summaryrefslogtreecommitdiffstats
path: root/xlators
Commit message (Collapse)AuthorAgeFilesLines
...
* geo-rep: IPv6 supportAravinda VK2019-04-171-2/+28
| | | | | | | | | | | | | | | | `address_family=inet6` needs to be added while mounting master and slave volumes in gverify script. New option introduced to gluster cli(`--inet6`) which will be used internally by geo-rep while calling `gluster volume info --remote-host=<ipv6>`. Backport of https://review.gluster.org/22363 Fixes: bz#1695436 Change-Id: I1e0d42cae07158df043e64a2f991882d8c897837 Signed-off-by: Aravinda VK <avishwan@redhat.com> (cherry picked from commit 240e1d6821fbb779c3dd73f6f0225d755a5b7cc6)
* cluster/afr: Remove local from owners_list on failure of lock-acquisitionPranith Kumar K2019-04-164-18/+14
| | | | | | | | | | | | | When eager-lock lock acquisition fails because of say network failures, the local is not being removed from owners_list, this leads to accumulation of waiting frames and the application will hang because the waiting frames are under the assumption that another transaction is in the process of acquiring lock because owner-list is not empty. Handled this case as well in this patch. Added asserts to make it easier to find these problems in future. fixes bz#1699731 Change-Id: I3101393265e9827755725b1f2d94a93d8709e923 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* core: Log level changes do not effect on running client processMohit Agrawal2019-04-162-9/+20
| | | | | | | | | | | | | | | | | | | | | | | | | Problem: commit c34e4161f3cb6539ec83a9020f3d27eb4759a975 set log-level per xlator during reconfigure only for a brick process not for the client process. Solution: 1) Change per xlator log-level only if brick_mux is enabled.To make sure about brick multiplex introudce a flag brick_mux at ctx->cmd_args. Note: There are two other changes done with this patch 1) Ignore client-log-level option to attach a brick with already running brick if brick_mux is enabled 2) Add a log to print pid of the running process to make easier debugging > Change-Id: I39e85de778e150d0685cd9a79425ce8b4783f9c9 > Signed-off-by: Mohit Agrawal <moagrawal@redhat.com> > Fixes: bz#1696046 > (Cherry picked from commit 798aadbe51a9a02dd98a0f861cc239ecf7c8ed57) > (Reviewed on upstream link https://review.gluster.org/#/c/glusterfs/+/22495/) Change-Id: If91682830f894ab8f6857f19dcb1797fc15ca64c Fixes: bz#1699715 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* posix/ctime: Fix stat(time attributes) inconsistency during readdirpKotresh HR2019-04-162-26/+44
| | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Creation of tar file on gluster volume throws warning 'file changed as we read it' Cause: During readdirp, for few of the files whose inode is not present, time attributes were served from backend. This caused the ctime of few files to be different between before readdir and after readdir by tar. Solution: If ctime feature is enabled and inode is not present, don't serve the time attributes from backend file, serve it from xattr. Backport of: > Patch: https://review.gluster.org/22540 > BUG: 1698078 > Change-Id: I427ef865f97399475faf5aa6ca495f7e317603ae > Signed-off-by: Kotresh HR <khiremat@redhat.com> (cherry picked from commit c56f102da21c5b69e656a055aaf736281596284d) fixes: bz#1699703 Change-Id: I427ef865f97399475faf5aa6ca495f7e317603ae Signed-off-by: Kotresh HR <khiremat@redhat.com>
* ec: fix truncate lock to cover the write in tuncate cleanKinglong Mee2019-04-161-2/+6
| | | | | | | | | | | ec_truncate_clean does writing under the lock granted for truncate, but the lock is calculated by ec_adjust_offset_up, so that, the write in ec_truncate_clean is out of lock. Updates: bz#1699499 Change-Id: Idbe1fd48d26afe49c36b77db9f12e0907f5a4134 Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> (cherry picked from commit 0e1223491e964096384edfae5032ed0d50d028ad)
* core: Brick is not able to detach successfully in brick_mux environmentMohit Agrawal2019-04-161-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | Problem: In brick_mux environment, while volumes are stopped in a loop bricks are not detached successfully. Brick's are not detached because xprtrefcnt has not become 0 for detached brick. At the time of initiating brick detach process server_notify saves xprtrefcnt on detach brick and once counter has become 0 then server_rpc_notify spawn a server_graph_janitor_threads for cleanup brick resources.xprtrefcnt has not become 0 because socket framework is not working due to assigning 0 as a fd for socket. In commit dc25d2c1eeace91669052e3cecc083896e7329b2 there was a change in changelog fini to close htime_fd if htime_fd is not negative, by default htime_fd is 0 so it close 0 also. Solution: Initialize htime_fd to -1 after just allocate changelog_priv by GF_CALLOC > Fixes: bz#1699025 > Change-Id: I5f7ca62a0eb1c0510c3e9b880d6ab8af8d736a25 > Signed-off-by: Mohit Agrawal <moagrawal@redhat.com> > (cherry picked from commit b777d83001d8006420b6c7d2d88fe68950aa7e00) Change-Id: I7a2b6fc2d36405d51990376333e093661be48475 Fixes: bz#1699714 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* build: glusterfs build is failing on RHEL-6Mohit Agrawal2019-04-161-1/+1
| | | | | | | | | | | | | | | | Problem: glusterfs build is throwing error undefined reference to `dlclose' on RHEL 6 Solution: Add LIB_DL link in Makefile.am to resolve the same > Fixes: bz#1696512 > Change-Id: I58019ca9e29d569d8e6df282b8ab178ad540843b > Signed-off-by: Mohit Agrawal <moagrawa@redhat.com> > (cherry picked from commit 064aad721c249d63fb89686b32e5d15de50e2f8c) Change-Id: I4f68553b501c283e2066ddc64e204db40552ee73 Fixes: bz#1699713 Signed-off-by: Mohit Agrawal <moagrawa@redhat.com>
* cluster/afr: Thin-arbiter SHD fixeskarthik-us2019-04-162-13/+13
| | | | | | | | | This patch address post-merge review comments for commit 5784a00f997212d34bd52b2303e20c097240d91c Change-Id: I7ed954664a2ae8e1091d23ee3ceb9c66e83bfeac fixes: bz#1699319 Signed-off-by: karthik-us <ksubrahm@redhat.com>
* protocol/client: Do not fallback to anon-fd if fd is not openPranith Kumar K2019-04-161-1/+7
| | | | | | | | | | | | | | | | | | | If an open comes on a file when a brick is down and after the brick comes up, a fop comes on the fd, client xlator would still wind the fop on anon-fd leading to wrong behavior of the fops in some cases. Example: If lk fop is issued on the fd just after the brick is up in the scenario above, lk fop will be sent on anon-fd instead of failing it on that client xlator. This lock will never be freed upon close of the fd as flush on anon-fd is invalid and is not wound below server xlator. As a fix, failing the fop unless the fd has FALLBACK_TO_ANON_FD flag. Change-Id: I77692d056660b2858e323bdabdfe0a381807cccc fixes bz#1699198 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> (cherry picked from commit 92ae26ae8039847e38c738ef98835a14be9d4296)
* afr: thin-arbiter read txn fixesRavishankar N2019-04-163-22/+37
| | | | | | | | | | | | | | - Fixes afr_ta_read_txn() to handle inode refresh failures. code-path. - Fixes a double free issue of dict. Note: This patch address post-merge review comments for commit 69532c141be160b3fea03c1579ae4ac13018dcdf fixes: bz#1693992 Change-Id: Id5299b45b68569d47df6b73755918237a1592cb4 Signed-off-by: Ravishankar N <ravishankar@redhat.com> (cherry picked from commit 500bd0014128e6727e83b6cb77e8ac94304b8f4a)
* cluster/ec: Don't enqueue an entry if it is already healingAshish Pandey2019-04-165-30/+127
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: 1 - heal-wait-qlength is by default 128. If shd is disabled and we need to heal files, client side heal is needed. If we access these files that will trigger the heal. However, it has been observed that a file will be enqueued multiple times in the heal wait queue, which in turn causes queue to be filled and prevent other files to be enqueued. 2 - While a file is going through healing and a write fop from mount comes on that file, it sends write on all the bricks including healing one. At the end it updates version and size on all the bricks. However, it does not unset dirty flag on all the bricks, even if this write fop was successful on all the bricks. After healing completion this dirty flag remain set and never gets cleaned up if SHD is disabled. Solution: 1 - If an entry is already in queue or going through heal process, don't enqueue next client side request to heal the same file. 2 - Unset dirty on all the bricks at the end if fop has succeeded on all the bricks even if some of the bricks are going through heal. Change-Id: Ia61ffe230c6502ce6cb934425d55e2f40dd1a727 updates: bz#1693223 Signed-off-by: Ashish Pandey <aspandey@redhat.com> (cherry picked from commit 313dcefe7a62bd16cd794040df068f9bec9c6927)
* glusterd: load ctime in the client graph only if it's not turned offAtin Mukherjee2019-04-161-1/+2
| | | | | | | | | | | | Considering ctime is a client side feature, we can't blindly load ctime xlator into the client graph if it's explicitly turned off, that'd result into backward compatibility issue where an old client can't mount a volume configured on a server which is having ctime feature. Fixes: bz#1698471 Change-Id: I6ae7b96d056073aa6746de9a449cf319786d45cc Signed-off-by: Atin Mukherjee <amukherj@redhat.com> (cherry picked from commit efbf8abcc3bc729a90d4a7b57dc515f1df8a5863)
* glusterd: fix txn-id mem leakAtin Mukherjee2019-04-162-6/+36
| | | | | | | | | | | | | | | | This commit ensures the following: 1. Don't send commit op request to the remote nodes when gluster v status all is executed as for the status all transaction the local commit gets the name of the volumes and remote commit ops are technically a no-op. So no need for additional rpc requests. 2. In op state machine flow, if the transaction is in staged state and op_info.skip_locking is true, then no need to set the txn id in the priv->glusterd_txn_opinfo dictionary which never gets freed. Fixes: bz#1694610 Change-Id: Ib6a9300ea29633f501abac2ba53fb72ff648c822 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> (cherry picked from commit 34e010d64905b7387de57840d3fb16a326853c9b)
* afr: add client-pid to all gf_event() callsRavishankar N2019-04-167-15/+38
| | | | | | | | | | client-pid for glustershd is GF_CLIENT_PID_SELF_HEALD client-pid for glfsheal is GF_CLIENT_PID_GLFS_HEALD updates: bz#1693155 Change-Id: Ib3a863af160ff48c822a5e6b0c27c575c9887470 Signed-off-by: Ravishankar N <ravishankar@redhat.com> (cherry picked from commit 8016d51a3bbd410b0b927ed66be50a09574b7982)
* cluster/ec: Fix handling of heal info cases without locksAshish Pandey2019-04-091-25/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When we use heal info command, it takes lot of time as in some cases it takes lock on entries to find out if the entry actually needs heal or not. There are some cases where we can avoid these locks and can conclude if the entry needs heal or not. 1 - We do a lookup (without lock) on an entry, which we found in .glusterfs/indices/xattrop, and find that lock count is zero. Now if the file contains dirty bit set on all or any brick, we can say that this entry needs heal. 2 - If the lock count is one and dirty is greater than 1, then it also means that some fop had left the dirty bit set which made the dirty count of current fop (which has taken lock) more than one. At this point also we can definitely say that this entry needs heal. This patch is modifying code to take into consideration above two points. It is also changing code to not to call ec_heal_inspect if ec_heal_do was called from client side heal. Client side heal triggeres heal only when it is sure that it requires heal. [We have changed the code to not to call heal for lookup] updates bz#1697764 Change-Id: I7f09f0ecd12f65a353297aefd57026fd2bebdf9c Signed-off-by: Ashish Pandey <aspandey@redhat.com> (cherry picked from commit da47caf2405c08c9abafc4a55525a8b2c2dd5bb8)
* client-rpc: Fix the payload being sent on the wirePoornima G2019-03-296-244/+308
| | | | | | | | | | | | | | | | | | | The fops allocate 3 kind of payload(buffer) in the client xlator: - fop payload, this is the buffer allocated by the write and put fop - rsphdr paylod, this is the buffer required by the reply cbk of some fops like lookup, readdir. - rsp_paylod, this is the buffer required by the reply cbk of fops like readv etc. Currently, in the lookup and readdir fop the rsphdr is sent as payload, hence the allocated rsphdr buffer is also sent on the wire, increasing the bandwidth consumption on the wire. With this patch, the issue is fixed. Fixes: bz#1692101 Change-Id: Ie8158921f4db319e60ad5f52d851fa5c9d4a269b Signed-off-by: Poornima G <pgurusid@redhat.com>
* server.c: fix Coverity CID 1399758Yaniv Kaul2019-03-211-1/+2
| | | | | | | | | | | | | | | 1399758 Dereference before null check It was introduced @ commit 67f48bfcc16a38052e6c9ae7c25e69b03b8ae008 updates: bz#1691187 > updates: bz#789278 > Signed-off-by: Yaniv Kaul <ykaul@redhat.com> > Change-Id: I1424b008b240691fe2a8924e31c708d0fb4f362d > (cherry picked from commit 8aff9cc5c6277ef7dacfb89f1392b7c2eda9b825) Change-Id: Ie2160fb9ae9cdeacf845e849da7f6001b3b6b10b
* glusterfsd: Brick is getting crash at the time of startupMohit Agrawal2019-03-131-5/+5
| | | | | | | | | | | | | | | | | Problem: Brick is getting crash because graph was not activated at the time of accessing server_conf Solution: To avoid the crash check ctx->active before processing a request > Change-Id: Ib112e0eace19189e45f430abdac5511c026bed47 > fixes: bz#1687705 >(cherry picked from commit 67f48bfcc16a38052e6c9ae7c25e69b03b8ae008) > (Reviewed on upstream link https://review.gluster.org/#/c/glusterfs/+/22339/) Change-Id: I1367c564f04edbad145575b811c67522cc318851 fixes: bz#1688218 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* rpm: add thin-arbiter packagev6.0rc1Ashish Pandey2019-03-131-2/+0
| | | | | | | | | | | | | | | | | | | | Discussion on thin arbiter volume - https://github.com/gluster/glusterfs/issues/352#issuecomment-350981148 Main idea of having this rpm package is to deploy thin-arbiter without glusterd and other commands on a node, and all we need on that tie-breaker node is to run a single glusterfs command. Also note that, no other glusterfs installation needs thin-arbiter.so. Make sure RPM contains sample vol file, which can work by default, and a script to configure that volfile, along with translator image. Change-Id: Ibace758373d8a991b6a19b2ecc60c93b2f8fc489 updates: bz#1672818 Signed-off-by: Amar Tumballi <amarts@redhat.com> Signed-off-by: Ashish Pandey <aspandey@redhat.com> (cherry picked from commit ca9bef7f1538beb570fcb190ff94f86f0b8ba38a)
* cluster/afr: Send truncate on arbiter brick from SHDkarthik-us2019-03-121-15/+13
| | | | | | | | | | | | | | | | | | | Problem: In an arbiter volume configuration SHD will not send any writes onto the arbiter brick even if there is data pending marker for the arbiter brick. If we have a arbiter setup on the geo-rep master and there are data pending markers for the files on arbiter brick, SHD will not mark any data changelog during healing. While syncing the data from master to slave, if the arbiter-brick is considered as ACTIVE, then there is a chance that slave will miss out some data. If the arbiter brick is being newly added or replaced there is a chance of slave missing all the data during sync. Fix: If there is data pending marker for the arbiter brick, send truncate on the arbiter brick during heal, so that it will record truncate as the data transaction in changelog. Change-Id: I3242ba6cea6da495c418ef860d9c3359c5459dec fixes: bz#1687672 Signed-off-by: karthik-us <ksubrahm@redhat.com>
* glusterd: glusterd memory leak while running "gluster v profile" in a loopMohit Agrawal2019-03-122-3/+6
| | | | | | | | | | | | | | | | Problem: glusterd has memory leak while running "gluster v profile" in a loop Solution: Resolve leak code path to avoid leak > Change-Id: Id608703ff6d0ad34ed8f921a5d25544e24cfadcd > fixes: bz#1685414 > (Cherry pick from commit 9374484917466dff4688d96ff7faa0de1c804a6c) > (Reviewed on link https://review.gluster.org/#/c/glusterfs/+/22301/) Change-Id: I1ca118265f97b188f94b3d5cff649ec36cb18ca0 fixes: bz#1685771 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* core: make compute_cksum function op_version compatibleSanju Rakonde2019-03-081-4/+8
| | | | | | | | | | | | | | | | | | | | Problem: commit 5a152a changed the mechansim of computing the checksum. In heterogeneous cluster, peers are running into rejected state because we have different cksum computation mechansims in upgraded and non-upgraded nodes. Solution: add a check for op-version so that all the nodes in the cluster follow the same mechanism for computing the cksum. fixes: bz#1684029 > Change-Id: I1508f000e8c9895588b6011b8b6cc0eda7102193 > BUG: bz#1685120 > Signed-off-by: Sanju Rakonde <srakonde@redhat.com> > (cherry picked from commit 073444b693b7a91c42963512e0fdafb57ad46670) Change-Id: I1508f000e8c9895588b6011b8b6cc0eda7102193
* performance/readdir-ahead: fix deadlockRaghavendra Gowdappa2019-03-081-1/+2
| | | | | | | | | | | | | | | | | | | | | | | This deadlock happens while processing dentry corresponding to current directory (.) in rda_fill_readdirp. In this case following order is followed: LOCK(directory_fd_ctx->lock); rda_inode_ctx_get_iatt -> LOCK(directory_inode->lock); However, in rda_mark_inode_dirty following lock order is followed: LOCK(directory_inode->lock); LOCK(directory_fd_ctx->lock); these two codepaths when executed concurrently resulted in a deadlock. Current patch fixes this by removing locking directory inode and fd-ctx in rda_fill_readdirp. This is fine as directory inode's stat won't change due to writes to files within directory. Change-Id: Ic93a67a0dac8229bb0d79582e526a512e6f2569c Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> Fixes: bz#1686399
* io-threads: Prioritize fops with NO_ROOT_SQUASH pidSusant Palai2019-03-061-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | There was 30% regression observed in mkdir path with commit b139bc58eb504adf5ef81658896c9283ae21f390. On analysis it is found that io-threads xlator deprioritzes fops with all -ve pid. Some context in to the no-root-squash pid requirement: DHT xlator does some of the internal fops with root privileges. This is needed so that operations like layout healing should not be abandoned because a non root user is operating. If root-squash option is enabled the layout set operation looses its root privilege as server xlator converts the uid and pid to random numbers. Hence, the above mentioned commit converted pid to GF_CLIENT_PID_NO_ROOT_SQUASH to continue fops as root. Combining the above I am proposing not to deprioritize fops with no-root-squash pid. > Change-Id: I54d056c01b25729304a77f9242fbaff39c5672ba > fixes: bz#1676430 > Signed-off-by: Susant Palai <spalai@redhat.com> (cherry picked from commit f5c3b1727f55ffaa3dcdb3c3a09b968ebb45dbb2) Change-Id: I54d056c01b25729304a77f9242fbaff39c5672ba fixes: bz#1676429 Signed-off-by: Susant Palai <spalai@redhat.com>
* glusterd: remove experimental xlator options from glusterd-volume-set.cSanju Rakonde2019-02-271-20/+0
| | | | | | | | | | | experimental xlators have been removed from the codebase. But we missed to remove the options related to experimental xlators from the codebase. This patch removes those options. fixes: bz#1683506 Change-Id: I3fa7e14c6cd8ebde5cebc8d2b0cb2409bf37c1ae Signed-off-by: Sanju Rakonde <srakonde@redhat.com> (cherry picked from commit 5cddd4d758014fe116d9c130632eada2ecded88c)
* md-cache: Adapt integer data types to avoid integer overflowDavid Spisla2019-02-251-3/+3
| | | | | | | | | | | | | | The "struct iatt" in iatt.h is using int64_t types for storing the atime, mtime and ctime. Therefore the struct 'struct md_cache' in md-cache.c should also use this types to avoid an integer overflow. This can happen e.g. if someone uses a very high default-retention-period in the WORM-Xlator. Change-Id: I605268d300ab622b9c8ab30e459dc00d9340aad1 fixes: bz#1680020 Signed-off-by: David Spisla <david.spisla@iternity.com> (cherry picked from commit 15423e14f16dd1a15ee5e5cbbdbdd370e57ed59f)
* cluster/dht: Request linkto xattrs in dht_rmdir opendirN Balachandran2019-02-221-1/+26
| | | | | | | | | | | | | | | | | | If parallel-readdir is enabled, the rda xlator is loaded below dht in the graph and proactively lists and caches entries when an opendir is performed. dht_rmdir checks if the directory being deleted contains stale linkto files by performing a readdirp on its child subvols. However, as the entries are actually read in during the opendir operation which does not request the linkto xattr,no linkto xattrs are present for the entries causing dht to incorrectly identify them as data files and fail the rmdir operation with ENOTEMPTY. DHT now always adds the linkto xattr in the list of xattrs requested in the opendir. Change-Id: I0711198e66c59146282eb8b88084170bedfb4018 fixes: bz#1679004 Signed-off-by: N Balachandran <nbalacha@redhat.com>
* dht: fix double extra unref of inode at heal pathKinglong Mee2019-02-221-1/+1
| | | | | | | | | | | | | The loc_wipe is done in the _out_ section, inode_unref(loc.parent) here casues a double extra unref of loc.parent. > Change-Id: I2dc809328d3d34bf7b02c7df9a4f97788af511e6 > Signed-off-by: Kinglong Mee <mijinlong@open-fs.com> (cherry-pick of https://review.gluster.org/#/c/glusterfs/+/21998/) Change-Id: I2dc809328d3d34bf7b02c7df9a4f97788af511e6 updates: bz#1679275 Signed-off-by: Susant Palai <spalai@redhat.com>
* performance/write-behind: fix use-after-free in readdirpRaghavendra Gowdappa2019-02-221-18/+22
| | | | | | | | | | | | | | | | Two issues were found: 1. in wb_readdirp_cbk, inode should unrefed after wb_inode is unlocked. Otherwise, inode and hence the context wb_inode can be freed by the type we try to unlock wb_inode 2. wb_readdirp_mark_end iterates over a list of wb_inodes of children of a directory. But inodes could've been freed and hence the list might be corrupted. To fix take a reference on inode before adding it to invalidate_list of parent. Change-Id: I911b0e0b2060f7f41ded0b05db11af6f9b7c09c5 Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> Updates: bz#1678570 (cherry picked from commit 64cc4458918e8c8bfdeb114da0a6501b2b98491a)
* performance/write-behind: handle call-stub leaksRaghavendra Gowdappa2019-02-191-0/+8
| | | | | | | Change-Id: I7be9a5f48dcad1b136c479c58b1dca1e0488166d Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> Fixes: bz#1678570 (cherry picked from commit 6175cb10cd5f59f3c7ae4100bc78f359b68ca3e9)
* cluster/dht: Fix lookup selfheal and rmdir raceN Balachandran2019-02-181-9/+25
| | | | | | | | | | | | | | A race between the lookup selfheal and rmdir can cause directories to be healed only on non-hashed subvols. This can prevent the directory from being listed from the mount point and in turn causes rm -rf to fail with ENOTEMPTY. Fix: Update the layout information correctly and reduce the call count only after processing the response. Change-Id: I812779aaf3d7bcf24aab1cb158cb6ed50d212451 fixes: bz#1677260 Signed-off-by: N Balachandran <nbalacha@redhat.com>
* performance/md-cache: introduce an option to control invalidation of inodesRaghavendra Gowdappa2019-02-182-10/+50
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Explicit invalidation by calling inode_invalidate is necessary when same (meta)data is shared/access across multiple mounts. Without an explicit inode_invalidate call, caches in the mount which didn't witness writes wouldn't be aware of changes as writes wouldn't have passed through them. However, if (meta)data is not shared, all relevant I/O goes through the cache of single mount and hence is coherent with (meta)data on bricks always. So, explicit inode invalidation can be disabled for this case which gives a huge performance boost for workloads that write data and then immediately read the data they just wrote. Note that otherwise, local writes (which pass through the cache) will change ctime and cause unnecessary invalidations. The name of the option that controls this behavior is "performance.global-cache-invalidation". This option is global and it purges caches both in glusterfs and kernel stack for native FUSE mounts. For non-native FUSE mounts, it purges cache only from glusterfs stack. This option is effective only when performance.stat-prefetch is on. Note that there is a similar option "performance.cache-invalidation", but the scope of that option is limited to quick-read and md-cache. Change-Id: I462bb4b65ff9aae1f6ba76f50b1f2f94fb10323b Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> updates: bz#1674364 (cherry picked from commit 2b5aa4489de2017a03bcb6ec8986286f0c76a670)
* mount/fuse: fix bug related to --auto-invalidation in mount scriptRaghavendra Gowdappa2019-02-181-1/+1
| | | | | | | | | | | | When "auto-invalidation" option was not specified for mount script, glusterfs cmdline ended with "--auto-invalidation=" option. This patch fixes that bug in mount script. Thanks to Amar for reporting it. Change-Id: Ie5cd4c6ffb3ac644d9d2b032035f914a935d05a8 Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> updates: bz#1674364
* glusterd: improve loggingAtin Mukherjee2019-02-111-1/+3
| | | | | | | | | | glusterd_resolve_all_bricks failure log should highlight the brick identifier. Change-Id: I035b4650ef6a14bb1e1221d3bad1c40f9d43dbdd fixes: bz#1673972 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> (cherry picked from commit 12af2067a82e37079e76723d3e25ba1c72ca078a)
* glusterd: get-state command should not fail if any brick is gone badv7devSanju Rakonde2019-02-052-5/+7
| | | | | | | | | | | | | | | | | | | | | | Problem: get-state command will error out, if any of the underlying brick(s) of volume(s) in the cluster go bad. It is expected that get-state command should not error out, but should generate an output successfully. Solution: In glusterd_get_state(), a statfs call is made on the brick path for every bricks of the volumes to calculate the total and free memory available. If any of statfs call fails on any brick, we should not error out and should report total memory and free memory of that brick as 0. This patch also handles a statfs failure scenario in glusterd_store_retrieve_bricks(). fixes: bz#1672205 Change-Id: Ia9e8a1d8843b65949d72fd6809bd21d39b31ad83 Signed-off-by: Sanju Rakonde <srakonde@redhat.com>
* glusterd: manage upgrade to current masterAmar Tumballi2019-02-042-12/+13
| | | | | | | | | | | | | | | | | | | | | | Scenarios tested: * Upgrade the node when there are stripe / tiering and regular type of volumes are present. - All volumes are started fine (as the change was not on brick volfile) - For tier, the functionality may not even work, as changetimerecorder is not present. - 'gluster volume info' properly shows as 'NOT SUPPORTED' for stripe and tier type of volume. * Upgrade in a rolling upgrade scenario, where an old version is able to connect to higher master. - on a normal volume, if the volfile-server was new, the newer client volfiles needed to have utime xlator conditionally. - with this one change, all other changes seem to work fine. Change-Id: Ib2d3b69dafa02b2c695a735b13c1aa70aba07cb8 updates: bz#1635688 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* cluster/dht: Do not use gfid-req in fresh lookupN Balachandran2019-02-022-8/+60
| | | | | | | | | | | | Fuse sets a random gfid-req value for a fresh lookup. Posix lookup will set this gfid on entries with missing gfids causing a GFID mismatch for directories. DHT will now ignore the Fuse provided gfid-req and use the GFID returned from other subvols to heal the missing gfid. Change-Id: I5f541978808f246ba4542564251e341ec490db14 fixes: bz#1670259 Signed-off-by: N Balachandran <nbalacha@redhat.com>
* mount/fuse: expose auto-invalidation as a mount optionRaghavendra Gowdappa2019-02-023-10/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Auto invalidation is necessary when same (meta)data is shared/access across multiple mounts. However, if (meta)data is not shared, all relevant I/O goes through the cache of single mount and hence is coherent with (meta)data on bricks always. So, fuse-auto-invalidation can be disabled for this case which gives a huge performance boost for workloads that write data and then immediately read the data they just wrote. From glusterfs --help, <snip> --auto-invalidation[=BOOL] controls whether fuse-kernel can auto-invalidate attribute, dentry and page-cache. Disable this only if same files/directories are not accessed across two different mounts concurrently [default: "on"] </snip> Details on how disabling auto-invalidation helped to reduce pgbench init times can be found at [1]. Time taken for pgbench init of scale 8000 was 8340s. That will be an improvement of 86% (59280s vs 8340s) with auto-invalidations turned off along with other optimizations. Just disabling auto-invalidation contributed 56% improvement by reducing the total time taken by 33260s. [1] https://www.spinics.net/lists/gluster-devel/msg25907.html Change-Id: I0ed730dba9064bd9c576ad1800170a21e100e1ce Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> updates: bz#1664934
* core: make gf_thread_create() easier to useXavi Hernandez2019-02-014-23/+5
| | | | | | | | | | | | | | This patch creates a specific function to set the thread name using a string format and a variable argument list, like printf(). This function is used to set the thread name from gf_thread_create(), which now accepts a variable argument list to create the full name. It's not necessary anymore to use a local array to build the name of the thread. This is done automatically. Change-Id: Idd8d01fd462c227359b96e98699f8c6d962dc17c Updates: bz#1193929 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* cluster/thin-arbiter: Consider thin-arbiter before marking new entry changelogAshish Pandey2019-02-014-19/+87
| | | | | | | | | | | | | | | | If a fop to create an entry fails on one of the data brick, we mark the pending changelog on the entry on brick for which it was successful. This is done as part of post op phase to make sure that entry gets healed even if it gets renamed to some other path where its parent was not marked as bad. As it happens as part of post op, we should consider thin-arbiter to check if the brick, which was successful, is the good brick or not. This will avoide split brain and other issues. Change-Id: I12686675be98f02f70a5186b3ed748c541514d53 updates: bz#1662264 Signed-off-by: Ashish Pandey <aspandey@redhat.com>
* cluster/dht: Remove internal permission bitsN Balachandran2019-02-011-0/+6
| | | | | | | | | | | | | Rebalance sets the sgid and t bits on a file that is being migrated. These permissions are not removed in dht_readdirp_cbk when listing files causing them to show up on the mountpoint. We now remove these permissions if a non-linkto file has the linkto xattr set. Change-Id: I5c69b2ecfe2df804fe50faea903b242d01729596 fixes: bz#1669937 Signed-off-by: N Balachandran <nbalacha@redhat.com>
* feature/bitrot: Avoid thread creation if xlator is not enabledMohit Agrawal2019-01-311-8/+64
| | | | | | | | | | | | | Problem: Avoid thread creation for bitrot-stub for a volume if feature is not enabled Solution: Before thread creation check the flag if feature is enabled Updates: #475 Change-Id: I2c6cc35bba142d4b418cc986ada588e558512c8e Signed-off-by: Mohit Agrawal <moagrawal@redhat.com> Signed-off-by: Kotresh HR <khiremat@redhat.com>
* core: heketi-cli is throwing error "target is busy"Mohit Agrawal2019-01-311-2/+2
| | | | | | | | | | | | | | | | | | | | Problem: When rpc-transport-disconnect happens, server_connection_cleanup_flush_cbk() is supposed to call rpc_transport_unref() after open-files on that transport are flushed per transport.But open-fd-count is maintained in bound_xl->fd_count, which can be incremented/decremented cumulatively in server_connection_cleanup() by all transport disconnect paths. So instead of rpc_transport_unref() happening per transport, it ends up doing it only once after all the files on all the transports for the brick are flushed leading to rpc-leaks. Solution: To avoid races maintain fd_cnt at client instead of maintaining on brick Credits: Pranith Kumar Karampuri Change-Id: I6e8ea37a61f82d9aefb227c5b3ab57a7a36850e6 fixes: bz#1668190 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* readdir-ahead: do not zero-out iatt in fop cbkRavishankar N2019-01-311-20/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | ...when ctime is zero. ia_type and ia_gfid always need to be non-zero for things to work correctly. Problem: Commit c9bde3021202f1d5c5a2d19ac05a510fc1f788ac zeroed out the iatt buffer in the cbks of modification fops before unwinding if the ctime in the buffer was zero. This was causing the fops to fail: noticeable when AFR's 'consistent-metadata' option was enabled. (AFR zeros out the ctime when the option is set. See commit 4c4624c9bad2edf27128cb122c64f15d7d63bbc8). Fixes: -Do not zero out the ia_type and ia_gfid of the iatt buff under any circumstance. -Also, fixed _rda_inode_ctx_update_iatts() to always update these values from the incoming buf when ctime is zero. Otherwise we end up with zero ia_type and ia_gfid the first time the function is called *and* the incoming buf has ctime set to zero. fixes: bz#1670253 Reported-By:Michael Hanselmann <public@hansmi.ch> Change-Id: Ib72228892d42c3513c19fc6dfb543f2aa3489eca Signed-off-by: Ravishankar N <ravishankar@redhat.com>
* features/sdfs: disable by defaultAmar Tumballi2019-01-292-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With the feature enabled, some of the performance testing results, specially those which create millions of small files, got approximately 4x regression compared to version before enabling this. On master without this patch: 765 creates/sec On master with this patch : 3380 creates/sec Also there seems to be regression caused by this in 'ls -l' workload. On master without this patch: 3030 files/sec On master with this patch : 16610 files/sec This is a feature added to handle multiple clients parallely operating (specially those which race for file creates with same name) on a single namespace/directory. Considering that is < 3% of Gluster's usecase right now, it makes sense to disable the feature by default, so we don't penalize the default users who doesn't bother about this usecase. Also note that the client side translators, specially, distribute, replicate and disperse already handle the issue upto 99.5% of the cases without SDFS, so it makes sense to keep the feature disabled by default. Credits: Shyamsunder <srangana@redhat.com> for running the tests and getting the numbers. Change-Id: Iec49ce1d82e621e9db25eb633fcb1d932e74f4fc Updates: bz#1670031 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* Multiple files: reduce work while under lock.Yaniv Kaul2019-01-2913-117/+120
| | | | | | | | | | | | | | | | | Mostly, unlock before logging. In some cases, moved different code that was not needed to be under lock (for example, taking time, or malloc'ing) to be executed before taking the lock. Note: logging might be slightly less accurate in order, since it may not be done now under the lock, so order of logs is racy. I think it's a reasonable compromise. Compile-tested only! updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com> Change-Id: I2438710016afc9f4f62a176ef1a0d3ed793b4f89
* features/shard: Ref shard inode while adding to fsync listKrutika Dhananjay2019-01-241-8/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | PROBLEM: Lot of the earlier changes in the management of shards in lru, fsync lists assumed that if a given shard exists in fsync list, it must be part of lru list as well. This was found to be not true. Consider this - a file is FALLOCATE'd to a size which would make the number of participant shards to be greater than the lru list size. In this case, some of the resolved shards that are to participate in this fop will be evicted from lru list to give way to the rest of the shards. And once FALLOCATE completes, these shards are added to fsync list but without a ref. After the fop completes, these shard inodes are unref'd and destroyed while their inode ctxs are still part of fsync list. Now when an FSYNC is called on the base file and the fsync-list traversed, the client crashes due to illegal memory access. FIX: Hold a ref on the shard inode when adding to fsync list as well. And unref under following conditions: 1. when the shard is evicted from lru list 2. when the base file is fsync'd 3. when the shards are deleted. Change-Id: Iab460667d091b8388322f59b6cb27ce69299b1b2 fixes: bz#1669077 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
* afr/self-heal:Fix wrong type checkingRavishankar N2019-01-242-32/+9
| | | | | | | | | | gf_dirent struct has d_type variable which should check with DT_DIR istead of IA_IFDIR or IA_IFDIR has to compare with entry->d_stat.ia_type Change-Id: Idf1059ce2a590734bc5b6adaad73604d9a708804 updates: bz#1653359 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* core: heketi-cli is throwing error "target is busy"Mohit Agrawal2019-01-241-0/+17
| | | | | | | | | | | | | | | Problem: At the time of deleting block hosting volume through heketi-cli , it is throwing an error "target is busy". cli is throwing an error because brick is not detached successfully and brick is not detached due to race condition to cleanp xprt associated with detached brick Solution: To avoid xprt specifc race condition introduce an atomic flag on rpc_transport Change-Id: Id4ff1fe8375a63be71fb3343f455190a1b8bb6d4 fixes: bz#1668190 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* performance/readdir-ahead: Fix deadlock in readdir ahead.Mohammed Rafi KC2019-01-231-4/+14
| | | | | | | | | | | | This patch fixes a lock contention in reaadir-ahead xlator. There are two issues, one is the processing of "." ".." entry while holding an fd_ctx lock. The other one is destroying the stack inside a fd_ctx lock. Change-Id: Id0bf83a3d9fea6b40015b8d167525c59c6cfa25e updates: bz#1659708 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
generated by cgit (git 2.34.1) at 2024-11-15 11:17:25 +0000