| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
| |
xattr value has changed
Change-Id: Ia3225a523287f6689b966ba4f893fc1b1fa54817
BUG: 1272986
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12400
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is a series of patches which aims to fix geo-replication
in a Tiering Volume.
Problem:
Consider, a file is placed in volume initially and then hot tier is
attached. During any operation on the file, due to lookup a linkto
file is created in hot tier.
Now, any namespace operation carried out on the file is recorded in
both cold and hot tier.
There is a room for races when both changelogs are replayed.
Solution:
So, We are going to replay (namespace related)operations
only in the hot tier.
Why?
a. If the file is directly placed in Hot tier, all fops will be
recorded in HOT tier.
b. If the file is already present in Cold tier, and if any fop is
carried out, it creates linkto file in Hot tier.
Now, operations like UNLINK, RENAME are captured in Hot tier(by means of linkto file).
This way, we can get both tier's operation in HOT tier itself.
But, We may miss initial Data sync immediately after creating the
file as it is only recording MKNOD. So, if MKNOD encountered
with sticky bit set, queue DATA operation for the corresponding gfid.
( This geo-rep related changes are addressed in this patch: http://review.gluster.org/12326/ )
So, If tier-dht linkto is set, we need to record the corresponding
MKNOD. Earlier this was avoided as it was set as INTERNAL fop.
(This is addressed here in this patch)
Change-Id: I25514fe3e25f68592a8d6361507f8c8a4fcb70b1
BUG: 1266875
Signed-off-by: Saravanakumar Arumugam <sarumuga@redhat.com>
Reviewed-on: http://review.gluster.org/12417
Reviewed-by: Aravinda VK <avishwan@redhat.com>
Reviewed-by: Kotresh HR <khiremat@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Recording of tiering rebalance process's fops like Creation
and Deletion of file must be avoided.
Ignore the fops using corresponding pid.
Change-Id: Ifdc7765598d04d033f93e6339e9b188f7566cb65
BUG: 1266875
Signed-off-by: Saravanakumar Arumugam <sarumuga@redhat.com>
Reviewed-on: http://review.gluster.org/12239
Reviewed-by: Aravinda VK <avishwan@redhat.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Approach:
Shard xlator on slave side is by passed for all the fops
to geo-rep mount. So each shard on master is considered as a
separate file for geo-rep and it syncs them separately on to
slave. The extended attribute in which shard maintains the
size is also synced from master and shard on slave doesn't
calculate by itself.
Pre-requisites:
1. If master is sharded volume, slave also should be sharded.
2. Slave's shard configurations should be same as master.
3. Geo-rep config of xattr sync should not be disabled.
All other dependant patches:
1. http://review.gluster.org/#/c/12205/
2. http://review.gluster.org/#/c/12206/
3. http://review.gluster.org/#/c/12225/
4. http://review.gluster.org/#/c/12226/
Change-Id: I474220d69fa030b1e06a4fa0868c34fabe02efcf
BUG: 1265148
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/12228
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Correcting the internal fop calculation method, as it had wrong logic.
Change-Id: I1d0b40a1e27548147203ddd503794059652ac049
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/12418
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem : In svc_statfs function, wipe_loc is getting called on loc
passed by nfs. This loc is being used by svc_stat which
throws erro if loc->inode is NULL.
Solution : wipe_loc should be called on local root_loc.
Change-Id: I9cc5ee3b1bd9f352f2362a6d997b7b09051c0f68
BUG: 1260848
Signed-off-by: Ashish Pandey <aspandey@redhat.com>
Reviewed-on: http://review.gluster.org/12123
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>
|
|
|
|
|
|
|
|
|
|
| |
Change-Id: Idba1070b11c5c1de26ef57e6843c93c105b8b8a5
BUG: 1270694
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12340
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>
|
|
|
|
|
|
|
|
|
|
| |
Change-Id: I3c5e5bd93288c4c9a2665a26c0d6a76e67ecf914
BUG: 1270694
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12334
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Consider below scenario:
Quota enabled on pre-existing data
Now quota-crawl process will start healing xattrs
Now if write is performed where healing is not complete, there is a
possibility that 'update txn' is started before 'create xattr txn', in
this case dir count can be missed on a dir where quota size xattr is not
yet created.
Solution is to get size xattr and if xattr is missing, add 1 for
dir_count, this requires one additional fop if done in marker during
each update iteration
Better solution is to us xattrop GF_XATTROP_ADD_ARRAY64_WITH_DEFAULT
Change-Id: Idc8978860a3914e70c98f96effeff52e9a24e6ba
BUG: 1243798
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/11694
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Heal hardlink in the db for already existing data in the cold
tier during attach tier. i.e during fix layout do lookup to files
in the cold tier.
CTR xlator on the brick/server side does db update/insert of the hardlink on a namelookup.
Currently the namedlookup is done synchronous to the fixlayout that is
triggered by attach tier. This is not performant, adding more time to
fixlayout. The performant approach is record the hardlinks on a compressed
datastore and then do the namelookup asynchronously later, giving the ctr db
eventual consistency
Change-Id: I4ffc337fffe7d447804786851a9183a51b5044a9
BUG: 1252586
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/11828
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
objects
Shard translator will now maintain an lru list of inodes associated with
individual shards of constant size, and will make sure that at no point the
number of these inodes will exceed the configured limit.
This is to keep the memory consumption by the thousands of shards of every large
file from exploding.
Change-Id: I5e60eea5dcf3130257fb431ca70cfaba53cae7f3
BUG: 1252263
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12254
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Change-Id: I2076fcab51f4ecc529dffd89ca6ee9eb99d80f09
BUG: 1265531
Signed-off-by: Susant Palai <spalai@redhat.com>
Reviewed-on: http://review.gluster.org/12218
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Manikandan Selvaganesh <mselvaga@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
list head was not initialized and brick
was crashing with fallocate.
This patch fixes the issue
Change-Id: I9757b88eab61054892f0fe3de63af2683cd4fef7
BUG: 1269754
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/12314
Reviewed-by: Manikandan Selvaganesh <mselvaga@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
version less than 3.7 i.e rhel 6.7
Problem: On RHEL 6.7, we have sqlite version 3.6.2 which doesnt support
WAL journaling mode, as this journaling mode is only available in sqlite 3.7 and above.
As a result we cannot have to progreses concurrently accessing sqlite, without
running into db locks! Well WAL is also need for performace on CTR side.
Solution: This solution is to use CTR db connection for doing queries when WAL mode is
absent. i,e tier migrator will send sync_op ipc calls to CTR, which in turn will
do the query and create/update the query file suggested by tier migrator.
Pending: Well this solution will stop the db locks but the performance is still an issue for CTR.
We are developing an in-Memory Transaction Log (iMeTaL) which will help boost the CTR
performance by doing in memory udpates on the IO path and later flush the updates to
the db in a batch/segment flush.
Change-Id: Ie3149643ded159234b5cc6aa6cf93b9022c2f124
BUG: 1240577
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Signed-off-by: Dan Lambright <dlambrig@redhat.com>
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/12191
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Luis Pabon <lpabon@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
DHT re-balance, sets frame root PID < 0 and quota_check_limit skips
enforcement if this PID is less than 0.
When creating new frame for quota_check_limit we need to use
copy_frame instead of create_frame, so that all auth information
are copied from original frame.
Change-Id: Ib3b4a3744f8b0d72a8bc32826f6edae836d6faed
BUG: 1267812
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/12265
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>
|
|
|
|
|
|
|
|
|
|
|
|
| |
The change http://review.gluster.org/#/c/11938/ makes a fix in posix translator
which would cause sharding to fail fops post xattrop without this patch.
Change-Id: If096965b319f393608b0f763402b9b90acb61492
BUG: 1268796
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12300
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
marker is re-factored with syncop approach,
remove unused old code
Change-Id: I36e670e63b6c166db5e64d3149d2978981e2f7c2
BUG: 1240581
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/11560
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>
|
|
|
|
|
|
|
|
|
|
| |
Change-Id: Iac01e6a89a0d0c37a12a5e47f17f7ced85a31590
BUG: 1265516
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12217
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We've been lucky that we haven't had any symbol collisions until now.
Now we have a collision between the snapview-client's svc_lookup() and
libntirpc's svc_lookup() with nfs-ganesha's FSAL_GLUSTER and libgfapi.
As a short term solution all the snapview-client's FOP methods were
changed to static scope. See http://review.gluster.org/11805. This
works in snapview-client because all the FOP methods are defined in
a single source file. This solution doesn't work for other xlators
with FOP methods defined in multiple source files.
To address this we link with libtool's '-export-symbols $symbol-file'
(a wrapper around `ld --version-script ...` --- on linux anyway) and
only export the minimum required symbols from the xlator sharedlib.
N.B. the libtool man page says that the symbol file should be named
foo.sym, thus the rename of *.exports to *.sym. While foo.exports
worked, we will follow the documentation.
Signed-off-by: Kaleb S. KEITHLEY <kkeithle@redhat.com>
BUG: 1248669
Change-Id: I1de68b3e3be58ae690d8bfb2168bfc019983627c
Reviewed-on: http://review.gluster.org/11814
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is change 2/2 of the performance improvements for sharding.
The changes are with respect to maintaining up-to-date values of
file attributes in [f]stat, [f]setattr, link, and [f]truncate
codepaths.
Change-Id: Ia3ce4664fb33be869e4dc76494adbe9c314cc098
BUG: 1258905
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12138
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is patch 1/2 of the performance improvement work
for sharding in the IO path.
What this patch does:
Since the primary use-case where sharding is targeted -
VM store - is a single-writer workload, instead of
performing lookup on the base file everytime to gather the
size and block count from the backend in reads, writes and
truncate, now the size and block count is also cached and
kept up-to-date after every inode write in the inode ctx.
TO-DO:
Make changes in rename, link, unlink, [f]setattr and [f]stat
to keep the relevant iatt members up-to-date in the inode ctx.
Change-Id: Ica87d020dabc3a3dbccec814b26b01d6a629ff4d
BUG: 1258905
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12126
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
During a DHT re-balance operation, quota accounts for the destination.
Problem of accounting this destination file are:
1) Migration is an internal operation, 'quota list' shows more usage on the CLI
and this will come to the normal numbers once the migration is complete
2) If the usage is close to the limit set, then we can get 'Disk Quota
Exceeded' errors in the I/O path during file migration
Solution is we should not account of the usage on the destination file
during migration, at the end of the migration. We need to reduce size of
the source directory and accounting for the migrated dest file
We assume that there are sufficent disk space in the back-end. DHT
migrator should make sure that there are sufficient disk space before it
starts the migration process.
Change-Id: Ie3cfe3e4ab5241c2a127ba0edc599a053d30c3a0
BUG: 1260545
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/12113
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Removing the logically dead code as reported by coverity tool run
on GlusterFS.
The code changes are removal of logically dead code, hence did not
run the testcases.
CIDs Fixed starts from 1292652 to 1292663 in sequence.
Signed-off-by: Akhil Bhansali <bhansaliakhil@gmail.com>
Change-Id: I05b35f744c89b5e49b6322635c7a0d367ef10abb
BUG: 789278
Reviewed-on: http://review.gluster.org/12150
Reviewed-by: Anoop C S <anoopcs@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Also,
1) the getxattr() callback must check for the fop return status
before attempting to delete the internal keys.
2) the correct dict was not being used in shard_getxattr_cbk(). This
patch also fixes that issue.
Change-Id: I516a1d98e112b572bcec7d1f1e03e23152567be3
BUG: 1260637
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12136
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>
|
|
|
|
|
|
|
|
|
| |
Change-Id: I5f65c49484e44a05bb7df53c73869f89ad3392e0
BUG: 1261399
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12140
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Change-Id: I40e4a5dbd13d6c3d777e7e01f93dabc83e52b137
BUG: 1260637
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12121
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: The DB on the brick is been accessed by CTR, for write and
tier migrator, for read and write. The write from tier migrator is reseting
the heat counters after a cycle. Since we are using sqlite, two connections
trying to write would cause a db lock contention. As a result CTR used to fail
to update the db.
Solution: Using the same db connection of CTR for reseting the heat counters.
1) Introducted a new IPC FOP for CTR
2) After the query do a ipc syncop to the underlying client xlator associated
to the brick.
3) CTR in brick will catch the IPC FOP and cleat the heat counters.
Change-Id: I53306bfc08dcdba479deb4ccc154896521336150
BUG: 1260730
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/12031
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The svs_glfs_readdir() is a generic function which is called from
svs_readdir() and svs_readdirp(). But in svs_readdir 'buf' variable
is passed as NULL, then glfs_read_readdir() will fail. This patch
will fix the same.
Change-Id: Id02e4e17e30c85de117db5ddd9f97b578622dff9
BUG: 1260611
Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com>
Reviewed-on: http://review.gluster.org/12117
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Change-Id: I31ac99b290f82f4b74236c206193f7641c73d4dc
BUG: 1259651
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12099
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
There are three kinds of inline functions: plain inline, extern inline,
and static inline. All three have been removed from .c files, except
those in "contrib" which aren't our problem. Inlines in .h files, which
are overwhelmingly "static inline" already, have generally been left
alone. Over time we should be able to "lower" these into .c files, but
that has to be done in a case-by-case fashion requiring more manual
effort. This part was easy to do automatically without (as far as I can
tell) any ill effect.
In the process, several pieces of dead code were flagged by the
compiler, and were removed.
Change-Id: I56a5e614735c9e0a6ee420dab949eac22e25c155
BUG: 1245331
Signed-off-by: Jeff Darcy <jdarcy@redhat.com>
Reviewed-on: http://review.gluster.org/11769
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
Reviewed-by: Niels de Vos <ndevos@redhat.com>
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Unlink of a sharded file with holes was leading to EINVAL errors
because it was being wound on non-existent shards (those blocks that
fall in the hole region). loc->inode was NULL in these cases and
dht_unlink used to fail the FOP with EINVAL for failure to fetch
cached subvol for the inode.
The fix involves winding unlink on only those shards whose corresponding
inodes exist in memory.
Change-Id: I993ff70cab4b22580c772a9c74fc19ac893a03fc
BUG: 1258334
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12059
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>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch does the following:
* reverts commit b467af0e99b39ef708420d3f7f6696b0ca618512
* changes ownership on shards under /.shard to be root:root
* makes readv, writev, [f]truncate, rename, and unlink fops
to perform operations on files under /.shard with
frame->root->{uid,gid} as 0.
This would ensure that a [f]setattr on a sharded file
does not need to be called on all the shards associated with it.
Change-Id: Idcfb8c0dd354b0baab6b2356d2ab83ce51caa20e
BUG: 1251824
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/11992
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>
|
|
|
|
|
|
|
|
|
|
| |
Change-Id: Iceccef8f3f466c7ffb9991f8eb248b81e7b80efb
BUG: 1256580
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/12020
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In case if dir has become dirty because of brick crash,
this dirty flag on disk was getting reset in the
next update txn.
This patch now gets the dirty flag before setting the flag
in the update txn and if this value is dirty, it keeps
the flag dirty, so that inspect_directory can fix the
dirty dir
Change-Id: Iab2c343dbe19bd3b291adbfeebe6d9785b6bb9e3
BUG: 1251454
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/12032
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- fd_unref should decrement fd->inode->fd_count only if it is present in the
inode's fd list.
- successful open/opendir should perform fd_bind.
Change-Id: I81dd04f330e2fee86369a6dc7147af44f3d49169
BUG: 1207735
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: http://review.gluster.org/11044
Reviewed-by: Anoop C S <anoopcs@redhat.com>
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch does the following
1) Set loc.parent if it is NULL
Don't log warning in txn if parent is NULL
2) Don't initiate txn when inode gfid is NULL
3) optimize invoking dirty txn with status flag
Change-Id: I67dd9e6268014b0b257c136e951e6ded0a2e911f
BUG: 1251454
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/11863
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Few of the snapshot fops (like 'svc_lookup') may not get resolved
while using dynamic loading as there could be other libraries(like libntirpc)
with same routine names. Making them static to resolve the same.
Change-Id: I6577bf3705864f5583425c94427b4e1025a59bcd
BUG: 1248669
Signed-off-by: Soumya Koduri <skoduri@redhat.com>
Reviewed-on: http://review.gluster.org/11805
Reviewed-by: Niels de Vos <ndevos@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Rajesh Joseph <rjoseph@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previously glfs_h_lookupat won't follow the symlink, this patch
introduces new flag `follow` which will resolve the same. Applications
linking against the new library will need to use the new glfs_h_lookupat
API call.
In order to stay compatible with existing binaries that use the previous
glfs_h_lookupat() function, the old symbol needs to stay available.
Verification that there are two versions of glfs_h_lookupat:
$ objdump -T /usr/lib64/libgfapi.so.0 | grep -w glfs_h_lookupat
0000000000015070 g DF .text 000000000000021e GFAPI_3.7.4 glfs_h_lookupat
0000000000015290 g DF .text 0000000000000008 (GFAPI_3.4.2) glfs_h_lookupat
Testing with a binary (based on anonymous_fd_read_write.c from ./tests/)
that was linked against the old library:
$ objdump -T ./lookupat | grep -w glfs_h_lookupat
0000000000000000 DF *UND* 0000000000000000 GFAPI_3.4.2 glfs_h_lookupat
Enable debugging for 'ld.so' so that we can check that the GFAPI_3.4.2
version of the symbol gets loaded:
$ export LD_DEBUG_OUTPUT=lookupat.ld.log LD_DEBUG=all
$ ./lookupat
$ grep -w glfs_h_lookupat lookupat.ld.log.2543
2543: symbol=glfs_h_lookupat; lookup in file=./lookupat [0]
2543: symbol=glfs_h_lookupat; lookup in file=/lib64/libgfapi.so.0 [0]
2543: binding file ./lookupat [0] to /lib64/libgfapi.so.0 [0]: normal symbol `glfs_h_lookupat' [GFAPI_3.4.2]
Change-Id: I8bf9b1c19a0585f681bc1a7f84aad1ccd0f75f6a
BUG: 1252410
Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com>
Signed-off-by: Niels de Vos <ndevos@redhat.com>
Reviewed-on: http://review.gluster.org/11883
Reviewed-by: soumya k <skoduri@redhat.com>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When bitrot is configured on multiple volumes
in a cluster and scrubber-frequency is changed
for one volume, it is resetting frequency for
all other volumes w.r.t to its scrubber-frequency.
This should not happen. Changing scrubber-frequency
should affect only that volume on which it is set.
This patch fixes the issue.
Also restricted the logs to the configure volume.
Change-Id: I90d6e864b131e3d8dd4010079a00f924032f2098
BUG: 1252825
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/11897
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
If bad file detected by scrubber then scrubber should log that bad
file as a ALERT message in scrubber log.
Change-Id: I410429e78fd3768655230ac028fa66f7fc24b938
BUG: 1240218
Signed-off-by: Gaurav Kumar Garg <ggarg@redhat.com>
Reviewed-on: http://review.gluster.org/11965
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
There are three problems with marker-rename which
is fixed in this patch
Problem 1)
1) mq_reduce_parent_size is not handling inode-quota contribution
2) When dest files exists and IO is happening
Now renaming will overwrite existing file
mq_reduce_parent_size called on dest file
with saved contribution, this can be
a problem is IO is still happening
contribution might have changed
Problem 2)
There is a small race between rename and in-progress write
Consider below scenario
1) rename FOP invoked on file 'x'
2) write is still in progress for file 'x'
3) rename takes a lock on old-parent
4) write-update txn blocked on old-parent to acquire lock
5) in rename_cbk, contri xattrs are removed and contribution is deleted and
lock is released
6) now write-update txn gets the lock and updates the wrong parent
as it was holding lock on old parent
so validate parent once the lock is acquired
Problem 3)
when a rename operation is performed, a lock is
held on old parent. This lock is release before
unwinding the rename operation.
This can be a problem if there are in-progress
writes happening during rename, where update txn
can take a lock and update the old parent
as inode table is not updated with new parent
Change-Id: Ic3316097c001c33533f98592e8fcf234b1ee2aa2
BUG: 1240991
Signed-off-by: vmallika <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/11578
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
original file
Change-Id: Id759af8f3ff5fd8bfa9f8121bab25722709d42b7
BUG: 1251824
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/11874
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The @owner argument tells RPC layer the xlator that owns
the connection and to which xlator THIS needs be set during
network notifications like CONNECT and DISCONNECT.
Code paths that originate from the head of a (volume) graph and use
STACK_WIND ensure that the RPC local endpoint has the right xlator saved
in the frame of the call (callback pair). This guarantees that the
callback is executed in the right xlator context.
The client handshake process which includes fetching of brick ports from
glusterd, setting lk-version on the brick for the session, don't have
the correct xlator set in their frames. The problem lies with RPC
notifications. It doesn't have the provision to set THIS with the xlator
that is registered with the corresponding RPC programs. e.g,
RPC_CLNT_CONNECT event received by protocol/client doesn't have THIS set
to its xlator. This implies, call(-callbacks) originating from this
thread don't have the right xlator set too.
The fix would be to save the xlator registered with the RPC connection
during rpc_clnt_new. e.g, protocol/client's xlator would be saved with
the RPC connection that it 'owns'. RPC notifications such as CONNECT,
DISCONNECT, etc inherit THIS from the RPC connection's xlator.
Change-Id: I9dea2c35378c511d800ef58f7fa2ea5552f2c409
BUG: 1235582
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/11436
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
While rescheduling scrub frequency, boot time of
the brick was considered where it is not required
and also delta is calculated using unsigned int
resulting in the loss of fractional part leading to
wrong scrub frequency. Boot time is completely
removed and delta calculation is simplified.
Change-Id: If54697389f663afc86408dc8a01a3ea07e00f2dc
BUG: 1251042
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/11853
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>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The only place where shard translator was initialising inode ctx
was lookup callback. But if the inodes are created and linked through
readdirp, shard_lookup() path _may_ not be exercised before FUSE
winds other fops on them. Since shard translator does an
inode_ctx_get() first thing in most fops, an uninitialised ctx could
cause it to fail the operation with ENOMEM.
The solution would be to also initialise inode ctx if it has not been
done already in readdir(p) callback.
Change-Id: I3e058cd2a29bc6a69a96aaac89165c3251315625
BUG: 1250855
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/11854
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Change-Id: Ic7f842acca52908fd88e0796dc90b82650405b25
BUG: 1194640
Signed-off-by: Anusha Rao <anusha91rao@gmail.com>
Reviewed-on: http://review.gluster.org/10532
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>
Reviewed-by: Kotresh HR <khiremat@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In stub, for fops like readv, writev etc, if the the object is bad, then the fop
is denied. But for checking if the object is bad inode context should be
checked. Now, if the inode context is not there, then the fop is allowed to
continue. This patch fixes it and the fop is unwound with an error, if the inode
context is not found.
Change-Id: I5ea4d4fc1a91387f7f9d13ca8cb43c88429f02b0
BUG: 1243391
Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com>
Reviewed-on: http://review.gluster.org/11449
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Venky Shankar <vshankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
On enabling features.shard on a volume which already has few files,
performing operations on the mount was causing excessive logging of
messages of the following kind:
[2015-08-05 10:57:48.743352] E [shard.c:232:shard_modify_size_and_block_count]
2-dis-shard: Failed to get trusted.glusterfs.shard.file-size for
0b2bd401-c438-4d57-8ae5-8d26105d3396
Turns out this is coming from shard_readdir_cbk() where the shard
translator unconditionally looks for the xattr
'trusted.glusterfs.shard.file-size' in every entry's rsp dict and
logs this error on not finding it. But files that are not sharded
(i.e., the ones that were created before sharding was enabled on the volume)
will not (and should not) have this xattr associated with them.
So these logs are misleading and must be suppressed in readdir(p).
Change-Id: I8d268b4f90a8bf744c7851f1984f5a1b6968fb6a
BUG: 1250441
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/11843
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
| |
This reverts commit 871000e3ddb457c9cc5757cd94cfc178e3c1be29.
Change-Id: I05913151d9cb4c50057e5e72859768085041bdc9
Reviewed-on: http://review.gluster.org/11821
Tested-by: Kaleb KEITHLEY <kkeithle@redhat.com>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Smoke tests run on a new slave on Fedora 22 fail because make install
try to install the python package in /usr/lib/python2.7 without being
root, because there is no $DESTDIR support for that part.
Change-Id: Ibed17dd091a96fbdf5536ac66b8c876b33a39cd6
Signed-off-by: Michael Scherer <mscherer@redhat.com>
Reviewed-on: http://review.gluster.org/11813
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
|