summaryrefslogtreecommitdiffstats
path: root/xlators/cluster
Commit message (Collapse)AuthorAgeFilesLines
* cluster/dht: Del GF_READDIR_SKIP_DIRS key from dict for first_upshishir gowda2013-08-182-4/+12
| | | | | | | | | | | | | | | | Currently, we sent GF_READDIR_SKIP_DIRS for all subvolumes if first_subvol != first_up_subvolume. Also first_up_subvolume can change with-in the life of a call and cbk. Saving the first_up_subvol in dht_local for checks. Change-Id: I6e369e63f29c9761993f2a66ed768c424bb44d27 BUG: 996474 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5577 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/afr: Add largest file is source policyAnand Avati2013-08-142-29/+93
| | | | | | | | | | | | | | For Write Once Read Many times type of work-load choosing largest file to be the source will always resolve fool-fool scenarios correctly. In other cases we fsync() the files and will have a reliable 'wise man'. Change-Id: Ic4dbea8d06db6d578fbcb866fb65ee2d066ac7ba BUG: 958118 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/5519 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* afr: treat appending writes as stable writes.Anand Avati2013-08-133-1/+29
| | | | | | | | | | | | | Durability of appending writes is implicit in the file size. Therefore performing an explicit fsync() is unnecessary in such cases as self-heal can check for the size of file when pending changelog is not unambiguous. Change-Id: I05446180a91d20e0dbee5de5a7085b87d57f178a BUG: 927146 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/5501 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* cluster/afr: skip directory inspection when entry self-heal is offAnand Avati2013-08-111-1/+1
| | | | | | | | | | | | When user has explicitly configured to disable entry self-heal in the client, it is wrong to do the healing in opendir. So skip it. This is especially useful to reduce opendir() times after graph switches. Change-Id: Ic6eb9ff2334a5b8417f2f35410a366a536bad5df Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/5528 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Unwind frame on error in readdir[p]Pranith Kumar K2013-08-081-2/+2
| | | | | | | | | Change-Id: I5701bf115e0aa1adb4fb52f5418534910a2268d4 BUG: 994959 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5531 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* afr: check for non-zero call_count before doing a stack windRavishankar N2013-08-071-0/+5
| | | | | | | | | | | | | | | | | | | | When one of the bricks of a 1x2 replicate volume is down, writes to the volume is causing a race between afr_flush_wrapper() and afr_flush_cbk(). The latter frees up the call_frame's local variables in the unwind, while the former accesses them in the for loop and sending a stack wind the second time. This causes the FUSE mount process (glusterfs) toa receive a SIGSEGV when the corresponding unwind is hit. This patch adds the call_count check which was removed when afr_flush_wrapper() was introduced in commit 29619b4e Change-Id: I87d12ef39ea61cc4c8244c7f895b7492b90a7042 BUG: 988182 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/5393 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/afr: Disable eager-lock if open-fd-count > 1Pranith Kumar K2013-08-024-5/+98
| | | | | | | | | | | | | | | | | Lets say mount1 has eager-lock(full-lock) and after the eager-lock is taken mount2 opened the same file, it won't be able to perform any data operations until mount1 releases eager-lock. To avoid such scenario do not enable eager-lock for transaction if open-fd-count is > 1. Delaying of changelog piggybacking is avoided in this situation. Change-Id: I51b45d6a7c216a78860aff0265a0b8dabc6423a5 BUG: 910217 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5432 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: venkatesh somyajulu <vsomyaju@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* dht: make linkfile creation mode explicitly get setAnand Avati2013-07-311-0/+9
| | | | | | | | | | | | | | | | Because of posix default_acl on parent directory, the mode of linkfile can get masked with the mode in the default acl. This breaks DHT integrity. So let the mode get explicitly reset after mknod(). Change-Id: Ia7328e1ee7b4430bda308f9da293dba78405e081 BUG: 990410 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/5440 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra Talur <rtalur@redhat.com>
* cluster/dht: Fix non-regular file ownership during rebalanceshishir gowda2013-07-312-3/+10
| | | | | | | | | | | | | | | | | | | Currently non-regular files were created as root:root, and their ownership never healed during rebalance process. Also, in dht_linkfile_attr_heal, we have to heal the linkfiles as default, as currently linkfiles are created as root:root. That check existed, as earlier linkfiles were created as frame->root->uid/gid Change-Id: I6cd88361b81bdd500e15bc47b623f5db8eec88e9 BUG: 990154 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5434 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/afr: Print self-heal log when self-heal succeedsPranith Kumar K2013-07-315-32/+120
| | | | | | | | | Change-Id: I95e47e589419dc6a032cbd8ba01964b6c176c2d5 BUG: 927146 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5408 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Treat migration failures due to space constraints as skippedshishir gowda2013-07-302-5/+30
| | | | | | | | | | | | | | | | Currently rebalance/remove-brick op's display migration failed count even for files which failed due to space issues (not enough space for file, or migration leading to cluster imbalance) These will now be counted as skipped, and rebalance/remove-brick status will display the additional counter Change-Id: I674904d380b5f8300e9ca9e6af557c3d30d6cff4 BUG: 989846 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5399 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Allow non-local clients to function with nufa volumes.Vijay Bellur2013-07-291-6/+17
| | | | | | | | | | | | | nufa fails to init if a local brick is not found as of today. With this patch, if a local brick is not found, nufa switches over to dht mode of operations. Change-Id: I50ac1af37621b1e776c8c00a772b8e3dfb3691df BUG: 980838 Signed-off-by: Vijay Bellur <vbellur@redhat.com> Reviewed-on: http://review.gluster.org/5414 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/afr: Handle REPLICATE_TRASH_DIR from old bricksPranith Kumar K2013-07-263-13/+52
| | | | | | | | | Change-Id: Ib99f79d3fa607c818dbc62006516480f598d8add BUG: 886998 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/4640 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: mark linkfile creation/deletion as internal fopshishir gowda2013-07-241-9/+39
| | | | | | | | | | | | | | | | | | | Currently dht creates/deletes linkfiles for various ops like rename/linking and when layout changes. dht_linkfile_create already sends a key GLUSTERFS_INTERNAL_FOP_KEY in dict to identify this as an internal fop and not user based op. Enhancing rename related links/unlinks to send this key too. Marker/changelog or other xlators can now identify these as internal fops and handle them accordingly Change-Id: Ib1ca789e6dbce48703c55ad3f4f88f7cd2df3d06 BUG: 987428 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5335 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* storage/posix: implement batched fsync in a single threadAnand Avati2013-07-231-1/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Because of the extra fsync()s issued by AFR transaction, they could potentially "clog" all the io-threads denying unrelated operations from making progress. This patch assigns a dedicated thread to issues fsyncs, as an experimental feature to understand performance characteristics with the approach. As a basis, incoming individual fsync requests are grouped into batches, falling in the same @batch-fsync-delay-usec window of time. These windows can extend in practice, as processing of the previous batch can take longer than @batch-fsync-delay-usec while new requests are getting batched. The feature support three modes (similar to the -S modes of fs_mark) - syncfs: In this mode one syncfs() is issued per batch, instead of N fsync()s (one per file.) - syncfs-single-fsync: In this mode one syncfs() is issued per batch (which, on Linux, guarantees the completion of write-out of dirty pages in the filesystem up to that point) and one single fsync() to synchronize or flush the controller/drive cache. This corresponds to -S 2 of fsmark. - syncfs-reverse-fsync: In this mode, one syncfs() is issued per batch, and all the open files in that batch are fsync()'ed in the reverse order of the queue. This corresponds to -S 4 of fsmark. - reverse-fsync: In this mode, no syncfs() is issued and all the files in the batch are fsync()'ed in the reverse order. This corresponds to -S 3 of fsmark. Change-Id: Ia1e170a810c780c8d80e02cf910accc4170c4cd4 BUG: 927146 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4746 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Handle parallel hardlinks self-healPranith Kumar K2013-07-231-0/+29
| | | | | | | | | Change-Id: Ieda11870c65edae500140b6c061f15a7b3f264f3 BUG: 986905 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5370 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* fuse: auxiliary gfid mount supportRaghavendra G2013-07-191-6/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * files can be accessed directly through their gfid and not just through their paths. For eg., if the gfid of a file is f3142503-c75e-45b1-b92a-463cf4c01f99, that file can be accessed using <gluster-mount>/.gfid/f3142503-c75e-45b1-b92a-463cf4c01f99 .gfid is a virtual directory used to seperate out the namespace for accessing files through gfid. This way, we do not conflict with filenames which can be qualified as uuids. * A new file/directory/symlink can be created with a pre-specified gfid. A setxattr done on parent directory with fuse_auxgfid_newfile_args_t initialized with appropriate fields as value to key "glusterfs.gfid.newfile" results in the entry <parent>/bname whose gfid is set to args.gfid. The contents of the structure should be in network byte order. struct auxfuse_symlink_in { char linkpath[]; /* linkpath is a null terminated string */ } __attribute__ ((__packed__)); struct auxfuse_mknod_in { unsigned int mode; unsigned int rdev; unsigned int umask; } __attribute__ ((__packed__)); struct auxfuse_mkdir_in { unsigned int mode; unsigned int umask; } __attribute__ ((__packed__)); typedef struct { unsigned int uid; unsigned int gid; char gfid[UUID_CANONICAL_FORM_LEN + 1]; /* a null terminated gfid string * in canonical form. */ unsigned int st_mode; char bname[]; /* bname is a null terminated string */ union { struct auxfuse_mkdir_in mkdir; struct auxfuse_mknod_in mknod; struct auxfuse_symlink_in symlink; } __attribute__ ((__packed__)) args; } __attribute__ ((__packed__)) fuse_auxgfid_newfile_args_t; An initial consumer of this feature would be geo-replication to create files on slave mount with same gfids as that on master. It will also help gsyncd to access files directly through their gfids. gsyncd in its newer version will be consuming a changelog (of master) containing operations on gfids and sync corresponding files to slave. * Also, bring in support to heal gfids with a specific value. fuse-bridge sends across a gfid during a lookup, which storage translators assign to an inode (file/directory etc) if there is no gfid associated it. This patch brings in support to specify that gfid value from an application, instead of relying on random gfid generated by fuse-bridge. gfids can be healed through setxattr interface. setxattr should be done on parent directory. The key used is "glusterfs.gfid.heal" and the value should be the following structure whose contents should be in network byte order. typedef struct { char gfid[UUID_CANONICAL_FORM_LEN + 1]; /* a null terminated gfid * string in canonical form */ char bname[]; /* a null terminated basename */ } __attribute__((__packed__)) fuse_auxgfid_heal_args_t; This feature can be used for upgrading older geo-rep setups where gfids of files are different on master and slave to newer setups where they should be same. One can delete gfids on slave using setxattr -x and .glusterfs and issue stat on all the files with gfids from master. Thanks to "Amar Tumballi" <amarts@redhat.com> and "Csaba Henk" <csaba@redhat.com> for their inputs. Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Change-Id: Ie8ddc0fb3732732315c7ec49eab850c16d905e4e BUG: 952029 Reviewed-on: http://review.gluster.com/#/c/4702 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Amar Tumballi <amarts@redhat.com> Reviewed-on: http://review.gluster.org/4702 Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* dht: fix dht_discover_cbk doing a wrong layout set.shishir gowda2013-07-171-1/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | with the sequence of operations are like below, we have issues with current code (MP == mountpoint): T0,MP1# mkdir /abcd (Succeeds on hash_subvol) T1,MP2# mkdir /abcd (Gets EEXIST as dir exists in hash_subvol) T2,MP2# mkdir /.gfid/<abcd's gfid>/xyz (lookup happens on abcd's gfid, calls dht_discover) T3,MP1# (Completes mkdir(), goes to dir_selfheal to set the layouts). T4,MP2# (dht_discover_cbk gets success for lookup as the entry existed, as layout is not yet written, it says normalize done, found holes). T5,MP2# (as layout anomaly is not considered an issue in this patch, dht_layout_set happens on inode, with all xlators pointing to 0s) T6,MP1# (completes mkdir call, inode has proper layouts) T7,MP2# mkdir /.gfid/<abcd's gfid>/xyz fails with ENOENT (with log saying no subvol found for hash value of xyz. Porting Amar's fix from down-stream beta branch. Change-Id: Ibdc37ee614c96158a1330af19cad81a39bee2651 BUG: 982913 Original-author: Amar Tumballi <amarts@redhat.com> Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5302 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/dht: Prevent dht_access from going into a loop.shishir gowda2013-07-153-1/+40
| | | | | | | | | | | | | | | | | If access fails with ENOTCONN, do not wind to same subvol. We wind to first-up-subvol if access fails with ENOTCONN. In few cases, if dht has only 1 subvolume, and access fails with ENOTCONN, we go into a infinite loop of winding to same subvol The fix is to check if we previously wound to same subvol, and fail if first-up-subvol is same. Change-Id: Ib5d3ce7d33e8ea09147905a7df1ed280874fa549 BUG: 983431 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5319 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* afr: customize client-pid=-1 xtime aggregation to tolerate a replica downAvra Sengupta2013-07-151-2/+9
| | | | | | | | | | | | Using the new 'pluggable policies' API of libxlator. Change-Id: Ie7528182dff8fb42c6e8287a106d3057944df775 BUG: 847839 Original Author: Csaba Henk <csaba@redhat.com> Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/4904 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* libxlator: implement pluggable aggregation policiesAvra Sengupta2013-07-153-2/+8
| | | | | | | | | | | | | | | | | The API is described in libxlator.h. Behavior remains the same for this commit; this is a preparatory step for per-translator customization of aggregation. Change-Id: I5d42923af59b2fd78e1ff59c12763875b57c5190 BUG: 847839 Original Author: Csaba Henk <csaba@redhat.com> Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/4903 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: node-uuid for directories winds to all subvolumesAvra Sengupta2013-07-151-2/+6
| | | | | | | | | | | | | | | this works similar to pathinfo now except that the request is sent to all subvolumes of dht. Underlying replica selects it's subvolume in a round-robin fashion till one of them returns successfully. Change-Id: Ie46c5f7090d04d8c2e487b209916ae6791e94624 BUG: 847839 Original Author: Venky Shankar <vshankar@redhat.com> Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/5225 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/*: get logic to calculate min() of the 'stime' xattrAvra Sengupta2013-07-142-0/+63
| | | | | | | | | | | | | | | | | | | | | | * in both distribute and replicate (ignoring stripe for now), add logic to calculate the min() of stime values. * What is a 'stime' ? Why is this required: - stime means 'slave xtime', mainly used to keep track of slave node's sync status when distributed geo-replication is used. Logic of calculating 'min()' for this stime is very important as in case of crashes/reboots/shutdown, we will have to 'restart' with crawling from stime time value from the mount point, which gives the 'min()' of all the bricks, which means, we don't miss syncing any files in the above cases. Change-Id: I2be8d434326572be9d4986db665570a6181db1ee BUG: 847839 Original Author: Amar Tumballi <amarts@redhat.com> Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/4893 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Unlink dst file after cleanup during migrationshishir gowda2013-07-121-17/+17
| | | | | | | | | | | | | | | | | If a rename happens during migration, unlink fails. This leads to stale xattrs, and Sticky bits still being set. By removing the xattrs and Sticky bits from dst (through fd ops), the stale link file would be cleaned up eventually (even if unlink fails on src). Change-Id: Iec537d021905438327a20e1d811aa06e74034364 BUG: 983399 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5316 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/dht: If linkfile unlink fails with ENOTCONN, do not failshishir gowda2013-07-111-1/+2
| | | | | | | | | | | | | | Currently if linkfile fails with ENOENT, we do not fail. We also need to treat failures with ENOTCONN as success, as if cached subvol is up, rm of a file should succeed. A stale linkfile will get removed later Change-Id: I71d136847933351ed9e2c939bda4a69bc96a3cfc BUG: 983416 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5317 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/dht: Ignore subvols with error in min-free-disk/inodesshishir gowda2013-07-105-17/+85
| | | | | | | | | | | | | | | Currently when selecting a alternative subvolume when hashed subvol has exceeded min-free-disk/inodes, we do not check if layouts have errors (including decommissioning). This leads to data being written to those subvolumes, and in case of decommissioning, will lead to data loss. Change-Id: Ie0c6cf4a29d7c53d8a6d8a8c1bd595cf58a0012a BUG: 982919 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5299 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* afr : change the log level in lookup path to minimize incessant logging.Ravishankar N2013-07-081-3/+3
| | | | | | | | | | | | | Change the logging levels from WARNING to DEBUG in the lookup path to minimize incessant logging in case of gfid mismatch errors. Change-Id: I631b16df3249cf826606f547531f985dac696088 BUG: 959083 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/4939 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* nufa: allow subvols with fanout > 1Krishnan Parthasarathi2013-07-041-67/+100
| | | | | | | | | | | | Previously, nufa wouldn't work on volume topologies such as distribute-replicate or distribute-stripe. Change-Id: Ia89ed4412a00601022c1fc94f046056ce4820fe8 BUG: 980838 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/5262 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Let two data-self-heals compete in new domainPranith Kumar K2013-07-034-23/+73
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: At the moment data-self-heal acquires locks in following pattern. It takes full file lock then gets xattrs on files on both replicas. Decides sources/sinks based on the xattrs. Now it acquires lock from 0-128k then unlocks the full file lock. Syncs 0-128k range from source to sink now acquires lock 128k+1 till 256k then unlocks 0-128k, syncs 128k+1 till 256k block... so on finally it takes full file lock again then unlocks the final small range block. It decrements pending counts and then unlocks the full file lock. This pattern of locks is chosen to avoid more than 1 self-heal to be in progress. BUT if another self-heal tries to take a full file lock while a self-heal is already in progress it will be put in blocked queue, further inodelks from writes by the application will also be put in blocked queue because of the way locks xlator grants inodelks. So until the self-heal is complete writes are blocked. Here is the code: xlators/features/locks/src/inodelk.c - line 225 if (__blocked_lock_conflict (dom, lock) && !(__owner_has_lock (dom, lock))) { ret = -EAGAIN; if (can_block == 0) goto out; gettimeofday (&lock->blkd_time, NULL); list_add_tail (&lock->blocked_locks, &dom->blocked_inodelks); } This leads to hangs in applications. Fix: Since we want to prevent two parallel self-heals. We let them compete in a separate "domain". Lets call the domain on which the locks have been taken on in previous approach as "data-domain". In the new approach When a self-heal is triggered, it acquires a full lock in the new domain "self-heal-domain". After this it performs data-self-heal using the locks in "data-domain" as before. unlock the full file lock in "self-heal-domain" With this approach, application's writevs don't have to wait in pending queue when more than 1 self-heal is triggered. Change-Id: Id79aef3dfa888945977fb9758374ac41c320d0d5 BUG: 967717 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5100 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Refactor inodelk to handle multiple domainsPranith Kumar K2013-07-0311-428/+500
| | | | | | | | | | | | | | | | | | - afr_local_copy should not be memduping locked nodes, that would mean that lock is taken in self-heal on those nodes even before it actually takes the lock. So removed memdup code. Even entry lock related copying (lockee info) is also not necessary for self-heal functionality, so removing that as well. Since it is not local_copy anymore changed its name. - My editor changed tabs to spaces. Change-Id: I8dfb92cb8338e9a967c06907a8e29a8404782d61 BUG: 967717 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5099 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Provide an option to disable afr durabilityPranith Kumar K2013-07-033-3/+23
| | | | | | | | | Change-Id: I40eec20ca6b3f857245a2438883822e251077ee9 BUG: 979365 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5269 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: post-op should complete before starting flushPranith Kumar K2013-07-033-36/+43
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: At the moment afr-flush makes sure that a delayed post-op is woken up but it does not wait for it to complete the post-op before flush unwinds. These are the steps that are happening: 1) flush fop comes on an fd which wakes up a delayed post-op and continues with the flush fop. 2) post-op sends fsync on the wire. 3) flush completes and unwinds to fuse. 4) graph switch happens on the fuse mount disconnecting the old graph's client connections to bricks. 5) xattrop after fsync fails with ENOTCONN because the connections from old graph are taken down now. Fix: Wait for post-op to complete before starting to flush. We could make flush act similar to fsync (i.e.) wind flush as is but wait for post-op to complete before unwinding flush, but it is better to send flush as the final fop. So wind of flush will start after post-op is complete. Had to change fsync to accommodate this change. Change-Id: I93aa642647751969511718b0e137afbd067b388a BUG: 980548 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5274 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Allow data/entry self heal for metadata split-brainVenkatesh Somyajulu2013-07-027-134/+151
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Currently whenever there is metadata split-brain, a variable sh->op_failed is set to 1 to denote that self heal got failed. But if we proceed for data self heal, even code-path of data self heal also relies on the sh->op_failed variable. So if will check for sh->op_failed variable and will eventually fails to do data self heal. So needed a mechanism to allow data self heal even if metadata is in split brain. Fix: Some data structure revamp is done in http://review.gluster.com/#/c/5106/ fix and this patch is based on the above fix. Now we can store which particular self-heal got failed i.e GFID_OR_MISSING_ENTRY_SELF_HEAL, METADATA, DATA, ENTRY. And we can do two types of self heal failure check. 1. Individual type check: We can check which among all four (Metadata, Data, Gfid or missing entry, entry self heal) got failed. 2. In afr_self_heal_completion_cbk, we need to make check based on the fact that if any specific self heal got failed treat the complete self heal as failure so that it will populate corresponding circular buffer of event history accordingly. Change-Id: Icb91e513bcc752386fc8a78812405cfabe5cac2d BUG: 977797 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/5253 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Handle NULL fdctx in fsyncPranith Kumar K2013-06-271-1/+4
| | | | | | | | | | | | | | | | | | | Problem: If fdctx is NULL in afr_fsync, process crashes because of NULL dereference. Fix: if fdctx is NULL, always say witnessed unstable write so that fsyncs are done properly. Handled fdctx being null in afr_delayed_changelog_post_op otherwise fsync stub is never resumed and the mount was hanging. Change-Id: Icacc900e9be63c29db3325cb0e19cc250adebaac BUG: 978794 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5258 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* nfs: Remove afr split-brain handling in nfsPranith Kumar K2013-06-251-5/+0
| | | | | | | | | | | | | | | | We added this code as an interim fix until afr can handle split-brains even when opens are not issued. Afr code has matured to reject fd based fops when there are split-brains so we can remove it. Change-Id: Ib337f78eccee86469a5eaabed1a547a2cea2bdcf BUG: 974972 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5227 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Fix fd/memory leak on fsyncPranith Kumar K2013-06-241-1/+1
| | | | | | | | | Change-Id: I764883811e30ca9d9c249ad00b6762101083a2fe BUG: 976800 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5248 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* cluster/dht: In reconfig handle removed decommissioned nodesshishir gowda2013-06-211-0/+26
| | | | | | | | | | | | | | If no decommissioned nodes options are set in the options, then clear the conf->decommissioned_bricks. Change-Id: I426d2bcc874aab21b2eba0b16a580b9a26672ea2 Signed-off-by: shishir gowda <sgowda@redhat.com> BUG: 973073 Reviewed-on: http://review.gluster.org/5199 Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/afr: Perform delayed changelog wakeups for anon fdPranith Kumar K2013-06-201-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | Problem: Nfs xlator never does open on a file for performing writes, afr does not perform changelog wakeup for this fd so operations which do metadata operations as soon as the data operations are completed perceive a delay of 'post-op-delay-secs'. Fix: Perform changelog wakeup on anon-fd if the fd with same pid is not present in inode-list. Note: This approach is a short-term fix. A proper fix needs a new domain for taking metadata locks so that data/metadata locks don't compete with each other. Change-Id: I253afb289eadf30c7951e56fb2c4840d7132f5e4 BUG: 966018 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5066 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Improvement in logging of self heal completion statusVenkatesh Somyajulu2013-06-137-83/+280
| | | | | | | | | | | | | | | | | | | | | | Problem: As the end of the self heal, message logged by "afr_self_heal_completion_cbk" is inadequate to determine what exactly failed during the course of afr self heal. It is worth to have knowledge of what all types of self heal got triggered for an entity and whether the status is success or failure. Fix: At the end of self heal, it will log information about out of 4 types of self heal (gfid or missing entry self heal, metadata, data and entry self heal), who all got triggered and who all got failed or successful at the end. Change-Id: I5360762fbd7d391ac4c6af6706b4835c5801835a BUG: 968301 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/5106 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* glusterfs: discard (hole punch) supportBrian Foster2013-06-137-0/+556
| | | | | | | | | | | | | | | | Add support for the DISCARD file operation. Discard punches a hole in a file in the provided range. Block de-allocation is implemented via fallocate() (as requested via fuse and passed on to the brick fs) but a separate fop is created within gluster to emphasize the fact that discard changes file data (the discarded region is replaced with zeroes) and must invalidate caches where appropriate. BUG: 963678 Change-Id: I34633a0bfff2187afeab4292a15f3cc9adf261af Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-on: http://review.gluster.org/5090 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* gluster: add fallocate fop supportBrian Foster2013-06-137-0/+564
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implement support for the fallocate file operation. fallocate allocates blocks for a particular inode such that future writes to the associated region of the file are guaranteed not to fail with ENOSPC. This patch adds fallocate support to the following areas: - libglusterfs - mount/fuse - io-stats - performance/md-cache,open-behind - quota - cluster/afr,dht,stripe - rpc/xdr - protocol/client,server - io-threads - marker - storage/posix - libgfapi BUG: 949242 Change-Id: Ice8e61351f9d6115c5df68768bc844abbf0ce8bd Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-on: http://review.gluster.org/4969 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/dht: Make sure loc has gfidPranith Kumar K2013-06-101-0/+2
| | | | | | | | | | | | | | | | | | Problem: In some code paths neither loc->gfid nor loc->inode->gfid is populated which leads to EINVAL for linkfile setattr in dht_linkfile_attr_heal. Fix: Populate loc->gfid before dht_linkfile_attr_heal. Change-Id: I062770e6f6eaead304eff1dae81f8588a3b97eed BUG: 971805 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5178 Reviewed-by: Shishir Gowda <sgowda@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Fix unused-but-set-variable warningsPranith Kumar K2013-06-061-4/+0
| | | | | | | | | | Change-Id: Ie2b2dc54aa0d500c35752c72d3b562bcc05b1fc2 BUG: 969336 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5123 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Ignore ENOENT errors for unlink of linkfilesshishir gowda2013-06-061-2/+2
| | | | | | | | | | | | | If unlink of linkfile returns ENOENT, do not fail unlink. Proceed with unlinking of cached file. Change-Id: If7cec92b40c39d68dd9c3606c6c2c3a6bd67d27b BUG: 966848 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/4971 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/afr: Avoid order mismatch in blocking entrylksPranith Kumar K2013-06-051-6/+9
| | | | | | | | | | | | | | | | | | | | | | | Problem: When taking blocking entrylks, afr orders the entrylks based on uuid_compare of gfids of parent dirs, if they are equal then it orders them based on the basenames. While this approach works fine, the implementation assumes loc->gfids to be populated at the time of the comparison, but loc may have gfid in loc->inode->gfid instead of loc->gfid which was leading to order mismatches and dead-locks. Fix: Implemented loc_gfid which gives gfid by checking both loc->gfid, loc->inode->gfid. Used this for ordering the blocking entrylks. Change-Id: Ib0db36bbaf0df09fa87c3c3bb6a834db74fc2154 BUG: 965987 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5062 Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Prevent crash in dht_linkfile_lookupshishir gowda2013-06-041-3/+3
| | | | | | | | | | | | | Assign local = frame->local before dereferencing local->linkfile.linkfile_cbk. Additionally, fail if op_ret is non_zero. Change-Id: I96a2f34ba29887da9ccaae38a644431cf7c43265 BUG: 966858 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5141 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/dht: Set layout when inode is presentPranith Kumar K2013-06-041-1/+2
| | | | | | | | | | | | | | | | | Problem: Lookups in discovery fail with ENOENT so local->inode is never set. dht_layout_set logs the callstack when the function is called in that state. Fix: Don't set layout when lookups fail in discovery. Change-Id: I5d588314c89e3575fcf7796d57847e35fd20f89a BUG: 965434 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5055 Reviewed-by: Shishir Gowda <sgowda@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/dht: Return success in dht_discover if layout issuesJeff Darcy2013-06-033-33/+65
| | | | | | | | | | | | | | | | | We cannot heal in dht_discover, as it is a gfid based lookup, and not path based. So, returning error here would lead to app's to see failure. Also, update the layout in inode_ctx even if it has anomalies. Let subsequent heals fix the issue. Change-Id: I2358aadacf9a24e20a22ab0a6055c38c5eb6485c BUG: 960348 Original-author: shishir gowda <sgowda@redhat.com> Signed-off-by: shishir gowda <sgowda@redhat.com> Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-on: http://review.gluster.org/4959 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/afr: Removed misleading log from afr_start_crawlVenkatesh Somyajulu2013-05-311-2/+2
| | | | | | | | | | | | | | | Problem: If it is fresh volume with no files created the xattrop directory is not present. If crawl happens in that time, lookup for xattrop directory will fail and it results in printing a misleading log. Fix: Changed misleading log. Change-Id: Iae5da3e8423564d64096f88abdaf8c98e4935840 BUG: 928575 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/4993 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/dht: Handle linkfile creation with EEXIST errorshishir gowda2013-05-311-0/+59
| | | | | | | | | | | | | If linkfile create fails with EEXISTS, then check if the file is a linkfile for the same file. If not, return the error Change-Id: Iab42db54422dea69de0049b5196365e65edadd91 BUG: 966858 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5060 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>