| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: In case of error(ESTALE/ENOENT) dht_revalidate_cbk
throws "dict is null" error because xattr is not available
Solution: To avoid the logs update condition in dht_revalidate_cbk
and dht_lookup_dir_cbk
BUG: 1583565
Change-Id: Ife6b3eeb6d91bf24403ed3100e237bb5d15b4357
fixes: bz#1583565
Signed-off-by: Mohit Agrawal <moagrawa@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
An entry from readdirp might get renamed just before migration leading to
lookup failures. For such lookup failure, remove-brick process does not
see any increment in failure count. Though there is a warning message
after remove-brick commit for the user to check in the decommissioned brick
for any files those are not migrated, it's better to increase the failure count
so that user can check in the decommissioned bricks for files before commit.
Note: This can result in false negative cases for rm -rf interaction with
remove-brick op, where remove-brick shows non-zero failed count, but the
entry was actually deleted by user.
Fixes :bz#1580269
Change-Id: Icd1047ab9edc1d5bfc231a1f417a7801c424917c
fixes: bz#1580269
Signed-off-by: Susant Palai <spalai@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
Corrected the name of the xattr and fixed
the code to log an error only if op_errno
is not ENODATA or ENOATTR.
Change-Id: I42c5b1d838eec586ac7bed2471eb1d27ff09a9ea
fixes: bz#1580238
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Multiple pre-op xattrop can be simultaneously being processed. On the cbk
it was checked if the fop was waiting for some specific data (like size and
version) and, if so, it was assumed that this answer should contain that
data.
This is not true, since a fop can be waiting for some data, but it may come
from the xattrop of another fop.
This patch differentiates between needing some information and providing it.
This is related to parallel writes. Disabling them fixed the problem, but
also prevented concurrent reads. A change has been made so that disabling
parallel writes still allows parallel reads.
Fixes: bz#1578325
Change-Id: I74772ad6b80b7b37805da93d5ec3ae099e96b041
Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
In the .t, when the only good brick was brought down, writes on the fd were
still succeeding on the bad bricks. The inflight split-brain check was
marking the write as failure but since the write succeeded on all the
bad bricks, afr_txn_nothing_failed() was set to true and we were
unwinding writev with success to DHT and then catching the failure in
post-op in the background.
Fix:
Don't wind the FOP phase if the write_subvol (which is populated with readable
subvols obtained in pre-op cbk) does not have at least 1 good brick which was up
when the transaction started.
Note: This fix is not related to brick muliplexing. I ran the .t
10 times with this fix and brick-mux enabled without any failures.
Change-Id: I915c9c366aa32cd342b1565827ca2d83cb02ae85
updates: bz#1577672
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In the past, it was often[1] forgotten for xlators to be linked against
the symbols they refer to. This often caused glusterd2 to fail while
loading xlator's shared object (.so) file.
This change adds "--no-undefined" as a linker flag which causes the
linker to treat unresolved symbol references as an error and hence fail
linking.
[1]:
https://review.gluster.org/#/c/19912/
https://review.gluster.org/#/c/19664/
https://review.gluster.org/#/c/19056/
https://review.gluster.org/#/c/17659/
https://bugzilla.redhat.com/show_bug.cgi?id=1532238
Bonus:
Added cloudsync and utime xlator's generated source files to .gitignore
Updates: bz#1193929
Change-Id: I9604a4a87b7313a5fa43bda5fdb37dfa7ef8facd
Signed-off-by: Prashanth Pai <ppai@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Removed EIO from the list of errnos that triggered
a migrate check task.
Change-Id: I7f89c7a16056421588f1af2377cebe6affddcb47
fixes: bz#1578823
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: In Geo-Rep setup excessive "dict is null" logs in
dht_discover_complete while xattr is NULL
Solution: To avoid the logs update a condition in dht_discover_complete
BUG: 1576767
Change-Id: Ic7aad712d9b6d69b85b76e4fdf2881adb0512237
fixes: bz#1576767
Signed-off-by: Mohit Agrawal <moagrawa@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Provide a virtual xattr with which to query
the hashed subvol for a file.
Change-Id: Ic7abd031f875da4b9084841ea7c25d6c8a851992
fixes: bz#1574421
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Additional log messages to help debug issues
with file listings.
Change-Id: Iccd07498ba01d597c0c40f026f4177dd06d7e901
fixes: bz#1575887
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: Before populate MDS internal xattr first dht checks if MDS is
present in xattr or not.If xattr dictionary is NULL dict_get
log the message either dict or key is NULL
Solution: Before call dict_get check xattr, if it is NULL then no
need to call dict_get.
BUG: 1575910
Change-Id: I81604ec5945b85eba14b42f4583d06ec713028f4
fixes: bz#1575910
Signed-off-by: Mohit Agrawal <moagrawa@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Test case:
# while true; do uuid="`uuidgen`"; echo "some data" > "test$uuid"; mv
"test$uuid" "test" -f || break; echo "done:$uuid"; done
This script was run in parallel from multiple mountpoints
Along the course of getting the above usecase working, many issues
were found:
Issue 1:
=======
consider a case of rename (src, dst). We can encounter a situation
where,
* dst is a file present at the time of lookup
* dst is removed by the time rename fop reaches glusterfs
In this scenario, acquring inodelk on dst fails with ESTALE resulting
in failure of rename. However, as per POSIX irrespective of whether
dst is present or not, rename should be successful. Acquiring entrylk
provides synchronization even in races like this.
Algorithm:
1. Take inodelks on src and dst (if dst is present) on respective
cached subvols. These inodelks are done to preserve backward
compatibility with older clients, so that synchronization is
preserved when a volume is mounted by clients of different
versions. Once relevant older versions (3.10, 3.12, 3.13) reach
EOL, this code can be removed.
2. Ignore ENOENT/ESTALE errors of inodelk on dst.
3. protect namespace of src and dst. To protect namespace of a file,
take inodelk on parent on hashed subvol, then take entrylk on the
same subvol on parent with basename of file. inodelk on parent is
done to guard against changes to parent layout so that hashed
subvol won't change during rename.
4. <rest of rename continues>
5. unlock all locks
Issue 2:
========
linkfile creation in lookup codepath can race with a rename. Imagine
the following scenario:
* lookup finds a data-file with gfid - gfid-dst - without a
corresponding linkto file on hashed-subvol. It decides to create
linkto file with gfid - gfid-dst.
- Note that some codepaths of dht-rename deletes linkto file of
dst as first step. So, a lookup racing with an in-progress
rename can easily run into this situation.
* a rename (src-path:gfid-src, dst-path:gfid-dst) renames data-file
and hence gfid of data-file changes to gfid-src with path dst-path.
* lookup proceeds and creates linkto file - dst-path - with gfid -
dst-gfid - on hashed-subvol.
* rename tries to create a linkto file dst-path with src-gfid on
hashed-subvol, but it fails with EEXIST. But EEXIST is ignored
during linkto file creation.
Now we've ended with dst-path having different gfids - dst-gfid on
linkto file and src-gfid on data file. Future lookups on dst-path will
always fail with ESTALE, due to differing gfids.
The fix is to synchronize linkfile creation in lookup path with rename
using the same mechanism of protecting namespace explained in solution
of Issue 1. Once locks are acquired, before proceeding with linkfile
creation, we check whether conditions for linkto file creation are
still valid. If not, we skip linkto file creation.
Issue 3:
========
gfid of dst-path can change by the time locks are acquired. This
means, either another rename overwrote dst-path or dst-path was
deleted and recreated by a different client. When this happens,
cached-subvol for dst can change. If rename proceeds with old-gfid and
old-cached subvol, we'll end up in inconsistent state(s) like dst-path
with different gfids on different subvols, more than one data-file
being present etc.
Fix is to do the lookup with a new inode after protecting namespace of
dst. Post lookup, we've to compare gfids and correct local state
appropriately to be in sync with backend.
Issue 4:
========
During revalidate lookup, if following a linkto file doesn't lead to a
valid data-file, local->cached-subvol was not reset to NULL. This
means we would be operating on a stale state which can lead to
inconsistency. As a fix, reset it to NULL before proceeding with
lookup everywhere.
Issue 5:
========
Stale dentries left out in inode table on brick resulted in failures
of link fop even though the file/dentry didn't exist on backend fs. A
patch is submitted to fix this issue. Please check the dependency tree
of current patch on gerrit for details
In short, we fix the problem by not blindly trusting the
inode-table. Instead we validate whether dentry is present by doing
lookup on backend fs.
Change-Id: I832e5c47d232f90c4edb1fafc512bf19bebde165
updates: bz#1543279
BUG: 1543279
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
selfhealing of directory is invoked on two conditions:
1. no layout on disk or layout has some anomalies (holes/overlaps)
2. mds xattr is not set on the directory
When dht_selfheal_directory is called with a correct layout just to
set mds xattr, we see error msgs complaining about "not able to form
layout on directory", which is misleading as the layout is
correct. So, log this msg only if layout has anomalies.
Change-Id: I4af25246fc3a2450c2426e9902d1a5b372eab125
updates: bz#1543279
BUG: 1543279
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
| |
Change-Id: Ied047dd5ee44e9d5a5d3db214826f7df30332ef9
updates: #350
BUG: 1319992
Signed-off-by: Poornima G <pgurusid@redhat.com>
Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
If dht_selfheal_dir_mkdir returns an error, cbk passed to
dht_selfheal_directory is not invoked. So, Current codepath leaves an
unwound frame resulting in a hung fop forever.
Change-Id: I422308b8a34a074301ca46b029ffe676f5e0f66c
fixes: bz#1574305
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: A directory deletion can happen just before gf_defrag_settle_hash
which internally does a setxattr operation on a directory.
Solution: Ignore ENOENT and ESTALE errors
Fixes: bz#1572581
Change-Id: I2f91809f3b5e02976c4c3a5a596406a8b2f8f6f2
Signed-off-by: Susant Palai <spalai@redhat.com>
|
|
|
|
|
|
|
| |
Updates #352
Change-Id: I1bbb3c652ba33cec6aa37f3700370674077fb17d
Signed-off-by: karthik-us <ksubrahm@redhat.com>
|
|
|
|
|
|
|
|
|
| |
1. Create thin arbiter index file during mount.
2. Set pending marker in thin arbiter id file in case of failure.
Change-Id: I269eb8d069f0323f1fc616175e5e5eb7b91d5f82
updates: #352
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
Currently it is not possible to capture the xattrs values which
are set on the bricks by calling syncop_(f)xattrop, because the
response dict is not being assigned to any of the dictionaries.
Fix:
In the xattrop callback capture the response dict and send it
back to the caller if it is requested.
Change-Id: I9de9bcd97d6008091c9b060bcca3676cb9ae8ef9
fixes: bz#1572076
Signed-off-by: karthik-us <ksubrahm@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
If we have 2 bricks, brick-A and brick-B with brick-A within halo-max-latency
and brick-B more than halo-max-latency. If we set both halo-min, halo-max replicas
as '1'. In this case, brick-A comes online and then ping-latency will be updated for it.
When brick-B comes online, we have 2 up-bricks, so the code tries to find the brick with
worst latency to mark it down. Since Brick-B just came online it always had '0' latency
so brick-B used to be marked offline and Brick-B would eventually be the one to be
online even when brick-A is more suited.
Fix:
Consider latency of just-up child as HALO_MAX_LATENCY so that worst-child until
ping-latency is found as the just-up brick. Also keep ping-latency as -1 until
child-up during initialization.
BUG: 1567881
fixes bz#1567881
Change-Id: I148262fe505468190f0eb99225d0f6d57cdb6f04
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
Fixed dht_order_rename_lock to use the same inodelk ordering
as that of the dht selfheal locks (dictionary order of
lock subvolumes).
Change-Id: Ia3f8353b33ea2fd3bc1ba7e8e777dda6c1d33e0d
fixes: bz#1568348
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
| |
In Halo replication, there are pending heals more often than not.
It makes sense to give users the capability to configure it as low
as 5 seconds.
BUG: 1569489
fixes bz#1569489
Change-Id: I451c1975827f66398b903f659c981ef3121d5376
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
problem: With the current code, post graph switch the old fd is received for
fuse_getattr and since it is associated with old inode, it does not
have the inode ctx across xlators in new graph. Hence, dht
errored out saying "no layout" for fstat call. Hence the EINVAL.
Solution: if fd is passed, init and resolve fd to carry on getattr
test case:
- Created a single brick distributed volume
- Started untar
- Added a new-brick
Without this fix, untar used to abort with ERROR.
Change-Id: I5805c463fb9a04ba5c24829b768127097ff8b9f9
fixes: bz#1566207
Signed-off-by: Susant Palai <spalai@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
| |
xlator_notify doesn't pass the extra arguments that come in the
input function, so XLATOR_NOTIFY macro should be used instead
to pass the extra arguments to the function.
BUG: 1567881
fixes bz#1567881
Change-Id: Ic15b6c446638cbacf3149693147a754219037c47
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1. If pre-op fails on all bricks,set lock->release to true in
afr_handle_lock_acquire_failure so that the GF_ASSERT in afr_unlock() does not
crash.
2. Added a missing 'return' after handling pre-op failure in
afr_transaction_perform_fop(), fixing a use-after-free issue.
Change-Id: If0627a9124cb5d6405037cab3f17f8325eed2d83
fixes: bz#1561129
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The decision as to which node would migrate a file
was based on the gfid of the file. Files were divided
among the nodes for the replica/disperse set. However,
if a brick was down when rebalance started, the nodeuuids
would be saved as NULL and a set of files would not be migrated.
Now, if the nodeuuid is NULL, the first non-null entry in
the set is the node responsible for migrating the file.
Change-Id: I72554c107792c7d534e0f25640654b6f8417d373
fixes: bz#1564198
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
dht_opendir should wind the open to all subvols
whether or not local->subvols is set. This is
because dht_readdirp winds the calls to all subvols.
Change-Id: I67a96b06dad14a08967c3721301e88555aa01017
updates: bz#1564198
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
Various synchronization present in dht_rename while handling
directories and files is necessary only if we have more than only one
child.
Change-Id: Ie21ad419125504ca2f391b1ae2e5c1d166fee247
fixes: bz#1563511
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
| |
Change-Id: I0a290396c30c635b13ee73004d20259efb76a954
fixes: bz#1563945
Signed-off-by: Ashish Pandey <aspandey@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
We seem to be winding the FOP if pre-op did not succeed on quorum bricks
and then failing the FOP with EROFS since the fop did not meet quorum.
This essentially masks the actual error due to which pre-op failed. (See
BZ).
Fix:
Skip FOP phase if pre-op quorum is not met and go to post-op.
Fixes: 1561129
Change-Id: Ie58a41e8fa1ad79aa06093706e96db8eef61b6d9
fixes: bz#1561129
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Lookup-optimize has been shown to improve create
performance. The code has been in the project for several
years and is considered stable.
Enabling this by default in order to test this in the
upstream regression runs.
Change-Id: Iab792979ee34f0af4713931e0b5b399c23f65313
updates: bz#1557435
BUG: 1557435
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
| |
On shd, we shouldn't treat any brick down based
on latency, otherwise self-heal will never happen
fixes: bz#1562717
Change-Id: Ica07fcc4fae91a6bfd9c9a670e2be464704d94b7
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Set the levels for DHT options based on
https://review.gluster.org/#/c/19466/
Change-Id: I51b31a706a0b9517404e83224c89de145fd5d7e1
updates: #430
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
With lookup-optimize enabled, gf_defrag_settle_hash in rebalance
sometimes flips the on-disk layout on volume root post the
migration of all files in the directory.
This is sometimes seen when attempting to fix the layout of a
directory multiple times before calling gf_defrag_settle_hash.
dht_fix_layout_of_directory generates a new layout in memory but
updates it in the inode ctx before it is set on disk. The layout
may be different the second time around due to
dht_selfheal_layout_maximize_overlap. If the layout is then not
written to the disk, the inode now contains the wrong layout.
gf_defrag_settle_hash does not check the correctness of the layout
in the inode before updating the commit-hash and writing it to the
disk thus changing the layout of the directory.
Change-Id: Ie1407d92982518f2a0c40ec70ad370b34a87b4d4
updates: bz#1557435
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
Updates: #363
This new value (3) will try to wind read requests to the child of AFR
having the least amount of pending requests in its queue.
Change-Id: If6bda2aac9bf7aec3fc39622f78659313c4b6508
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
The xattr trusted.glusterfs.list-node-uuids was only sent to a single
subvolume. This was returning null uuids from the other subvolumes as
if they were down.
This fix forces that xattr to be requested from all subvolumes.
Change-Id: If62eb39a6857258923ba625e153d4ad79018ea2f
fixes: bz#1561406
Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
|
|
|
|
|
|
|
|
|
| |
ENOSPC returned by a file migration is no longer
considered a rebalance failure.
Change-Id: I21cf3a8acdc827bc478e138d6cb5db649d53a28c
fixes: bz#1553598
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem: if a lookup is done on a newly added brick for a path on which limit
has been reached, the lookup fails to heal the directory tree due to quota.
Solution: Tag the lookup as an internal fop and ignore it in quota.
Since marking internal fop does not usually give enough contextual information.
Introducing new flags to pass the contextual info.
Adding dict_check_flag and dict_set_flag to aid flag operations.
A flag is a single bit in a bit array (currently limited to 256 bits).
Change-Id: Ifb6a68bcaffedd425dd0f01f7db24edd5394c095
fixes: bz#1505355
BUG: 1505355
Signed-off-by: Sanoj Unnikrishnan <sunnikri@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When the self-heal daemon is doing a full sweep it uses readdirp to
get extra stat information from each file. This information is
obtained in two steps by the posix xlator: first the directory is
read to get the entries and then each entry is stated to get additional
info. Between these two steps, it's possible that the file is removed
by the user, so we'll get an error, leaving stat info empty.
EC's heal daemon was using the gfid blindly, causing an assert failure
when protocol/client was trying to encode the gfid.
To fix the problem a check has been added. If we detect a null gfid, we
simply ignore it and continue healing.
Change-Id: I2e4acdcecd0b6951055e50d1c37d686a2186a228
BUG: 1558016
Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
|
|
|
|
|
|
| |
BUG: 1557932
Change-Id: I3783e41b3812267bc10c0d05d062a31396ce135b
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
1) Afr's eager-lock only works for data transactions.
2) When there are conflicting writes, write with conflicting region initiates
unlock of eager-lock leading to extra pre-ops and post-ops on the file. When
eager-lock goes off, it leads to extra fsyncs for random-write workload in afr.
Solution (that is modeled after EC):
In EC, when there is a conflicting write, it waits for the current write to
complete before it winds the conflicted write. This leads to better utilization
of network and disk, because we will not be doing extra xattrops and FSYNCs and
inodelk/unlock. Moved fd based counters to inode based counters.
I tried to model the solution based on EC's locking, but it is not similar to
AFR because we had to keep backward compatibility.
Lifecycle of lock:
==================
First transaction is added to inode->owners list and an inodelk will be sent on
the wire. All the next transactions will be put in inode->waiters list until
the first transaction completes inodelk and [f]xattrop completely. Once
[f]xattrop also completes, all the requests in the inode->waiters list are
checked if it conflict with any of the existing locks which are in
inode->owners list and if not are added to inode->owners list and resumed with
doing transaction. When these transactions complete fop phase they will be
moved to inode->post_op list and resume the transactions that were paused
because of conflicts. Post-op and unlock will not be issued on the wire until
that is the last transaction on that inode. Last transaction when it has to
perform post-op can choose to sleep for deyed-post-op-secs value. During that
time if any other transaction comes, it will wake up the sleeping transaction
and takes over the ownership of the lock and the cycle continues. If the
dealyed-post-op-secs expire, then the timer thread will wakeup the sleeping
transaction and it will set lock->release to true and starts doing post-op and
then unlock. During this time if any other transactions come, they will be put
in inode->frozen list. Once the previous unlock comes it will move the frozen
list to waiters list and moves the first element from this waiters-list to
owners-list and attempts the lock and the cycle continues. This is the general
idea. There is logic at the time of dealying and at the time of new
transaction or in flush fop to wakeup existing sleeping transactions or
choosing whether to delay a transaction etc, which is subjected to change based
on future enhancements etc.
Fixes: #418
BUG: 1549606
Change-Id: I88b570bbcf332a27c82d2767dfa82472f60055dc
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Problem:
Whenever we read data from file over NFS, NFS reads
more data then requested and caches it. Based on the
stat information it makes sure that the cached/pre-read
data is valid or not.
Consider 4 + 2 EC volume and all the bricks are on
differnt nodes.
In EC, with round-robin read policy, reads are sent on
different set of data bricks. This way, it balances the
read fops to go on all the bricks and avoid heating UP
(overloading) same set of bricks.
Due to small difference in clock speed, it is possible
that we get minor difference for atime, mtime or ctime
for different bricks. That might cause a different stat
returned to NFS based on which NFS will discard
cached/pre-read data which is actually not changed and
could be used.
Solution:
Change read policy for EC as gfid-hash. That will force
all the read to go to same set of bricks.
Change-Id: I825441cc519e94bf3dc3aa0bd4cb7c6ae6392c84
BUG: 1554743
Signed-off-by: Ashish Pandey <aspandey@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Self-heal creates a thread per brick to sweep the index looking for
files that need to be healed. These threads are started before the
volume comes online, so nothing is done but waiting for the next
sweep. This happens once per minute.
When a replace brick command is executed, the new graph is loaded and
all index sweeper threads started. When all bricks have reported, a
getxattr request is sent to the root directory of the volume. This
causes a heal on it (because the new brick doesn't have good data),
and marks its contents as pending to be healed. This is done by the
index sweeper thread on the next round, one minute later.
This patch solves this problem by waking all index sweeper threads
after a successful check on the root directory.
Additionally, the index sweep thread scans the index directory
sequentially, but it might happen that after healing a directory entry
more index entries are created but skipped by the current directory
scan. This causes the remaining entries to be processed on the next
round, one minute later. The same can happen in the next round, so
the heal is running in bursts and taking a lot to finish, specially
on volumes with many directory levels.
This patch solves this problem by immediately restarting the index
sweep if a directory has been healed.
Change-Id: I58d9ab6ef17b30f704dc322e1d3d53b904e5f30e
BUG: 1547662
Signed-off-by: Xavi Hernandez <jahernan@redhat.com>
|
|
|
|
|
|
|
|
|
| |
For skipped files, use a return value of 1 to prevent
error messages being logged.
Change-Id: I18de31ac1a64d4460e88dea7826c3ba03c895861
BUG: 1553598
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Removed
1) afr-v1 self-heal locks related code which is not used anymore
2) transaction has some data types that are not needed, so removed them
3) Never used lock tracing available in afr as gluster's network tracing does
the job. So removed that as well.
4) Changelog is always enabled and afr is always used with locks, so
__changelog_enabled, afr_lock_server_count etc functions can be deleted.
5) transaction.fop/done/resume always call the same functions, so no need
to have these variables.
BUG: 1549606
Change-Id: I370c146fec2892d40e674d232a5d7256e003c7f1
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
| |
We are not seeing much improvement with this change. So removing the
feature so that it doesn't need to be maintained anymore.
Fixes: #414
Change-Id: Ic7969b151544daf2547bd262a9fa03f575626411
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
| |
Change-Id: I713401feb96393f668efb074f2d5b870d19e6fda
BUG: 1548361
Signed-off-by: karthik-us <ksubrahm@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
At the time of pre-op, pre_op_xdata is populted with the xattrs we get from the
disk and at the time of post-op it gets over-written without unreffing the
previous value stored leading to a leak.
This is a regression we missed in
https://review.gluster.org/#/q/ba149bac92d169ae2256dbc75202dc9e5d06538e
BUG: 1550078
Change-Id: I0456f9ad6f77ce6248b747964a037193af3a3da7
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Currently its passed in dht_blocking_inode(entry)lk, which would be a
global value for all the locks passed in the argument. This would
be a limitation for cases where we want to ignore failures on only few
locks and fail for others.
Change-Id: I02cfbcaafb593ad8140c0e5af725c866b630fb6b
BUG: 1543279
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch limits itself to only handling the case
where no file (data or linkto) exists on the subvol.
Additional cases to be handled:
1. A linkto file was found on the only child subvol. This currently
calls dht_lookup_everywhere which eventually deletes it. It can be
deleted directly as it will not be pointing to a valid subvol.
2. Directory lookups - locking might be unnecessary in some cases.
Change-Id: I940ba34531f2aaee1d36fd9ca45ecfd46be662a4
BUG: 1546620
Signed-off-by: N Balachandran <nbalacha@redhat.com>
|