-common.c:816:sh_missing_entries_lookup_cbk] afr1: path > /a/file on subvolume n1-brick2 => -1 (No such file or directory) > 2008-12-11 11:26:15 D [afr-self-heal-common.c:551:sh_missing_entries_mknod] > afr1: mknod /a/file mode 0100644 on 1 subvolumes > 2008-12-11 11:26:15 W > [afr-self-heal-common.c:816:sh_missing_entries_lookup_cbk] afr-ns: path > /a/file on subvolume n3-ns => -1 (No such file or directory) > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:808:sh_missing_entries_lookup_cbk] afr-ns: path > /a/file on subvolume n2-ns is of mode 0100644 > 2008-12-11 11:26:15 W > [afr-self-heal-common.c:816:sh_missing_entries_lookup_cbk] afr-ns: path > /a/file on subvolume n1-ns => -1 (No such file or directory) > 2008-12-11 11:26:15 D [afr-self-heal-common.c:551:sh_missing_entries_mknod] > afr-ns: mknod /a/file mode 0100644 on 2 subvolumes > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:499:sh_missing_entries_newentry_cbk] afr-ns: chown > /a/file to 0 0 on subvolume n3-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:499:sh_missing_entries_newentry_cbk] afr1: chown > /a/file to 0 0 on subvolume n1-brick2 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:446:sh_missing_entries_finish] afr1: unlocking > 11157510/file on subvolume n1-brick2 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:446:sh_missing_entries_finish] afr1: unlocking > 11157510/file on subvolume n2-brick1 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:499:sh_missing_entries_newentry_cbk] afr-ns: chown > /a/file to 0 0 on subvolume n1-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:446:sh_missing_entries_finish] afr-ns: unlocking > 11157510/file on subvolume n1-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:446:sh_missing_entries_finish] afr-ns: unlocking > 11157510/file on subvolume n2-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:446:sh_missing_entries_finish] afr-ns: unlocking > 11157510/file on subvolume n3-ns > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:386:afr_sh_missing_entries_done] afr1: proceeding to > metadata check on /a/file > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:709:afr_sh_metadata_lock] > afr1: locking /a/file on subvolume n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:709:afr_sh_metadata_lock] > afr1: locking /a/file on subvolume n2-brick1 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:386:afr_sh_missing_entries_done] afr-ns: proceeding > to metadata check on /a/file > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:709:afr_sh_metadata_lock] > afr-ns: locking /a/file on subvolume n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:709:afr_sh_metadata_lock] > afr-ns: locking /a/file on subvolume n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:709:afr_sh_metadata_lock] > afr-ns: locking /a/file on subvolume n3-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:643:afr_sh_metadata_lookup] > afr1: looking up /a/file on n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:643:afr_sh_metadata_lookup] > afr1: looking up /a/file on n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:643:afr_sh_metadata_lookup] > afr-ns: looking up /a/file on n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:643:afr_sh_metadata_lookup] > afr-ns: looking up /a/file on n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:643:afr_sh_metadata_lookup] > afr-ns: looking up /a/file on n3-ns > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:598:afr_sh_metadata_lookup_cbk] afr1: path /a/file > on subvolume n2-brick1 is of mode 0100644 > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:598:afr_sh_metadata_lookup_cbk] afr1: path /a/file > on subvolume n1-brick2 is of mode 0100644 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr1: > pending_matrix: [ 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr1: > pending_matrix: [ 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:486:afr_sh_metadata_sync_prepare] afr1: syncing > metadata of /a/file from subvolume n2-brick1 to 1 active sinks > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:598:afr_sh_metadata_lookup_cbk] afr-ns: path > /a/file on subvolume n3-ns is of mode 0100644 > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:598:afr_sh_metadata_lookup_cbk] afr-ns: path > /a/file on subvolume n2-ns is of mode 0100644 > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:598:afr_sh_metadata_lookup_cbk] afr-ns: path > /a/file on subvolume n1-ns is of mode 0100644 > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr-ns: > pending_matrix: [ 0 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr-ns: > pending_matrix: [ 0 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr-ns: > pending_matrix: [ 0 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:486:afr_sh_metadata_sync_prepare] afr-ns: syncing > metadata of /a/file from subvolume n2-ns to 2 active sinks > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:378:afr_sh_metadata_sync] > afr1: syncing metadata of /a/file from n2-brick1 to n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:378:afr_sh_metadata_sync] > afr-ns: syncing metadata of /a/file from n2-ns to n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:378:afr_sh_metadata_sync] > afr-ns: syncing metadata of /a/file from n2-ns to n3-ns > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:247:afr_sh_metadata_erase_pending] afr1: erasing > pending flags from /a/file on n1-brick2 > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:247:afr_sh_metadata_erase_pending] afr1: erasing > pending flags from /a/file on n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:155:afr_sh_metadata_finish] > afr1: unlocking /a/file on subvolume n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:155:afr_sh_metadata_finish] > afr1: unlocking /a/file on subvolume n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:83:afr_sh_metadata_done] > afr1: proceeding to data check on /a/file > 2008-12-11 11:26:15 D [afr-self-heal-data.c:936:afr_sh_data_lock] afr1: > locking /a/file on subvolume n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:936:afr_sh_data_lock] afr1: > locking /a/file on subvolume n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:893:afr_sh_data_lock_cbk] afr1: > inode of /a/file on child 1 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:893:afr_sh_data_lock_cbk] afr1: > inode of /a/file on child 0 locked > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr1: > pending_matrix: [ 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr1: > pending_matrix: [ 0 0 ] > 2008-12-11 11:26:15 D [afr-self-heal-data.c:717:afr_sh_data_sync_prepare] > afr1: syncing data of /a/file from subvolume n2-brick1 to 1 active sinks > 2008-12-11 11:26:15 D [afr-self-heal-data.c:615:afr_sh_data_open_cbk] afr1: > fd for /a/file opened, commencing sync > 2008-12-11 11:26:15 W [afr-self-heal-data.c:559:afr_sh_data_read_write] > afr1: sourcing file /a/file from n2-brick1 to other sinks > 2008-12-11 11:26:15 D [afr-self-heal-data.c:514:afr_sh_data_read_cbk] afr1: > read 29 bytes of data from /a/file on child 1, offset 0 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:451:afr_sh_data_write_cbk] > afr1: wrote 29 bytes of data from /a/file to child 0, offset 0 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:479:afr_sh_data_write_cbk] > afr1: closing fd's of /a/file > 2008-12-11 11:26:15 D [afr-self-heal-data.c:381:afr_sh_data_trim_cbk] afr1: > ftruncate of /a/file on subvolume n1-brick2 completed > 2008-12-11 11:26:15 D [afr-self-heal-data.c:329:afr_sh_data_erase_pending] > afr1: erasing pending flags from /a/file on n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:329:afr_sh_data_erase_pending] > afr1: erasing pending flags from /a/file on n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:253:afr_sh_data_finish] afr1: > finishing data selfheal of /a/file > 2008-12-11 11:26:15 D [afr-self-heal-data.c:229:afr_sh_data_unlock] afr1: > unlocking /a/file on subvolume n1-brick2 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:229:afr_sh_data_unlock] afr1: > unlocking /a/file on subvolume n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:186:afr_sh_data_unlck_cbk] > afr1: inode of /a/file on child 1 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:186:afr_sh_data_unlck_cbk] > afr1: inode of /a/file on child 0 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:134:afr_sh_data_close] afr1: > closing fd of /a/file on n2-brick1 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:149:afr_sh_data_close] afr1: > closing fd of /a/file on n1-brick2 > 2008-12-11 11:26:15 W [afr-self-heal-data.c:70:afr_sh_data_done] afr1: self > heal of /a/file completed > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:247:afr_sh_metadata_erase_pending] afr-ns: erasing > pending flags from /a/file on n1-ns > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:247:afr_sh_metadata_erase_pending] afr-ns: erasing > pending flags from /a/file on n2-ns > 2008-12-11 11:26:15 D > [afr-self-heal-metadata.c:247:afr_sh_metadata_erase_pending] afr-ns: erasing > pending flags from /a/file on n3-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:155:afr_sh_metadata_finish] > afr-ns: unlocking /a/file on subvolume n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:155:afr_sh_metadata_finish] > afr-ns: unlocking /a/file on subvolume n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:155:afr_sh_metadata_finish] > afr-ns: unlocking /a/file on subvolume n3-ns > 2008-12-11 11:26:15 D [afr-self-heal-metadata.c:83:afr_sh_metadata_done] > afr-ns: proceeding to data check on /a/file > 2008-12-11 11:26:15 D [afr-self-heal-data.c:936:afr_sh_data_lock] afr-ns: > locking /a/file on subvolume n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:936:afr_sh_data_lock] afr-ns: > locking /a/file on subvolume n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:936:afr_sh_data_lock] afr-ns: > locking /a/file on subvolume n3-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:893:afr_sh_data_lock_cbk] > afr-ns: inode of /a/file on child 2 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:893:afr_sh_data_lock_cbk] > afr-ns: inode of /a/file on child 1 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:893:afr_sh_data_lock_cbk] > afr-ns: inode of /a/file on child 0 locked > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr-ns: > pending_matrix: [ 0 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr-ns: > pending_matrix: [ 0 0 0 ] > 2008-12-11 11:26:15 D > [afr-self-heal-common.c:112:afr_sh_print_pending_matrix] afr-ns: > pending_matrix: [ 0 0 0 ] > 2008-12-11 11:26:15 D [afr-self-heal-data.c:717:afr_sh_data_sync_prepare] > afr-ns: syncing data of /a/file from subvolume n2-ns to 2 active sinks > 2008-12-11 11:26:15 D [afr-self-heal-data.c:615:afr_sh_data_open_cbk] > afr-ns: fd for /a/file opened, commencing sync > 2008-12-11 11:26:15 W [afr-self-heal-data.c:559:afr_sh_data_read_write] > afr-ns: sourcing file /a/file from n2-ns to other sinks > 2008-12-11 11:26:15 D [afr-self-heal-data.c:514:afr_sh_data_read_cbk] > afr-ns: read 0 bytes of data from /a/file on child 1, offset 0 > 2008-12-11 11:26:15 D [afr-self-heal-data.c:381:afr_sh_data_trim_cbk] > afr-ns: ftruncate of /a/file on subvolume n3-ns completed > 2008-12-11 11:26:15 D [afr-self-heal-data.c:381:afr_sh_data_trim_cbk] > afr-ns: ftruncate of /a/file on subvolume n1-ns completed > 2008-12-11 11:26:15 D [afr-self-heal-data.c:329:afr_sh_data_erase_pending] > afr-ns: erasing pending flags from /a/file on n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:329:afr_sh_data_erase_pending] > afr-ns: erasing pending flags from /a/file on n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:329:afr_sh_data_erase_pending] > afr-ns: erasing pending flags from /a/file on n3-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:253:afr_sh_data_finish] afr-ns: > finishing data selfheal of /a/file > 2008-12-11 11:26:15 D [afr-self-heal-data.c:229:afr_sh_data_unlock] afr-ns: > unlocking /a/file on subvolume n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:229:afr_sh_data_unlock] afr-ns: > unlocking /a/file on subvolume n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:229:afr_sh_data_unlock] afr-ns: > unlocking /a/file on subvolume n3-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:186:afr_sh_data_unlck_cbk] > afr-ns: inode of /a/file on child 2 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:186:afr_sh_data_unlck_cbk] > afr-ns: inode of /a/file on child 1 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:186:afr_sh_data_unlck_cbk] > afr-ns: inode of /a/file on child 0 locked > 2008-12-11 11:26:15 D [afr-self-heal-data.c:134:afr_sh_data_close] afr-ns: > closing fd of /a/file on n2-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:149:afr_sh_data_close] afr-ns: > closing fd of /a/file on n1-ns > 2008-12-11 11:26:15 D [afr-self-heal-data.c:149:afr_sh_data_close] afr-ns: > closing fd of /a/file on n3-ns > 2008-12-11 11:26:15 W [afr-self-heal-data.c:70:afr_sh_data_done] afr-ns: > self heal of /a/file completed > 2008-12-11 11:26:15 D [fuse-bridge.c:384:fuse_entry_cbk] glusterfs-fuse: > 171: LOOKUP() /a/file => 3833866(loc->ino:0) > 2008-12-11 11:26:15 D [inode.c:94:__dentry_hash] fuse/inode: dentry hashed > file (3833866) > 2008-12-11 11:26:15 D [inode.c:299:__inode_passivate] fuse/inode: > passivating inode(3833866) lru=1/0 active=2 purge=0 > 2008-12-11 11:26:15 D [inode.c:280:__inode_activate] fuse/inode: activating > inode(3833866), lru=0/0 active=3 purge=0 > 2008-12-11 11:26:15 D [fuse-bridge.c:1505:fuse_open] glusterfs-fuse: 172: > OPEN /a/file > 2008-12-11 11:26:15 D [ioc-inode.c:142:ioc_inode_update] brick: locked > table(0x83ccf08) > 2008-12-11 11:26:15 D [ioc-inode.c:150:ioc_inode_update] brick: adding to > inode_lru[0] > 2008-12-11 11:26:15 D [ioc-inode.c:152:ioc_inode_update] brick: unlocked > table(0x83ccf08) > 2008-12-11 11:26:15 D [fuse-bridge.c:654:fuse_fd_cbk] glusterfs-fuse: 172: > OPEN() /a/file => 0xb6b3a878 > 2008-12-11 11:26:15 D [fuse-bridge.c:1565:fuse_readv] glusterfs-fuse: 173: > READ (0xb6b3a878, size=4096, offset=0) > 2008-12-11 11:26:15 D [io-cache.c:63:ioc_get_inode] brick: locked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:67:ioc_get_inode] brick: unlocked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:988:ioc_readv] brick: NEW REQ > (0xb6b39458) offset = 0 && size = 4096 > 2008-12-11 11:26:15 D [io-cache.c:992:ioc_readv] brick: locked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:996:ioc_readv] brick: unlocked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:866:dispatch_requests] brick: locked > inode(0x83d5bf8) > 2008-12-11 11:26:15 D [page.c:204:ioc_page_create] io-cache: returning new > page 0xb6b39608 > 2008-12-11 11:26:15 D [page.c:230:ioc_wait_on_page] brick: > frame(0xb6b39458) waiting on page = 0xb6b39608, offset=0, size=4096 > 2008-12-11 11:26:15 D [page.c:239:ioc_wait_on_page] brick: locked > local(0xb6b37ac8) > 2008-12-11 11:26:15 D [page.c:241:ioc_wait_on_page] brick: unlocked > local(0xb6b37ac8) > 2008-12-11 11:26:15 D [io-cache.c:899:dispatch_requests] brick: unlocked > inode(0x83d5bf8) > 2008-12-11 11:26:15 D [page.c:429:ioc_page_fault] brick: stack winding page > fault for offset = 0 with frame 0xb6b39688 > 2008-12-11 11:26:15 D [page.c:623:ioc_frame_return] brick: locked > local(0xb6b37ac8) > 2008-12-11 11:26:15 D [page.c:625:ioc_frame_return] brick: unlocked > local(0xb6b37ac8) > 2008-12-11 11:26:15 D [io-cache.c:809:ioc_need_prune] brick: locked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:813:ioc_need_prune] brick: unlocked > table(0x83ccf08) > 2008-12-11 11:26:15 D [page.c:302:ioc_fault_cbk] brick: locked > inode(0x83d5bf8) > 2008-12-11 11:26:15 D [page.c:324:ioc_fault_cbk] brick: op_ret = 29 > 2008-12-11 11:26:15 D [page.c:653:ioc_page_wakeup] brick: page is > 0xb6b39608 && waitq = 0xb6b3a898 > 2008-12-11 11:26:15 D [page.c:453:ioc_frame_fill] brick: frame (0xb6b39458) > offset = 0 && size = 4096 && page->size = 29 && wait_count = 1 > 2008-12-11 11:26:15 D [page.c:482:ioc_frame_fill] brick: copy_size = 29 && > src_offset = 0 && dst_offset = 0 > 2008-12-11 11:26:15 D [page.c:623:ioc_frame_return] brick: locked > local(0xb6b37ac8) > 2008-12-11 11:26:15 D [page.c:625:ioc_frame_return] brick: unlocked > local(0xb6b37ac8) > 2008-12-11 11:26:15 D [page.c:590:ioc_frame_unwind] brick: > frame(0xb6b39458) unwinding with op_ret=29 > 2008-12-11 11:26:15 D [fuse-bridge.c:1530:fuse_readv_cbk] glusterfs-fuse: > 173: READ => 29/4096,0/0 > 2008-12-11 11:26:15 D [page.c:366:ioc_fault_cbk] brick: unlocked > inode(0x83d5bf8) > 2008-12-11 11:26:15 D [page.c:370:ioc_fault_cbk] brick: locked > table(0x83ccf08) > 2008-12-11 11:26:15 D [page.c:372:ioc_fault_cbk] brick: unlocked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:809:ioc_need_prune] brick: locked > table(0x83ccf08) > 2008-12-11 11:26:15 D [io-cache.c:813:ioc_need_prune] brick: unlocked > table(0x83ccf08) > 2008-12-11 11:26:15 D [page.c:386:ioc_fault_cbk] brick: fault frame > 0xb6b39688 returned > 2008-12-11 11:26:15 D [fuse-bridge.c:618:fuse_getattr] glusterfs-fuse: 174: > FGETATTR 3833866 (/a/file/0xb6b3a878) > 2008-12-11 11:26:15 D [fuse-bridge.c:530:fuse_attr_cbk] glusterfs-fuse: > 174: FSTAT() /a/file => 3833866 > 2008-12-11 11:26:15 D [fuse-bridge.c:1648:fuse_flush] glusterfs-fuse: 175: > FLUSH 0xb6b3a878 > 2008-12-11 11:26:15 D [fuse-bridge.c:902:fuse_err_cbk] glusterfs-fuse: 175: > FLUSH() ERR => 0 > 2008-12-11 11:26:15 D [fuse-bridge.c:1668:fuse_release] glusterfs-fuse: > 176: RELEASE 0xb6b3a878 > 2008-12-11 11:26:15 D [inode.c:299:__inode_passivate] fuse/inode: > passivating inode(3833866) lru=1/0 active=2 purge=0 > 2008-12-11 11:26:15 D [fuse-bridge.c:2067:fuse_statfs] glusterfs-fuse: 177: > STATFS > > Why file is bring back? Can anyone help? > > -- > rash at konto pl > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users >-- Raghavendra G -- Raghavendra G -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20081211/73c8966f/attachment.html>
Maybe Matching Threads
- Would difference in size (and content) of a file on replicated bricks be healed?
- Where is log file of GlusterFS 3.0?
- Issue with files on glusterfs becoming unreadable.
- File uploaded to webDAV server on GlusterFS AFR - ends up without xattr!
- software raid performance