summaryrefslogtreecommitdiffstats
path: root/xlators
Commit message (Collapse)AuthorAgeFilesLines
* protocol/client: Prevent excessive logging of client's "disconnect" messages.Venkatesh Somyajulu2013-05-283-3/+18
| | | | | | | | | | | | | | | | | | | | | Problem: Currently when gluster volume start force is executed, client process will talk to glusterd to get the port of the brick. But if brick's path is not available it cannot return brick's port. So client process will keep connecting and disconnecting from glusterd for port-query which is ultimately responsible for execssive logging of disconnect messages. Fix: Message will be logged just once at INFO level after the first disconnect from glusterd. Afterwards "disconnect" messages will be logged in DEBUG mode. Change-Id: I2b787f3820b5da45e090c562e5698fcfe24a02cd BUG: 959969 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/4953 Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* logging: Fix to avoid excessive logging.Venkatesh Somyajulu2013-05-282-3/+3
| | | | | | | | | | | | | | | | | | | | | mem_get function: Log message related to mem_pool calloc is removed as its been calculated in mempool 'stats'. This messgae is consuming nearly half of the total log messages in DEBUG mode. dht_hash_compute function: Changed log level from DEBUG to TRACE. client_fdctx_destroy function: Changed log level from DEBUG to TRACE. Change-Id: Ic948db0419e76df4e95ebd0cabaf66eadbaada6b BUG: 966851 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/5086 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Allow volume start force to succeed if brick directories are recreatedKrutika Dhananjay2013-05-251-1/+15
| | | | | | | | | | | Change-Id: I4fc3c5c829adca256bb131f4a2722abc95741158 BUG: 963665 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/5020 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* dht,posix: support for case discoveryAnand Avati2013-05-252-0/+139
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is support for discovering a filename in a given directory which has a case insensitive match of a given name. It is implemented as a virtual extended attribute on the directory where the required filename is specified in the key. E.g: sh# getfattr -e "text" -n user.glusterfs.get_real_filename:FiLe-B /mnt/samba/patchy getfattr: Removing leading '/' from absolute path names # file: mnt/samba/patchy user.glusterfs.get_real_filename:FiLe-B="file-b" In reality, there can be multiple "answers" as the backend filesystem is case sensitive and there can be multiple files which can strcasecamp() successfully. In this case we pick the first matched file from the first responding server. If a matching file does not exist, we return ENOENT (and NOT ENODATA). This way the caller can differentiate between "unsupported" glusterfs API and file not existing. This API is used by Samba VFS to perform efficient discovery of the real filename without doing a full scan at the Samba level. Change-Id: I53054c4067cba69e585fd0bbce004495bc6e39e8 BUG: 953694 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4941 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* gfapi: link inodes in relevant entry FOPsAnand Avati2013-05-251-3/+3
| | | | | | | | | | | | Do not let inode linking to happen only in lookup(). While that works, it is inefficient. Change-Id: I51bbfb6255ec4324ab17ff00566375f49d120c06 BUG: 953694 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4931 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* md-cache: support negative xattr entriesAnand Avati2013-05-251-10/+31
| | | | | | | | | | | | | | | Add support for negative xattr caching. For this, we need to fetch xattrs in every opportunity (including readdirplus) in order to treat missing key in cached dict as negative entry. This is crucial to detect missing ACL xattrs in Samba workload. Change-Id: I918a2ef4ab804724256f7546b15e808332ed518d BUG: 953694 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4929 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/dht: Ignore decommissioned subvol in overlap optimizationshishir gowda2013-05-241-0/+7
| | | | | | | | | | Change-Id: Ib727948c6e21b19fd509f258ff0aea1c5d1a84d1 BUG: 966845 Signed-off-by: shishir gowda <sgowda@redhat.com> Reviewed-on: http://review.gluster.org/5056 Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* nfs: Unable to resolve FHRajesh Joseph2013-05-241-10/+8
| | | | | | | | | | | | | | | | | | | | Bug (965435): while deleting files/directory from multiple machines nfs server logs show "Unable to resolve FH" error. Cause: The error is shown whenever the server receives rmdir/remove call and the file/directory is already deleted. Server always shows "Unable to resolve FH" irrespective of what is the actual error. Fix: The error message seems little misleading therefore changed the error message to display the actual cause. Change-Id: I4f9c151f737317d618278c59d9f66fe9f46350b8 BUG: 965435 Signed-off-by: Rajesh Joseph <rjoseph@redhat.com> Reviewed-on: http://review.gluster.org/5057 Reviewed-by: Santosh Pradhan <spradhan@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Give up biglock during rpc conn cleanupKrishnan Parthasarathi2013-05-231-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | glusterd could deadlock after a peer-detach command as follows, 1) glusterd_friend_cleanup function 'flushes' out messages in the rpc layer's queue, that haven't received a response. At this point, glusterd has already acquired the big lock. 2) The side-effect of flushing out the messages is that the corresponding call backs are called. Call backs themselves are executed after acquiring the big lock. This results in the big lock being acquired in a nested manner (in the same thread), which causes a deadlock. This can also happen during brick/NFS/SHD disconnect in volume-stop. Change-Id: Iab3aad143cd8ebbab53ea0b69687f0e7627dc8a9 BUG: 965533 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/5061 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* xlator: NULL terminate volume_options structSantosh Kumar Pradhan2013-05-222-5/+7
| | | | | | | | | | | | | | | | | Problem: volume_options struct for open-behind and quick-read xlators were not NULL terminated. Fix: Make them NULL terminated. Change-Id: I2615a1f15c6e5674030a219a99ddf91596bf346b BUG: 965995 Signed-off-by: Santosh Kumar Pradhan <spradhan@redhat.com> Reviewed-on: http://review.gluster.org/5064 Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* md-cache: Make options structure NULL terminated.Krishnan Parthasarathi2013-05-201-0/+1
| | | | | | | | | Change-Id: I8aa4f90ba7e1eecf3f978be04f8550049275464f BUG: 765785 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4994 Reviewed-by: Anand Avati <avati@redhat.com> Tested-by: Anand Avati <avati@redhat.com>
* quick-read: prune cache on write/[f]truncateAnand Avati2013-05-201-0/+43
| | | | | | | | | | | | | Cache needs to be pruned on write and [f]truncate. The lack of this is causing Samba ping-pong test to return wierd 'data increment' values during startup. Change-Id: I9cd6a839bcd02de738d78638211b78f382f58e0a BUG: 953694 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/5033 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* configure.ac: build glupy with installed pythonKaleb S. KEITHLEY2013-05-192-12/+3
| | | | | | | | | | | | | | IOW with more than just python2.6. Python2.7 is certainly what's on the vast majority of non-RHEL systems that are out there. Also our rpm.t regression test will build on epel-5 under mock; RHEL5 has Python2.4. Change-Id: I09c95c1fb6b3498e910ad239c4f0af7f786c3700 BUG: 961856 Signed-off-by: Kaleb S. KEITHLEY <kkeithle@redhat.com> Reviewed-on: http://review.gluster.org/5007 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* locks: fix leaking entrylk lock structureAnand Avati2013-05-161-0/+2
| | | | | | | | | | | | | When entrylk lock requests are blocked and granted aysnchronously, the entrylk lock structure was getting leaked. Change-Id: Ie3f29f550730189f27745d991b029e50c63e63da BUG: 962350 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4991 Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/dht: Don't do extra unref in dht-migration checksPranith Kumar K2013-05-161-5/+2
| | | | | | | | | | | | | | | | | | | Problem: syncop_open used to perform a ref in syncop_open_cbk so the extra unref was needed but now syncop_open_cbk does not take a ref so no need to do extra unref. Fix: remove the extra fd_unref and let dht_local_wipe do the final unref. Change-Id: Ibe8f9a678d456a0c7bff175306068b5cd297ecc4 BUG: 961615 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/4974 Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glusterd: Set op_errstr to error string received from peerKrutika Dhananjay2013-05-161-0/+4
| | | | | | | | | | | | ... in case of volume op failure on remote host Change-Id: I7177dc02369dffa82f217496559532d18b7c7c7a BUG: 963628 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/5018 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* client: Reset remote-port on first disconnect from brickKrishnan Parthasarathi2013-05-161-5/+9
| | | | | | | | | | Change-Id: I8940358788a7c4f8be81d705749f668a43422b8e BUG: 962930 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4988 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* rpc-transport: Moved unix socket options function to rpc-transportKrishnan Parthasarathi2013-05-162-6/+6
| | | | | | | | | | | | | This change removes the asymmetry in the 'layer' (read rpc, transport etc) in which transport options were being filled for inet and unix sockets. Change-Id: Iaa080691fd5e4c3baedffa97e9c3f16642c1fc12 BUG: 955919 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4850 Reviewed-by: Raghavendra G <raghavendra@gluster.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glusterd: Fix misleading log messages of the kind "Node <n> responded to <n>"Krutika Dhananjay2013-05-163-10/+13
| | | | | | | | | | | | | | | | | | | | | PROBLEM: glusterd logs coming from glusterd_xfer_friend_add_resp() (wrongly) indicate that a node responded to itself, although it actually responded to one of its peers. FIX: Make glusterd_xfer_friend_add_resp() distinguish between remote host and self and print the appropriate hostname. Change-Id: I2a504eeb058c08a0d378443888eb6f1dc7edc76f BUG: 963537 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/5017 Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glusterd: Start bricks on glusterd startup, only onceKrishnan Parthasarathi2013-05-154-5/+7
| | | | | | | | | | | | | | | The restarting of bricks has been deffered until the cluster 'stabilizes' itself volumes' view. Since glusterd_spawn_daemons is executed everytime a peer 'joins' the cluster, it may inadvertently restart bricks that were taken offline for say, maintenance purposes. This fix avoids that. Change-Id: Ic2a0a9657eb95c82d03cf5eb893322cf55c44eba BUG: 960190 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4973 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* mount/fuse: enable fuse real async dio when availableBrian Foster2013-05-152-0/+8
| | | | | | | | | | | | | | | | | | | | | fuse has support for optimized async. direct I/O handling via the FUSE_ASYNC_DIO init flag. Enable FUSE_ASYNC_DIO when advertised by fuse. performance/write-behind: fix dio hang Also fix a hang observed during aio-stress testing due to conflicting request handling in write-behind. Overlapping requests are skipped in pick_winds and may never continue when the conflicting write in progress returns. Add a wb_process_queue() call after a non-wb request completes to keep the queue moving. BUG: 963258 Change-Id: Ifba6e8aba7a7790b288a32067706b75f263105d4 Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-on: http://review.gluster.org/5014 Reviewed-by: Anand Avati <avati@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glupy patch by Ram, Justin: Add/Modify fops, structure types, utility fnsRam Raja2013-05-138-162/+3773
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Extend the following fops with Python: * open * readv * writev * opendir * readdir * readdirp * stat * fstat * statfs * setxattr * getxattr * fsetxattr * fgetxattr * removexattr * fremovexattr * link * unlink * readlink * symlink * mkdir * rmdir Add fd_t, inode_t and iatt_t structure types. Modify loc_t structure type; Alter the data types of the following attributes - inode, parent, gfid, pargfid. Modify uuid2str function, which returns a string equivalent for a ctype object representing a gfid, to make use of python's 'uuid' module for accurate representation of uuids. by Justin Clift: Adjust debug-trace.py to work with Python 2.6 Work around 'zero length field name in format' bug in negative.py's uuid2str function Fix indentation errors in negative.py, glupy.h, glupy.c, gluster.py Change-Id: If0fcfb2866e21c0380a973f8ffab9ea7b6a4cd5d BUG: 961856 Signed-off-by: Ram Raja <rraja@redhat.com> Reviewed-on: http://review.gluster.org/4907 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Justin Clift <jclift@redhat.com> Tested-by: Justin Clift <jclift@redhat.com>
* glusterd: Perform NULL check on rsp.op_errstr before using itKrutika Dhananjay2013-05-131-1/+1
| | | | | | | | | | Change-Id: Id18b215a91cf016964ea98d2f414293b82167d24 BUG: 962362 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/4992 Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glusterd: remove-brick: prevent removal from a replicate volume.Ravishankar N2013-05-131-2/+13
| | | | | | | | | | | | Prevent the removal of brick(s) from a plain replicate volume and display the error message at the CLI. Change-Id: I8e182404564147329d8cd364b7c7931d19f14570 BUG: 961669 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/4975 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glusterd: Fix uuid to hostname conversion for 'volume status'Kaushal M2013-05-121-3/+4
| | | | | | | | | | Change-Id: I46c41c29c2d11652f6d8ccd5637be0ac9774fc1d BUG: 927648 Signed-off-by: Kaushal M <kaushal@redhat.com> Reviewed-on: http://review.gluster.org/4873 Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Set op-version on startup based on install statusKaushal M2013-05-121-5/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | If the current installation of glusterfs doesn't have a stored op-version and is, a. a fresh install, then set op-version to maximum b. an upgrade from release which didn't have op-version support, set it to minimum. The install status is detected using the peer-uuid. If both peer-uuid and op-version are not present in the store, the installation is fresh. If peer-uuid is present, but op-version is absent in the store, the installation has been upgraded from a version which didn't support op-versions. By setting the initial op-version as above, we can ensure that a. features are not enabled accidentally during upgrades b. a fresh install starts with all possible features enabled. Change-Id: I52aed9ebeb5d3823c81e65f739a78a924ecf7e12 BUG: 954256 Signed-off-by: Kaushal M <kaushal@redhat.com> Reviewed-on: http://review.gluster.org/4867 Reviewed-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glupy: Importing Jeff's glupy project into glusterfsRam Raja2013-05-109-1/+750
| | | | | | | | | | Change-Id: I3891ef6eaf6ede7c8cbedc3298ce2501a69b2b05 BUG: 961856 Original-author: Jeff Darcy <jdarcy@redhat.com> Signed-off-by: Ram Raja <rraja@redhat.com> Reviewed-on: http://review.gluster.org/4906 Reviewed-by: Justin Clift <jclift@redhat.com> Tested-by: Justin Clift <jclift@redhat.com>
* object-storage: final removal of ufo codePeter Portante2013-05-101-54/+0
| | | | | | | | | | | | | | | | | | | See https://git.gluster.org/gluster-swift.git for the new location of the Gluster-Swift code. With this patch, no OpenStack Swift related RPMs are constructed. This patch also removes the unused code that references the user.ufo-test xattr key in the DHT translator. Change-Id: I2da32642cbd777737a41c5f9f6d33f059c85a2c1 BUG: 961902 (https://bugzilla.redhat.com/show_bug.cgi?id=961902) Signed-off-by: Peter Portante <peter.portante@redhat.com> Reviewed-on: http://review.gluster.org/4970 Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Reviewed-by: Luis Pabon <lpabon@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* glusterd: Give up big lock before performing any RPCKrishnan Parthasarathi2013-05-071-1/+13
| | | | | | | | | Change-Id: Ib0a772dc1cb9afc8adccd8f7092f480d2b525ea0 BUG: 960580 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4964 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* nfs3-server: call truncate fop only if necessaryMichael Brown2013-05-071-1/+2
| | | | | | | | | | | * nfs3svc_setattr_cbk: only truncate if requested size != current size Change-Id: I3d89e4d2b0710118f90cf5bf9cfdea61d8877491 BUG: 960725 Signed-off-by: Michael Brown <michael@netdirect.ca> Reviewed-on: http://review.gluster.org/4917 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/afr: Club missing entry, missing gfid self-healsPranith Kumar K2013-05-071-45/+8
| | | | | | | | | | | | | | | | | | | | | Problem: gfid-self-heal always assigns the gfid(GFID-1) it gets from lookup. Between the time of lookup to triggering the gfid-self-heal the entry could have changed. Now lets say there is a case where one of the files of the replica subolumes already has a gfid (GFID-2) and the other does not. In that case healing should happen with GFID-2 instead of GFID-1. Fix: Missing-entry-self-heal already handles all these cases. So removed separate handling of gfid-self-heal. Change-Id: Ie96261e9036c8f3cb4cad89347f9bf7b681cdc1a BUG: 767585 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/2670 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* nfs: avoid double fd unref in opendirRajesh Amaravathi2013-05-061-3/+1
| | | | | | | | | | | | | | | Noticed that the fd_unref was called on the fd regardless of the return value at nfs3svc_opendir_readdir_cbk(), hence removing an extra unref in the negative case in nfs_inode_opendir_cbk, which fixes the spurious fd_unref(). Change-Id: I2bf68410dd86cdf9cfe8a3d43adc27497d8bb36f BUG: 959190 Signed-off-by: Rajesh Amaravathi <rajesh@redhat.com> Reviewed-on: http://review.gluster.org/4943 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Anand Avati <avati@redhat.com>
* Revert "glusterd: Fix spurious wakeups in glusterd syncops"Krishnan Parthasarathi2013-05-042-32/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit efa154bb0a4cac34d5a9610ec25d38eebe495f22. -- Following is Avati's analysis (edited) from gerrit -- The claim of the patch (being reverted) is that it in some cases cbkfn is missed. This is wrong analysis. cbk_fn is _always_ called. The patch treats ret > 0 as a "missed cbk". ret > 0 only means socket submission was not complete, and is queued to submit asynchronously when POLLOUT is raised. This is sufficient to guarantee that cbkfn is going to be called (either the socket errors or submission succeeds and reply eventually arrives). This commit also removes spurious barrier_wake(s). call backs are guaranteed to be called even if the transport is disconnected. This means, a 'wake' would be called if rpc_clnt_submit is called. Also, we count both successful and failed operations in a particular batch of operations for the synctask_barrier_wait. So, calling synctask_barrier_wake on failure of rpc_clnt_submit (say, due to network failure) would result in a spurious wake. Change-Id: I7d508c2a54b74a65b82f097742206bc777afc53a BUG: 948686 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4922 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* synctask: implement barriers around yield, not the other wayAnand Avati2013-05-041-0/+2
| | | | | | | | | | | | | | | | | | | | In the current implementation, barriers are in the core of the syncprocessors. Wake()s are treated as syncbarrier wake. This is however delicate, as spurious wake()s of the synctask can mess up the accounting of the barrier and waking it prematurely. The fix is to keep yield() and wake() as the basic primitives, and implement barriers as an object impelemented on top of these primitives. This way, only an explicit barrier_wake() gets counted towards the barrier accounting, and spurious wakes will be truly safe. Change-Id: I8087f0f446113e5b2d0853431c0354335ccda076 BUG: 948686 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4921 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com>
* posix-acl: fetch ACLs in readdirplusAnand Avati2013-05-021-0/+6
| | | | | | | | | | | | | Not fetching ACLs in readdirplus can potentially result in spurious wrong ACL decisions (which magically go away on a lookup() which populates the ACLs) Change-Id: Ided38b4d868fab482b477ce51b4878289ef9eed0 BUG: 953694 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/4926 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Syncop callbks should take big lock tooKrishnan Parthasarathi2013-05-022-13/+53
| | | | | | | | | | Change-Id: I5ae71ab98f9a336dc9bbf0e7b2ec50a6ed42b0f5 BUG: 948686 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4938 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* glusterd: delete "volume-name" from dict before processing the next optionKrutika Dhananjay2013-05-021-0/+2
| | | | | | | | | | Change-Id: Ib78963c1f43a66dab50b443742979c7c4e4cbc23 BUG: 958790 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/4940 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Log hostname of the peer where there is cksum/version mismatchKrutika Dhananjay2013-05-023-9/+12
| | | | | | | | | Change-Id: I08065aaa3c140d4b02af4ca38f5f4d00d7f0c2bb BUG: 958739 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/4937 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* performance/io-cache: check the inode context to be NULL before accessingRaghavendra Bhat2013-05-011-0/+7
| | | | | | | | | | Change-Id: I475af7f8ffd5e5d8adbd2a74af20e56ad7751f69 BUG: 958108 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-on: http://review.gluster.org/4916 Reviewed-by: Amar Tumballi <amarts@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* Expand gluster's NFS FD header to 4 bytesMichael Brown2013-05-012-3/+15
| | | | | | | | | | | | | | * https://bugzilla.redhat.com/show_bug.cgi?id=950121 * Oracle's DNFS does not properly XDR encoding on NFS FDs that are not congruent to 0mod4 bytes long * This patch is a workaround to support Oracle's buggy code Change-Id: Ic621e2cd679a86aa9a06ed9ca684925e1e0ec43f BUG: 950121 Signed-off-by: Michael Brown <michael@netdirect.ca> Reviewed-on: http://review.gluster.org/4918 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* cluster/afr: Avoid self-healing extended attribute used by SELinux.Vijay Bellur2013-04-302-1/+9
| | | | | | | | | | | | | | | | | | Since removexattr() fails to remove "security.selinux" in a system where SELinux is enforcing, xattr self-healing fails. As a consequence of this, user extended attributes are not being healed. Added a check in afr to prune SELinux xattr from the dictionary used for removing xattrs from the sink. Minor changes in tests and md-cache as well. Signed-off-by: Vijay Bellur <vbellur@redhat.com> Change-Id: I854bfc0098dde812ce2afe64b125ee40c04bdeb1 BUG: 957877 Reviewed-on: http://review.gluster.org/4905 Reviewed-by: Venky Shankar <vshankar@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
* glusterd: Removed 'proactive' failing of volume opKrishnan Parthasarathi2013-04-301-53/+3
| | | | | | | | | | | | | | | | | | | Volume operations were failed 'proactively', on the first disconnect of a peer that was participating in the transaction. The reason behind having this kludgey code in the first place was to 'abort' an ongoing volume operation as soon as we perceive the first disconnect. But the rpc call backs themselves are capable of injecting appropriate state machine events, which would set things in motion for an eventual abort of the transaction. Change-Id: Iad7cb2bd076f22d89a793dfcd08c2d208b39c4be BUG: 847214 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4869 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cli: add a command 'gluster pool list [--xml]'Niels de Vos2013-04-261-19/+32
| | | | | | | | | | | | | | | | | * unlike 'gluster peer status', which lists only info about peers, this command lists localhost also in the list, so the sorted output from all the nodes should match. * made the output script friendly by keeping it one output per line. Change-Id: I853656753b35c617debbcceecbb71c8d6dd3c334 BUG: 764638 Original-review: http://review.gluster.org/4221 Original-author: Amar Tumballi <amarts@redhat.com> Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/4862 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Introduce volume op-versionsKaushal M2013-04-2610-418/+600
| | | | | | | | | | | | | | | | | | | | | | | Each volume is now associated with two op-versions, * op_version - the op-version of the highest op-versioned feature enabled * client_op_version - the op-version of the highest op-versioned feature enabled which affects the clients only. These two op-versions are generated dynamically and kept updated during runtime. Glusterd now uses the respective volumes' client-op-version during getspec requests. To achieve the above a new field in the vme table is introduced, client_option, this boolean field tells if the option is a client side option. Change-Id: I12c83b1dd29ab506026efd50d448cebbcee53c27 BUG: 907311 Signed-off-by: Kaushal M <kaushal@redhat.com> Reviewed-on: http://review.gluster.org/4584 Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* performance/io-cache: Avoid double mem_put in ioc_readvPranith Kumar K2013-04-261-2/+3
| | | | | | | | | | | | | On readv error io-cache frame->local is not set to NULL so the local is mem_put in STACK_DESTROY as well. This patch sets frame->local to NULL in all cases. Change-Id: I00013df1377475aa5f3c0c681dcb58b32e1e8063 BUG: 955751 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/4884 Reviewed-by: Raghavendra G <raghavendra@gluster.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/afr: Added documentation for eager-lock checkPranith Kumar K2013-04-221-0/+17
| | | | | | | | | Change-Id: Ifa42762adde8b55ef1e2b51a59c93cebd983343f BUG: 912581 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/4792 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* glusterd: volume-sync needs to work with rejected peersKrishnan Parthasarathi2013-04-221-3/+5
| | | | | | | | | Change-Id: I970a51d3f62bcf414eb9552a68d1068430b93216 BUG: 950048 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4815 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: validate performance.nfs.* option values during volume set stageKrutika Dhananjay2013-04-181-2/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | PROBLEM: performance.nfs.* option values (which are of type boolean) are not validated during the stage phase of 'volume set'. The result - nfs graph generation fails during commit phase, AFTER the option and its (invalid) value have been placed in volinfo->dict. CAUSE: nfsperfxl_option_handler() - the function that validates the values of performance.nfs.* options - never receives the (key,value) pair that needs to be set, for validation during 'volume set' stage. FIX: In build_nfs_graph(), copy the (mod_)dict containing the (option,value) parameters into set_dict before attempting to build the client graph for the volume on which the operation is being performed. Of course, an easier way out would be to simply do a 'volume reset' and pretend nothing wrong happened! Change-Id: I56b17d0239d58a9e0b7798933a3c8451e2675b69 BUG: 949930 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/4814 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* glusterd: Avoided deadlock in single node cluster, glusterd restartKrishnan Parthasarathi2013-04-161-0/+3
| | | | | | | | | | | | | | | | | | | In a single node cluster, it is possible to deadlock on the "big lock", while restarting bricks. In glusterd_restart_bricks, we perform a glusterd_brick_connect, where we release the big lock in anticipation that glusterd_brick_rpc_notify could run in the same C stack (and deadlocking). So, in the restart code path, we could unlock before we have performed a lock on the big lock. To fix this, we need to take the big lock in the glusterd_launch_synctask 'thread' as well. Change-Id: I1abea1ca82b55c784b8a810a8194f254b32b1dcc BUG: 948686 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4837 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* glusterd: big lock - a coarse-grained locking to prevent racesKrishnan Parthasarathi2013-04-1216-106/+656
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are primarily three lists that are part of glusterd process, that are concurrently accessed. Namely, priv->volumes, priv->peers and volinfo->bricks_list. Big-lock approach ----------------- WHAT IS IT? Big lock is a coarse-grained lock which protects all three lists, mentioned above, from racy access. HOW DOES IT WORK? At any given point in time, glusterd's thread(s) are in execution _iff_ there is a preceding, inbound network event. Of course, the sigwaiter thread and timer thread are exceptions. A network event is an external trigger to glusterd, via the epoll thread, in the form of POLLIN and POLLERR. As long as we take the big-lock at all such entry points and yield it when we are done, we are guaranteed that all the network events, accessing the global lists, are serialised. This amounts to holding the big lock at - all the handlers of all the actors in glusterd. (POLLIN) - all the cbks in glusterd. (POLLIN) - rpc_notify (DISCONNECT event), if we access/modify one of the three lists. (POLLERR) In the case of synctask'ized volume operations, we must remember that, if we held the big lock for the entire duration of the handler, we may block other non-synctask rpc actors from executing. For eg, volume-start would block in PMAP SIGNIN, if done incorrectly. To prevent this, we need to yield the big lock, when we yield the synctask, and reacquire on waking up of the synctask. Change-Id: Ib929f9905b55fb6c3fc27fefb497a26dba058e4f BUG: 948686 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/4784 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>