| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Free the xdr string allocations after decoding the upcall
cache_invalidation request.
Change-Id: I0ffc64f587d6c8566cba76cf08148f937a735926
BUG: 1295107
Signed-off-by: Soumya Koduri <skoduri@redhat.com>
Reviewed-on: http://review.gluster.org/13232
Reviewed-by: Niels de Vos <ndevos@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1. while handling short writes, __wb_fulfill_short_write would've freed
current request before moving on to next in the list if request is not
big enough to accomodate completed number of bytes. So, make sure to
save next member before invoking __wb_fulfill_short_write on current
request. Also handle the case where request is exactly the size of
remaining completed number of bytes.
2. When write request is unwound because there is a conflicting failed
liability, make sure its deleted from tempted list. Otherwise there
will be two unwinds (one as part handling a failed request in
wb_do_winds and another in wb_do_unwinds).
Change-Id: Id1b54430796b19b956d24b8d99ab0cdd5140e4f6
BUG: 1297373
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
Reviewed-on: http://review.gluster.org/13213
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra Talur <rtalur@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
During resolving of an entry or inode, if inode ctx
was not set, we will send a lookup.
This patch also make sure that inode_ctx will be created
after every inode_link
Change-Id: I4211533ca96a51b89d9f010fc57133470e52dc11
BUG: 1297311
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13225
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fuse shoud sent atleast one lookup for an inode/gfid
populated via readdirp before actual fop to populate
inode ctx for xlators
Change-Id: I5c02ed73f892924c9e404d91cbe0633a275accbd
BUG: 1236032
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/11892
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
During resolving of an entry or inode, if inode ctx
was not set, we will send a lookup.
This patch also make sure that inode_ctx will be created
after every inode_link.
Change-Id: I137a7e2510635ff4ea6d007b671961341f89c949
BUG: 1297311
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13224
Reviewed-by: soumya k <skoduri@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
After creating an inode and before linking it
to inode table, if there is a request to setattr
for that file, it fails and leads to crash.
Before linking inode to inode table ia_type is IA_INVAL
which will casue have_size and have_config as zero.
Solution:
Check and get size and config if an inode is invalid
Change-Id: I0c0e564940b1b9f351369a76ab14f6b4aa81f23b
BUG: 1293223
Signed-off-by: Ashish Pandey <aspandey@redhat.com>
Reviewed-on: http://review.gluster.org/13039
Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In lookup call back path, we are checking for parent inode
type to make sure parent inode was set properly, so that
next op on the inode can be successfuly completed.
More info can be found at bugid 1297311
Change-Id: Ifb1b17f472f855f9b12088c3dd8328389d895e77
BUG: 1297311
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13227
Reviewed-by: Avra Sengupta <asengupt@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Rajesh Joseph <rjoseph@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
performance.resync-failed-syncs-after-fsync was
introduced after 3.7.6 was released. Hence it should
use 3_7_7 as op version not 3_7_6.
Change-Id: If4def1bf0fdc9fa4938ccb78308bec77eeaa2284
BUG: 1279730
Signed-off-by: Raghavendra Talur <rtalur@redhat.com>
Reviewed-on: http://review.gluster.org/13117
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Given a two node cluster with node N1 & N2, if a dummy node N3 is peer probed, the
probed node N3 goes for importing volumes from the probing node (N1), but
it still doesn't have information about the other node (N2) about its membership
(since peer update happens post volume updates) and hence fail to update its
brick's uuid. Post that even though N2 updates N3 about its membership the
brick's uuid was never generated. Now as a consequence when N3 initiates a
detach of N2, it checks whether the node to be detached has any bricks
configured by its respective uuid which is NULL in this case and hence it goes
ahead and removes the peer which ideally it shouldn't have (refer to
glusterd_friend_contains_vol_bricks () for the logic)
Fix is to export brick's uuid and import it at the probed node instead of
resolving it.
Change-Id: I2d88c72175347550a45ab12aff0ae248e56baa87
BUG: 1293414
Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
Reviewed-on: http://review.gluster.org/13047
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Gaurav Kumar Garg <ggarg@redhat.com>
Reviewed-by: Avra Sengupta <asengupt@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The dst_fd was being unrefed twice in case the call
to __dht_rebalance_create_dst_file failed.
Change-Id: I56c5aff7fa3827887e67936b8aa1ecbd1a08a9e9
BUG: 1296611
Signed-off-by: N Balachandran <nbalacha@redhat.com>
Reviewed-on: http://review.gluster.org/13193
Reviewed-by: Susant Palai <spalai@redhat.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The -n option does not take any arguments. It seems like this shift is
removing the next option. On my CentOS 7 system, automount calls
mount.glusterfs with the parameters:
host:/volume /mountpoint -n -o rw,acl,_netdev
This causes the -o option to be siliently ignored.
Change-Id: Ice3c877f6ab346b04292e3dfed968d04d15077a5
BUG: 1297195
Signed-off-by: James Augustine <jcaugust81@gmail.com>
Reviewed-on: http://review.gluster.org/12988
Reviewed-by: Niels de Vos <ndevos@redhat.com>
Tested-by: Niels de Vos <ndevos@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Check for corrupted objects is done bt bitrot stub component
for data operations and such fops are denied processing by
returning EIO. These checks were not done for operations such
as get/set extended attribute, stat and the likes - IOW, stub
only blocked pure data operations.
However, its necessary to have these checks for certain other
fops, most importantly stat (and fstat). This is due to the
fact that clients could possibly get stale stat information
(such as size, {a,c,m}time) resulting in incorrect operation
of the application that rely on these fields. Note that, the
data that replication would take care of fetching good (and
correct) data, but the staleness of stat information could
lead to data inconsistencies (e.g., rebalance, tier).
Change-Id: I5a22780373b182a13f8d2c4ca6b7d9aa0ffbfca3
BUG: 1296399
Signed-off-by: Venky Shankar <vshankar@redhat.com>
Reviewed-on: http://review.gluster.org/13120
Reviewed-by: Kotresh HR <khiremat@redhat.com>
Reviewed-by: mohammed rafi kc <rkavunga@redhat.com>
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A query to the database may take a long time if the database
has many entries. The tier daemon also sends IPC calls to the
bricks which can run slowly, espcially in RHEL6. While it is
possible to track down each such instance, the snapshot
feature should not be affected by database operations. It requires
no migration be underway. Therefore it is okay to pause tiering
at any time except when DHT is moving a file. This fix implements
this strategy by monitoring when control passes to DHT to
migrate a file using the GF_XATTR_FILE_MIGRATE_KEY trigger. If it
is not, the pause operation is successful.
Change-Id: I21f168b1bd424077ad5f38cf82f794060a1fabf6
BUG: 1287842
Signed-off-by: Dan Lambright <dlambrig@redhat.com>
Reviewed-on: http://review.gluster.org/13104
Reviewed-by: Joseph Fernandes
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
If xattr is node-uuid and the inode is marked bad, fail getxattr
and fgetxattr with EIO. Returning EIO would result in AFR to
choose correct node-uuid coresponding to the subvolume where
the good copy of the file resides.
Change-Id: I45a42ca38f8322d2b10f3c4c48dc504521162b42
BUG: 1294786
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/13116
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When a quota is disable and enabled again before completing
the cleanup operation, this can remove the new xattrs
and quota accounting can become wrong
Remove removing the xattr, check if quota enabled again and the
xattr is new
Change-Id: Idda216f1e7346a9b843dbc112ea3e6faa9c47483
BUG: 1293601
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/13065
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
short writes.
1. Imagine a write when cache is filled with failed syncs.
2. This write won't be unwound since cache size has exceeded
configured limit.
3. With trickling-writes on by default, the last write request wont be
considered for winding when there is non zero in-transit size.
4. There was a bug in accounting of in-transit size when winds
resulted in short writes. Due to this bug, in-transit size used to be
non-zero even when there are no syncs in progress.
5. Due to 3 and 4, current write request won't be wound till there is
another write or fsync or flush from application. But application
can't do any other fop till current write request is unwound. This
resulted in deadlock and hence application would be hung in 'D'
state.
This patch fixes bug in accounting of in-transit size during short
writes.
Change-Id: I04ce8bb510efaaed7623cac38d69b32dbc3730ce
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
BUG: 1279730
Reviewed-on: http://review.gluster.org/13177
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
gcc-6 now has -Wmisleading-indentation as part of -Wall.
compiling with gcc-6 gives this warning.
...
dht-diskusage.c: In function ‘dht_subvol_has_err’:
dht-diskusage.c:361:33: warning: statement is indented as if it were
guarded by... [-Wmisleading-indentation]
goto out;
^~~~
dht-diskusage.c:358:25: note: ...this ‘if’ clause, but it is not
if (conf->decommissioned_bricks[i] &&
^~
...
Inspection of the source shows that without braces the loop is
terminated prematurely.
Change-Id: Ica48a8c59ee5d0a206797827d7920259d33b47ec
BUG: 1295784
Signed-off-by: Kaleb S KEITHLEY <kkeithle@redhat.com>
Reviewed-on: http://review.gluster.org/13176
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In tier_create, a new key TIER_LINKFILE_GFID was introduced to
avoid a race in stale linkfile deletion. Storing this key in
xattr dictionary instead of using local->params dictionary.
Because local->params dictionary was also used to create the file
before stale linkfile deletion, that leads posix_create to fail,
trying to set the added key as extended attributes
Change-Id: I24fecb62b47bee65a1e86103925a67d13304c5df
BUG: 1290677
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13130
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently we check the watermarks only before a cycle
begins. We should also check the hot tier's fullness
against the watermarks during the migration so the watermark
is not exceeded as files are promoted.
Change-Id: I2ff87a1c308d64fbdca14bbdf55f3ec3007290ae
BUG: 1293932
Signed-off-by: Dan Lambright <dlambrig@redhat.com>
Reviewed-on: http://review.gluster.org/13103
Reviewed-by: Joseph Fernandes
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Added file path/gfid when available to the tier log
messages to make debugging easier.
Change-Id: I22dda329367df2b846dcf254594312c997b66083
BUG: 1273043
Signed-off-by: N Balachandran <nbalacha@redhat.com>
Reviewed-on: http://review.gluster.org/13114
Reviewed-by: mohammed rafi kc <rkavunga@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Tier process is not updating the status when the process killed
mnually.
Change-Id: Ia5ea903af78ff3582da2242e6058f11c71923fab
BUG: 1294600
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13107
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When compiled with -Werror flag gcc throws the following
error:
‘iov_length’ is static but used in inline
function ‘__wb_modify_write_request’ which is not static.
Let gcc decide what functions to inline and remove the inline
keyword.
Change-Id: I6d832596eefcf08306634936e11d2c8d4b8f9ccd
BUG: 1279730
Signed-off-by: Raghavendra Talur <rtalur@redhat.com>
Reviewed-on: http://review.gluster.org/13113
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently we are storing the memory as a static pointer.
There is a chance to go that variable in out of scope.
So we should allocate in Dynamic way.
Change-Id: I096876deb8055ac3a44681599591a0a032bc0c24
BUG: 1290677
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13102
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
during unlink of a file, we will get stat just after
deleting the file, to see if the file is under migration or not.
but this stat call will fail for symlink if the actual file
was deleted.
So it is better not to send stat request from client if it is
a symlink as we are not migrating symlink.
Change-Id: Idc033b24fa3522b5261e579889d2195b43419682
BUG: 1293963
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13074
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
DHT after creating missing directory, tries to heal the
xattrs. This xattrs operation fails as INTERNAL FOP key was not set
Change-Id: I819d373cf7073da014143d9ada908228ddcd140c
BUG: 1294479
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/13100
Reviewed-by: Susant Palai <spalai@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Commit 2b7226f9d3470d8fe4c98c1fddb06e7f641e364d did not check for the
validity of a dict before doing a dict_get. Fix that.
Change-Id: Ie21f4da19256b17196f242cd8fd5bb76b0a69c1e
BUG: 1294053
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: http://review.gluster.org/13077
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch is to supress the error log of Failed to aggregate rsp_dict where the
above function returns a non zero ret which is not required
Change-Id: If331980291bd369690257215333cea175e2042ec
BUG: 1290734
Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
Reviewed-on: http://review.gluster.org/12950
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Gaurav Kumar Garg <ggarg@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When in a befriended state, glusterd would broadcast friend updates to
all other peers whenver a ACC or LOCAL_ACC event occurred.
When a downed glusterd came back up and established connections again,
this lead to a flood of friend updates to happen on the order of N^2 (N
is the number of peers in the cluster)
In larger clusters this was problematic, and could lead to very long
times for the cluster to settle down when a peer came back up. Multiple
peers coming back up at the same time would compound the problem.
Broadcasting of friend updates doesn't have much use in places other
that during a peer probe. Instead of broadcasting friend updates on
connection re-establishment, updates can just be exchanged between the
peers involved in the connection.
This patch changes the glusterd friend state-machine to send updates
only to the required peer for ACC or LOCAL_ACC events when in befriended
state. The number of updates sent now is in the order of N.
For a 10 node cluster, the number of updates reduced by 5 times. When
creating the 10 node cluster, the updates reduced from ~500 to ~150.
When a glusterd restarted, the number of exchanges reduced from ~160 to
~35.
BUG: 1292749
Change-Id: Ib6072090c7069b081d018cdaa3dc878819ab1d18
Signed-off-by: Kaushal M <kaushal@redhat.com>
Reviewed-on: http://review.gluster.org/12999
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The start command doesnt restart the tier deamon if the deamon
is running at one node. hence to bring up the tierd on the nodes
where the deamon is down, the force command is implemented.
It skips the check for tierd running.
Change-Id: I0037d3e5ecfe56637d0da201a97903c435d26436
BUG: 1292112
Signed-off-by: hari gowtham <hgowtham@redhat.com>
Reviewed-on: http://review.gluster.org/12983
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
What:
If dht_open is called on a migrating file after the inode_ctx is set,
subsequent FOPs on that fd do not open the fd on the dst subvol.
This is seen when the open-ftruncate-close sequence is repeatedly
called on a migrating file.
A second call to the sequence described above causes dht_truncate_cbk
to call dht_truncate2 as the dht_inode_ctx was already set by the first
call. As dht_rebalance_in_progress_check is not called, the fd is not
opened on the dst subvol.
On a distributed-replicate volume, this causes AFR to
open the fd using afr_fix_open, but with the wrong flags, causing
posix_ftruncate to fail with EINVAL.
The fix: We require fd specific information to make a decision while
handling migrating files.
Set the fd_ctx to indicate the fd has been opened on the dst subvol
and check if it has been set while processing Phase1/Phase2 checks
in the FOP callback functions.
Change-Id: I43cdcd8017b4a11e18afdd210469de7cd9a5ef14
BUG: 1284823
Signed-off-by: N Balachandran <nbalacha@redhat.com>
Reviewed-on: http://review.gluster.org/12985
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Revisiting http://review.gluster.org/#/c/11814/, which unintentionally
introduced warnings from libtool about the xlator .so names.
According to [1], the -module option must appear in the Makefile.am
file(s); if -module is defined in a macro, e.g. in configure(.ac),
then libtool will not recognize that this is a module and will emit a
warning.
[1]
http://www.gnu.org/software/automake/manual/automake.html#Libtool-Modules
Change-Id: Ifa5f9327d18d139597791c305aa10cc4410fb078
BUG: 1248669
Signed-off-by: Kaleb S KEITHLEY <kkeithle@redhat.com>
Reviewed-on: http://review.gluster.org/13003
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: soumya k <skoduri@redhat.com>
Reviewed-by: Niels de Vos <ndevos@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
add additional system calls plus pick up a couple missed unwrapped
system calls that seem to have slipped into the master branch.
Change-Id: If268ccd5e9a139ac3ffd38293c67cd2f62ea5b58
BUG: 1289258
Signed-off-by: Kaleb S KEITHLEY <kkeithle@redhat.com>
Reviewed-on: http://review.gluster.org/12895
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Niels de Vos <ndevos@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
recording path
1. Providing vol set option for cache size and wal autocheck point
so that performance can be tuned.
2. Removed recording of file path in the db. Trimming database columns.
Path need not be stored in the db, as PARGFID, GFID, Basename is suffice
to derive the path during migration.
Change-Id: I2cb590451a6d244bc91fe66c6dbffe2c2059dfb8
BUG: 1293034
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/12972
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
If we are creating data file in a hot subvolume
then we will create a linkfile in cold subvolume.
Linkfile creation happens first. If linkfile creation
was successful and data file creation failed, then
linkfile in cold subvolume will become stale.
This patch will delete the linkfile as well, if data
file creation fails.
Also this code duplicates dht_create to make tier_create
Change-Id: I377a90dad47f288e9576c7323b23cf694a91a7a3
BUG: 1290677
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/12948
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1. When sync fails, the cached-write is still preserved unless there
is a flush/fsync waiting on it.
2. When a sync fails and there is a flush/fsync waiting on the
cached-write, the cache is thrown away and no further retries will
be made. In other words flush/fsync act as barriers for all the
previous writes. The behaviour of fsync acting as a barrier is
controlled by an option (see below for details). All previous
writes are either successfully synced to backend or forgotten in
case of an error. Without such barrier fop (especially flush which
is issued prior to a close), we end up retrying for ever even after
fd is closed.
3. If a fop is waiting on cached-write and syncing to backend fails,
the waiting fop is failed.
4. sync failures when no fop is waiting are ignored and are not
propagated to application. For eg.,
a. first attempt of sync of a cached-write w1 fails
b. second attempt of sync of w1 succeeds
If there are no fops dependent on w1 are issued b/w a and b,
application won't know about failure encountered in a.
5. The effect of repeated sync failures is that, there will be no
cache for future writes and they cannot be written behind.
fsync as a barrier and resync of cached writes post fsync failure:
==================================================================
Whether to keep retrying failed syncs post fsync is controlled by an
option "resync-failed-syncs-after-fsync". By default, this option is
set to "off".
If sync of "cached-writes issued before fsync" (to backend) fails,
this option configures whether to retry syncing them after fsync or
forget them. If set to on, cached-writes are retried till a "flush"
fop (or a successful sync) on sync failures. fsync itself is failed
irrespective of the value of this option, when there is a sync failure
of any cached-writes issued before fsync.
Change-Id: I6097c9257bfb9ee5b15616fbe6a0576ae9af369a
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
BUG: 1279730
Reviewed-on: http://review.gluster.org/12594
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The master xlator needs to allocate 'logbuf_pool'
else 'gf_msg' fails with EINVAL.
Change-Id: I6b2d3450250de7e77126d12b75b0dbc4db414bfb
BUG: 1292463
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/12997
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
quota-version features is implemented for 3.7.6
please see below patch for more details:
http://review.gluster.org/#/c/12386
As part of this feature, new volume info option 'quota-version'
was introduced, this can cause check-sum problem
when a one of the node in a cluster is upgraded to 3.7.6
(heterogeneous cluster)
So do a OP_VERSION check when storing this option
in volume info
Change-Id: Ic5b03a1e3f1236b645a065b1fadee7950307e191
BUG: 1283178
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/12642
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
When IO is happening on a file and a brick goes down comes back up
during this time, protocol/client translator attempts reopening of the
fd on the gfid handle of the file. But if another client renames this
file while a brick was down && writes were in progress on it, once this
brick is back up, there can be a race between reopening of the fd and
entry self-heal replaying the effect of the rename() on the sink brick.
If the reopening of the fd happens first, the application's writes
continue to go into the data blocks associated with the gfid.
Now entry-self-heal deletes 'src' and creates 'dst' file on the sink,
marking dst as a 'newentry'. Data self-heal is also completed on 'dst'
as a result and self-heal terminates. If at this point the application
is still writing to this fd, all writes on the file after self-heal
would go into the data blocks associated with this fd, which would be
lost once the fd is closed. The result - the 'dst' file on the source
and sink are not the same and there is no pending heal on the file,
leading to silent corruption on the sink.
Fix:
Leverage http://review.gluster.org/#/c/12816/ to ensure the gfid handle
path gets saved in .glusterfs/unlink until the fd is closed on the file.
During this time, when self-heal sends mknod() with gfid of the file,
do the following:
link() the gfid handle under .glusterfs/unlink to the new path to be
created in mknod() and
rename() the gfid handle to go back under .glusterfs/ab/cd/.
Change-Id: I86ef1f97a76ffe11f32653bb995f575f7648f798
BUG: 1292379
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/13001
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Since commit 6e635284a4411b816d4d860a28262c9e6dc4bd6a
(glusterfs-3.7.7), the afr pending xattrs are stored in the volfile and used
by afr when it initializes. If a cluster is upgraded, prevent afr from loading
until the op-version has been bumped up to 3.7.7 and the volfiles have been
regenerated using a volume set command.
Without this fix, AFR will crash when initialzing.
Change-Id: I14249dedb3f2f77cd754d78d8a9a70fdc5fc8c10
BUG: 1293293
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: http://review.gluster.org/13038
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
DUring unlink of a file, dht request stat to see whether
the file is under migration or not. But in posix_unlink
currently we are opening for regular files. so the fdstat
for special files are failing with EBAD
Change-Id: Ic0678e42e7701c3dffb91d98272e664b0fc646b5
BUG: 1293256
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/13034
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Reviewed-by: Susant Palai <spalai@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We had run sleep() in the pause tier callback. Blocking within
a synctask is dangerous. The sleep() call does not inform
the synctask scheduler that a thread is no longer running.
It therefore believes it is running. If a second synctask already
exists, it may not be able to run. This occurs if the thread
limit in the pool has been reached.
Note the pool size only grows when a synctask is created, not
when it is moved from wait state to run state, as is the case
when an FOP completes. When the tier is paused during migration,
synctasks already exist waiting for responses to FOPs to the
server with high probability.
The fix is to yield() in the RPC callback, which will place
the synctask into the wait queue and free up a thread for the
FOP callback. A timer wakes the callback after sufficient
time has elapsed for the pause to occur.
Change-Id: I6a947ee04c6e5649946cb6d8207ba17263a67fc6
BUG: 1267950
Signed-off-by: Dan Lambright <dlambrig@redhat.com>
Reviewed-on: http://review.gluster.org/12987
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Rajesh Joseph <rjoseph@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
During migration if the file is present we just open the file
in hashed subvol. Now if the linkfile present on hashed is just
linkfile to another subvol, we actually open in hashed subvol.
But subsequent operation will go to linkto subvol ie,
to non-hashed subvol. This operation will get failed
since we haven't opened d on non-hashed.
Change-Id: I9753ad3a48f0384c25509612ba76e7e10645add3
BUG: 1292067
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/12980
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Susant Palai <spalai@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
While tier migration, free src and dst fd's when create of
destination or open of source fails.
Change-Id: I62978a669c6c9fbab5fed9df2716b9b2ba00ddf1
BUG: 1291566
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/12969
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
If an object (file) is marked bad by bitrot, do not consider the brick
on which the object is present as a potential read subvolume for AFR
irrespective of the pending xattr values.
Also do not consider the brick containing the bad object while
performing afr_accuse_smallfiles(). Otherwise if the bad object's size
is bigger, we may end up considering that as the source.
Change-Id: I4abc68e51e5c43c5adfa56e1c00b46db22c88cf7
BUG: 1290965
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: http://review.gluster.org/12955
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
For fd based operations (fgetxattr, readv etc.) if an inode refresh is
required, do so using fstat instead of lookup. This is because the file
might have been deleted by another client before refresh but posix
mandates that FOPS using already open fds must still succeed.
Change-Id: Id5f71c3af4892b648eb747f363dffe6208e7ac09
BUG: 1285230
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: http://review.gluster.org/12894
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The option tier-max-files represents the maximum number
of files trasferred by a node in a gives cycle. Fix help message
to reflect the "per node" aspect. The code transferred one
more file per cycle than the given value.
Also change the default values of max file and max bytes to
very large values, effectively we will not throttle migration
unless the administrator requests it via CLI.
Change-Id: Ic2949ed3d8c35afe7c9ae4db72195603cfb2e28f
BUG: 1292671
Signed-off-by: Dan Lambright <dlambrig@redhat.com>
Reviewed-on: http://review.gluster.org/12984
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: Currently even if we have received xattrs from any one of
the subvolume, we unwind with error in case the last subvol (which
unwinds) received a negative response.
To handle the case check if any of the subvolume has received
a response and pass it down.
Change-Id: Ia12a1f9671a6764f7550e6dc223324b1039fcc51
BUG: 1287539
Signed-off-by: Susant Palai <spalai@redhat.com>
Reviewed-on: http://review.gluster.org/12845
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
files deleted during promotion were not deleting as the
files are moving from hashed to non-hashed.
On deleting a file that is undergoing promotion,
the unlink call is not sent to the dst file as the
hashed subvol == cached subvol. This causes
the file to reappear once the migration is complete.
This patch also fixes a problem with stale linkfile
deleting.
Change-Id: I4b02a498218c9d8eeaa4556fa4219e91e7fa71e5
BUG: 1282390
Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
Reviewed-on: http://review.gluster.org/12829
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Due to the changes from http://review.gluster.org/#/c/12722/,
for tier volume the readirp will be send only to cold subvol,
therefore the resulting list may contain 'T' files. For those
files, by performing additional getattr call will populate the
attributes correctly. This check should be based on inode value
passed from the readdirp(both T files and directory have NULL
value) and skip directory in the same.
Change-Id: Ieb6724b05301cdbf0a0ef15ad9db51014faa0457
BUG: 1291212
Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com>
Reviewed-on: http://review.gluster.org/12960
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: soumya k <skoduri@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When the bad object is deleted (as of now manually from the backend itself),
along with its gfid handle, the entry for the bad object in the quarantne
directory is left as it is (it also can be removed manually though). But the
next lookup of the object upon not finding it in the backend, sends forget on
the in-memory inode. If the stale link for the gfid still exists in the
quarantine directory, bir-rot-stub will unlink the entry in its forget or in
the next failed lookup on that object with errno being ENOENT.
Change-Id: If84292d3e44707dfa11fa29023b3d9f691b8f0f3
BUG: 1285241
Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com>
Reviewed-on: http://review.gluster.org/12743
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|