glusterfs.git, branch v3.12.4 GlusterFS is a distributed file-system capable of scaling to several petabytes. It aggregates various storage bricks over Infiniband RDMA or TCP/IP interconnect into one large parallel network file system. doc : release-notes for GlusterFS-3.12.4 2017-12-13T09:59:31+00:00 Jiffin Tony Thottan jthottan@redhat.com 2017-12-13T09:57:46+00:00 7b8d2f12414d67da01bcbf1fc9872e07dac2e99f Change-Id: Ib48b2ae64a3cf90b44c3a80ffcda6204f152ae40 BUG: 1519095 Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com> 
Change-Id: Ib48b2ae64a3cf90b44c3a80ffcda6204f152ae40
BUG: 1519095
Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com>
glusterd: Free up svc->conn on volume delete 2017-12-12T10:00:52+00:00 Atin Mukherjee amukherj@redhat.com 2017-12-06T12:35:24+00:00 2c588f81d452b0d54920a0abbb266c8c1d37e62f Daemons like snapd, tierd and gfproxyd are maintained on per volume basis and on a volume delete we should destroy the rpc connection established for them. >mainline patch : https://review.gluster.org/#/c/18957/ Change-Id: Id1440e39da07b990fdb9b207df18da04b1ca8014 BUG: 1523048 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> (cherry picked from commit 36ce4c614a3391043a3417aa061d0aa16e60b2d3) 
Daemons like snapd, tierd and gfproxyd are maintained on per volume
basis and on a volume delete we should destroy the rpc connection
established for them.

>mainline patch : https://review.gluster.org/#/c/18957/

Change-Id: Id1440e39da07b990fdb9b207df18da04b1ca8014
BUG: 1523048
Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
(cherry picked from commit 36ce4c614a3391043a3417aa061d0aa16e60b2d3)
core/memacct: save allocs in mem_acct_rec list 2017-12-08T14:40:31+00:00 N Balachandran nbalacha@redhat.com 2017-12-08T03:11:13+00:00 aae8eaa8104197652d487042a66fddd850da72f3 With configure --enable-debug, add all object allocations to a list in the corresponding mem_acct_rec. This allows us to see all objects of a particular type and allows for additional debugging in case of memory leaks. This is not compiled in by default and must be explicitly enabled. It is intended to be used by developers. > Change-Id: I7cf2dbeadecf994423d7e7591e85f18d2575cce8 > BUG: 1522662 > Signed-off-by: N Balachandran <nbalacha@redhat.com> (cherry picked from commit 47d01546a1826dc14a8331ea8700015f1cfdc4db) Change-Id: I7cf2dbeadecf994423d7e7591e85f18d2575cce8 BUG: 1523455 Signed-off-by: N Balachandran <nbalacha@redhat.com> 
With configure --enable-debug, add all object allocations
to a list in the corresponding mem_acct_rec. This
allows us to see all objects of a particular type
and allows for additional debugging in case of memory
leaks.

This is not compiled in by default and must be explicitly
enabled. It is intended to be used by developers.

> Change-Id: I7cf2dbeadecf994423d7e7591e85f18d2575cce8
> BUG: 1522662
> Signed-off-by: N Balachandran <nbalacha@redhat.com>

(cherry picked from commit 47d01546a1826dc14a8331ea8700015f1cfdc4db)
Change-Id: I7cf2dbeadecf994423d7e7591e85f18d2575cce8
BUG: 1523455
Signed-off-by: N Balachandran <nbalacha@redhat.com>
Disable gfid2path by default on NetBSD 2017-12-08T14:38:57+00:00 Emmanuel Dreyfus manu@netbsd.org 2017-11-15T03:04:39+00:00 7359ecec6a8919a15dc1ce3bef3ab99d0898414f NetBSD storage of extended attributes for UFS1 badly scales when the list of extended attributes names rises. gfid2path can add as many extended attributes names as we have files, hence we keep it disabled for performance sake. > Change-Id: Id77b5f5ceb4d5eba1b3362b4b9fc693450ffbc2b > Signed-off-by: Emmanuel Dreyfus <manu@netbsd.org> > BUG: 1129939 Change-Id: Id77b5f5ceb4d5eba1b3362b4b9fc693450ffbc2b Signed-off-by: Emmanuel Dreyfus <manu@netbsd.org> BUG: 1513258 
NetBSD storage of extended attributes for UFS1 badly scales when
the list of extended attributes names rises. gfid2path can add as
many extended attributes names as we have files, hence we keep it
disabled for performance sake.

> Change-Id: Id77b5f5ceb4d5eba1b3362b4b9fc693450ffbc2b
> Signed-off-by: Emmanuel Dreyfus <manu@netbsd.org>
> BUG: 1129939

Change-Id: Id77b5f5ceb4d5eba1b3362b4b9fc693450ffbc2b
Signed-off-by: Emmanuel Dreyfus <manu@netbsd.org>
BUG: 1513258
cluster/dht: don't overfill the buffer in readdir(p) 2017-12-08T05:36:52+00:00 Raghavendra G rgowdapp@redhat.com 2017-09-18T10:31:34+00:00 fd3448c4a70c0c4ed2b8053ebe5bbe4d261086ee Superflous dentries that cannot be fit in the buffer size provided by kernel are thrown away by fuse-bridge. This means, * the next readdir(p) seen by readdir-ahead would have an offset of a dentry returned in a previous readdir(p) response. When readdir-ahead detects non-monotonic offset it turns itself off which can result in poor readdir performance. * readdirp can be cpu-intensive on brick and there is no point to read all those dentries just to be thrown away by fuse-bridge. So, the best strategy would be to fill the buffer optimally - neither overfill nor underfill. > Change-Id: Idb3d85dd4c08fdc4526b2df801d49e69e439ba84 > BUG: 1492625 > Signed-off-by: Raghavendra G <rgowdapp@redhat.com> (cherry picked from commit e785faead91f74dce7c832848f2e8f3f43bd0be5) Change-Id: Idb3d85dd4c08fdc4526b2df801d49e69e439ba84 BUG: 1478411 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> 
Superflous dentries that cannot be fit in the buffer size provided by
kernel are thrown away by fuse-bridge. This means,

* the next readdir(p) seen by readdir-ahead would have an offset of a
dentry returned in a previous readdir(p) response. When readdir-ahead
detects non-monotonic offset it turns itself off which can result in
poor readdir performance.

* readdirp can be cpu-intensive on brick and there is no point to read
 all those dentries just to be thrown away by fuse-bridge.

So, the best strategy would be to fill the buffer optimally - neither
overfill nor underfill.

> Change-Id: Idb3d85dd4c08fdc4526b2df801d49e69e439ba84
> BUG: 1492625
> Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
(cherry picked from commit e785faead91f74dce7c832848f2e8f3f43bd0be5)
Change-Id: Idb3d85dd4c08fdc4526b2df801d49e69e439ba84
BUG: 1478411
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
cluster/dht: populate inode in dentry for single subvolume dht 2017-12-06T10:08:54+00:00 Raghavendra G rgowdapp@redhat.com 2017-09-19T04:14:55+00:00 f85154306277fbd0510109dc67c9a85e67223028 ... in readdirp response if dentry points to a directory inode. This is a special case where the entire layout is stored in one single subvolume and hence no need for lookup to construct the layout >Change-Id: I44fd951e2393ec9dac2af120469be47081a32185 >BUG: 1492625 >Signed-off-by: Raghavendra G <rgowdapp@redhat.com> (cherry picked from commit 59d1cc720f52357f7a6f20bb630febc6a622c99c) Change-Id: I44fd951e2393ec9dac2af120469be47081a32185 BUG: 1478411 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> 
... in readdirp response if dentry points to a directory inode. This
is a special case where the entire layout is stored in one single
subvolume and hence no need for lookup to construct the layout

>Change-Id: I44fd951e2393ec9dac2af120469be47081a32185
>BUG: 1492625
>Signed-off-by: Raghavendra G <rgowdapp@redhat.com>

(cherry picked from commit 59d1cc720f52357f7a6f20bb630febc6a622c99c)
Change-Id: I44fd951e2393ec9dac2af120469be47081a32185
BUG: 1478411
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
cli: remove summary option from heal info command 2017-12-01T04:49:28+00:00 Ravishankar N ravishankar@redhat.com 2017-11-28T05:22:29+00:00 f4867128fe36e4521c56e4d1e8afd7ad1b3f621e commit c49fcf570439e47a5e1224436bbaf3f8dd580105 was a straight forward backport from its corresponding master patch but in doing so, also added the 'summary' option to the CLI. The heal info summary command is present only in glusterfs-3.13. So remove it from the CLI in 3.12 Change-Id: Idb742f0b9752726c94619c0528fe792e4f5134fd BUG: 1518061 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reported-by: Shubhendu Tripathi <shtripat@redhat.com> 
commit c49fcf570439e47a5e1224436bbaf3f8dd580105 was a straight forward backport
from its corresponding master patch but in doing so, also added the 'summary'
option to the CLI. The heal info summary command is present only in
glusterfs-3.13. So remove it from the CLI in 3.12

Change-Id: Idb742f0b9752726c94619c0528fe792e4f5134fd
BUG: 1518061
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reported-by: Shubhendu Tripathi <shtripat@redhat.com>
tests: fix bug-1483058-replace-brick-quorum-validation.t spurious failure 2017-11-30T06:48:06+00:00 Atin Mukherjee amukherj@redhat.com 2017-11-09T17:12:22+00:00 e5db48bf5780c1d278481e0dc25e5c64ccbf9583 > mainline patch : https://review.gluster.org/#/c/18710/ Change-Id: I04c35305bfb663eabbf715eee78695adfd4a2d20 BUG: 1512432 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> (cherry picked from commit 76a83f98b78a0bdf29bbb0f8e4c9ab74dae52be4) 
> mainline patch : https://review.gluster.org/#/c/18710/

Change-Id: I04c35305bfb663eabbf715eee78695adfd4a2d20
BUG: 1512432
Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
(cherry picked from commit 76a83f98b78a0bdf29bbb0f8e4c9ab74dae52be4)
glusterd: display gluster volume status, when quorum type is server 2017-11-30T06:46:02+00:00 Sanju Rakonde srakonde@redhat.com 2017-11-09T07:45:51+00:00 4c9478b3604305e0e20c90096198b14dda83e3d0 Problem: when server-quorum-type is server, after restarting glusterd in the node which is up, gluster volume status is giving incorrect information. Fix: check whether server is blank, before adding other keys into the dictionary. Change-Id: I926ebdffab330ccef844f23f6d6556e137914047 BUG: 1511782 Signed-off-by: Sanju Rakonde <srakonde@redhat.com> (cherry picked from commit 046c7e3199fca715592762e271e6061ac99b0c4b) 
Problem: when server-quorum-type is server, after restarting glusterd
in the node which is up, gluster volume status is giving incorrect
information.

Fix: check whether server is blank, before adding other keys into the
dictionary.

Change-Id: I926ebdffab330ccef844f23f6d6556e137914047
BUG: 1511782
Signed-off-by: Sanju Rakonde <srakonde@redhat.com>
(cherry picked from commit 046c7e3199fca715592762e271e6061ac99b0c4b)
cluster/afr: Print heal info split-brain output in stream fashion 2017-11-30T06:43:18+00:00 karthik-us ksubrahm@redhat.com 2017-10-25T07:12:23+00:00 3c39df42ffadb060b38b62d70eded285d650f08d Problem: When we trigger the heal info split-brain command the o/p is not streamed as it is received, but dumped at the end for all the bricks together. This gives a perception that the command is hung. Fix: When we get a split brain entry while crawling throught the pending heal entries, flush that immediately so that it prints the output in a stream fashion and doesn't look like the cli is hung. Change-Id: I7547e86b83202d66616749b8b31d4d0dff0abf07 BUG: 1514420 Signed-off-by: karthik-us <ksubrahm@redhat.com> (cherry picked from commit 05f9c13f4d69e4113f5a851f4097ef35ba3f33b2) 
Problem:
When we trigger the heal info split-brain command the o/p is not
streamed as it is received, but dumped at the end for all the bricks
together. This gives a perception that the command is hung.

Fix:
When we get a split brain entry while crawling throught the pending
heal entries, flush that immediately so that it prints the output
in a stream fashion and doesn't look like the cli is hung.

Change-Id: I7547e86b83202d66616749b8b31d4d0dff0abf07
BUG: 1514420
Signed-off-by: karthik-us <ksubrahm@redhat.com>
(cherry picked from commit 05f9c13f4d69e4113f5a851f4097ef35ba3f33b2)