summaryrefslogtreecommitdiffstats
path: root/xlators/cluster/ec
Commit message (Collapse)AuthorAgeFilesLines
...
* ec: Fix return errors when not enough bricksXavier Hernandez2014-12-058-14/+81
| | | | | | | | | | | | | | | | | | | | | Changes introduced by this patch: * Fix an incorrect error propagation when the state of the life cycle of a fop returns an error. * Fix incorrect unlocking of failed locks. * Return ENOTCONN if there aren't enough bricks online. * In readdir(p) check that the fd has been successfully open by a previous opendir. Change-Id: Ib44f25a1297849ebcbab839332f3b6359f275ebe BUG: 1162805 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9098 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix mutex related coverity scan issuesXavier Hernandez2014-12-041-2/+14
| | | | | | | | | | | | | | | | | | This patch solves 3 issues detected by coverity scan: CID1241484 Data race condition CID1241486 Data race condition CID1256173 Thread deadlock With this patch, inode lock is never acquired inside a region locked with fop->lock. Change-Id: I35c4633efd1b68b9f72b42661fa7c728b1f52c6a BUG: 1170254 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9230 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* ec: Fix incorrect value of EC_MAX_NODESXavier Hernandez2014-12-042-1/+4
| | | | | | | | | | | | | EC_MAX_NODES was incorrectly calculated. Now the value if computed as the minimum between the theoretical maximum and the limit imposed by the Galois Field. Change-Id: I75a8345147f344f051923d66be2c10d405370c7b BUG: 1167419 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9193 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* ec: Fix self-healing issues.Xavier Hernandez2014-12-0410-313/+548
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Three problems have been detected: 1. Self healing is executed in background, allowing the fop that detected the problem to continue without blocks nor delays. While this is quite interesting to avoid unnecessary delays, it can cause spurious failures of self-heal because it may try to recover a file inside a directory that a previous self-heal has not recovered yet, causing the file self-heal to fail. 2. When a partial self-heal is being executed on a directory, if a full self-heal is attempted, it won't be executed because another self-heal is already in process, so the directory won't be fully repaired. 3. Information contained in loc's of some fop's is not enough to do a complete self-heal. To solve these problems, I've made some changes: * Improved ec_loc_from_loc() to add all available information to a loc. * Before healing an entry, it's parent is checked and partially healed if necessary to avoid failures. * All heal requests received for the same inode while another self-heal is being processed are queued. When the first heal completes, all pending requests are answered using the results of the first heal (without full execution), unless the first heal was a partial heal. In this case all partial heals are answered, and the first full heal is processed normally. * An special virtual xattr (not physically stored on bricks) named 'trusted.ec.heal' has been created to allow synchronous self-heal of files. Now, the recommended way to heal an entire volume is this: find <mount> -d -exec getfattr -h -n trusted.ec.heal {} \; Some minor changes: * ec_loc_prepare() has been renamed to ec_loc_update(). * All loc management functions return 0 on success and -1 on error. * Do not delay fop unlocks if heal is needed. * Added basic ec xattrs initially on create, mkdir and mknod fops. * Some coding style changes Change-Id: I2a5fd9c57349a153710880d6ac4b1fa0c1475985 BUG: 1161588 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9072 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* ec: Change licenseXavier Hernandez2014-12-0323-369/+138
| | | | | | | | | | Change-Id: Iae90ade2421898417b53dec0417a610cf306c44b BUG: 1168167 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9201 Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Avoid self-heal on directories on (f)stat callsXavier Hernandez2014-11-151-1/+2
| | | | | | | | | | | | | | | | | | | To avoid inconsistent directory listings, a full self-heal cannot happen on a directory until all its contents have been healed. This is controlled by a manual command using getfattr recursively and in post-order. While navigating the directories, sometimes an (f)stat fop can be sent. This fop caused a full self-heal of the directory. This patch makes that (f)stat only initiates a partial self-heal. Change-Id: I0a92bda8f4f9e43c1acbceab2d7926944a8a4d9a BUG: 1163760 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9117 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* ec: Correctly handle quota xattrsXavier Hernandez2014-11-121-0/+53
| | | | | | | | | Change-Id: I35e11d83c318210d44b918e847cf13db35b01510 BUG: 1158008 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8990 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* ec: Correctly handle xtime extended attributeXavier Hernandez2014-10-281-2/+39
| | | | | | | | | | Change-Id: I2bd34f063d6bf1835d5ae57a8e9aa03f3ec3deb3 BUG: 1156404 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8972 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix rebalance issuesXavier Hernandez2014-10-275-113/+218
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some issues in ec xlator made that rebalance didn't complete successfully and generated some warnings and errors in the log. The most critical error was a race condition that caused false corruption detection when two specific operations were executed sequentially and they shared the same lock. This explains the problem: 1. A setxattr is issued. 2. setxattr: ec locks the inode before updating the xattr. 3. setxattr: The xattr is updated. 4. setxattr: Upper xlator is notified that the operation completed. 5. setxattr: A background task is initiated to update the version of the file. 6. A stat is issued on the same file. 7. stat: Since the lock is already acquired, it's reused. 8. stat: A lookup is issued to determine version and size information of the file. At this point, operations 5 and 8 can interfere. This can make that lookup sees different information on each brick, determining that some bricks are corrupted and incorrectly excluding them from the operation and initiating a self-heal. In some cases this false detection combined with self-heal could lead to invalid updates of the trusted.ec.size xattr, leaving the file smaller than it should be. This only happens if the first operation does not perform a lookup, because chained operations reuse the information returned by the previous one, avoiding this kind of problems. To solve this, now the background update is executed atomically with the posterior unlock. This avoids some reuses of the lock while updating. However this reduces performance because the window in which new requests can reuse the lock is much smaller now. This has been alleviated by using the same technique implemented in AFR (i.e. waiting some time before releasing the lock). Some minor changes also introduced in this patch: * Bug in management of 'trusted.glusterfs.pathinfo' that was writing beyond the allocated space. * Uninitialized variable. * trusted.ec.config was not created for regular files created with mknod. * An invalid state was used in access fop. Change-Id: Idfaf69578ed04dbac97a62710326729715b9b395 BUG: 1152902 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8947 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix self-heal issuesXavier Hernandez2014-10-2113-302/+391
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Doing an 'ls' of a directory that has been modified while one of the bricks was down, sometimes returns the old directory contents. Cause: Directories are not marked when they are modified as files are. The ec xlator balances requests amongst available and healthy bricks. Since there is no way to detect that a directory is out of date in one of the bricks, it is used from time to time to return the directory contents. Solution: Basically the solution consists in use versioning information also for directories, however some additional changes have been necessary. Changes: * Use directory versioning: This required to lock full directory instead of a single entry for all requests that add or remove entries from it. This is needed to allow atomic version update. This affects the following fops: create, mkdir, mknod, link, symlink, rename, unlink, rmdir Another side effect is that opendir requires to do a previous lookup to get versioning information and discard out of date bricks for subsequent readdir(p) calls. * Restrict directory self-heal: Till now, when one discrepancy was found in lookup, a self-heal was automatically started. This caused the versioning information of a bad directory to be healed instantly, making the original problem to reapear again. To solve this, when a missing directory is detected in one or more bricks on lookup or opendir fops, only a partial self-heal is performed on it. A partial self-heal basically creates the directory but does not restore any additional information. This avoids that an 'ls' could repair the directory and cause the problem to happen again. With this change, output of 'ls' is always consistent. However, since the directory has been created in the brick, this allows any other operation on it (create new files, for example) to succeed on all bricks and not add additional work to the self-heal process. To force a self-heal of a directory, any other operation must be done on it. For example a getxattr. With these changes, the correct healing procedure that would avoid inconsistent directory browsing consists on a post-order traversal of directoriesi being healed. This way, the directory contents will be healed before healing the directory itslef. * Additional changes to fix self-heal errors - Don't use fop->fd to decide between fd/loc. open, opendir and create have an fd, but the correct data is in loc. - Fix incorrect management of bad bricks per inode/fd. - Fix incorrect selection of fop's target bricks when there are bad bricks involved. - Improved ec_loc_parent() to always return a parent loc as complete as possible. Change-Id: Iaf3df174d7857da57d4a87b4a8740a7048b366ad BUG: 1149726 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8916 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* ec: Fix 32 bits issues on file size calculationXavier Hernandez2014-10-202-6/+4
| | | | | | | | | | | | | | Some additional 32 bits issues have been added by a recent patch. This patch solves it. Change-Id: Ice81032fbe8e36e5ccad19a781b7876891993906 BUG: 1146903 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8882 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Emmanuel Dreyfus <manu@netbsd.org> Tested-by: Emmanuel Dreyfus <manu@netbsd.org> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix incorrect management of healed bricksXavier Hernandez2014-10-203-7/+16
| | | | | | | | | | | | | | | | | | The final lookup made to restore final file attributes after a self-heal did clear the mask of bad bricks, causing that the final setattr won't modify any brick at all. This caused that some attriutes, specially the modification time of the file didn't get updated properly. Now the mask of healed bricks is saved before doing the last lookup. It's also used to correctly report the repaired bricks. Change-Id: Ib94083c9e1b562515dfb54f9574120f1f031dccc BUG: 1149723 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8905 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix memory leak caused by undestroyed fopsXavier Hernandez2014-10-031-1/+1
| | | | | | | | | | | | | | Operations processed by ec_dispatch_one() were not correctly completed by ec_complete(), leaving some structures in memory. Now ec_complete() also calls ec_resume() for this type of fops. Change-Id: Iaf0f2e8227399ebb735db9f1bd007593e0ece041 BUG: 1148520 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8896 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Add state dump supportXavier Hernandez2014-10-031-0/+30
| | | | | | | | | | | | Change-Id: I4504f3050674dde217e79af28cb4d2b5370fe2d5 BUG: 1148010 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8891 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Emmanuel Dreyfus <manu@netbsd.org> Tested-by: Emmanuel Dreyfus <manu@netbsd.org> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Add config information in an xattrXavier Hernandez2014-09-237-1/+185
| | | | | | | | | | | | | | | | | | | | | | | | | | | | To simplify backward compatibility of the ec xlator when some parameter or the implementation itself is changed, a new xattr is added to each file with the configuration needed to recover it. The new attribute is called 'trusted.ec.config', and it's a 64-bit value containing the following information: 8 bits: version of the config information (currently always 0) 8 bits: algorithm used to encode the file (currently always 0) 8 bits: size of the galois field (currently always 8) 8 bits: number of bricks 8 bits: redundancy 24 bits: chunk size (currently 512) This new xattr could allow, in a future version, to have different configurations per file. Change-Id: I8c12d40ff546cc201fc66caa367484be3d48aeb4 BUG: 1140861 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8770 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix invalid inode lock in ftruncateXavier Hernandez2014-09-195-21/+21
| | | | | | | | | | | | | | | | | | | The fops 'truncate' and 'ftruncate' share some code and inodelk() was always made against the inode inside the loc_t structure instead of that of fd_t. Since ftruncate has the loc initialized to NULL, this fop was executed without any lock, allowing some concurrent modifications in the file size. Also changed the way in which 'fop' and 'ffop' are differentiated in shared code. Now it uses 'id' field instead of checking if 'fd' is NULL. Change-Id: Ibd18accf2652193b395a841b9029729e5f4867c6 BUG: 1140396 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8695 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix some size_t vars to 64 bits even on 32 bits machinesXavier Hernandez2014-09-196-21/+20
| | | | | | | | | | | | | | | | The 64 bits 'trusted.ec.size' extended attribute was incorrectly computed on 32 bits machines due to an overflow on negative numbers. Also changed some potentially dangerous uses of size_t in other places. Change-Id: Id76cfe49a2f350e564b5c71d8c8644fb9ce86662 BUG: 1125312 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8738 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Optimize read/write performanceXavier Hernandez2014-09-1513-268/+706
| | | | | | | | | | | | | | | | | | This patch significantly improves performance of read/write operations on a dispersed volume by reusing previous inodelk/ entrylk operations on the same inode/entry. This reduces the latency of each individual operation considerably. Inode version and size are also updated when needed instead of on each request. This gives an additional boost. Change-Id: I4b98d5508c86b53032e16e295f72a3f83fd8fcac BUG: 1122586 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8369 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* ec: Only heal data/metadata when inode has enough informationXavier Hernandez2014-09-151-0/+8
| | | | | | | | | | | | | | Sometimes loc_t structure in a heal request doesn't contain enough information to do an inodelk call (basically the gfid is missing). In these cases, self heal only recovers entry information. Change-Id: I459990c7df728ff4baf164df046672ddcde3efa5 BUG: 1122581 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8368 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* ec: Do not destroy inode context on inode invalidationXavier Hernandez2014-09-111-28/+13
| | | | | | | | | | | | | | Currently there is no need to handle inode invalidation requests, so this callback has been removed. Change-Id: I0ac2e47679bf62b1493e0403178305923bc036e8 BUG: 1126932 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8420 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Removed SSE2 dependencyXavier Hernandez2014-09-117-10271/+11684
| | | | | | | | | | | | | | | | | | | | | | | | | This patch implements the Galois Field multiplications using pure C code without any assembler support. This makes the ec xlator portable to other architectures. In the future it will be possible to use an optimized implementation of the multiplications using architecture dependent facilities (it will be automatically detected and configured). To allow bricks with different machine word sizes to be able to work seamlessly in the same volume, the minimum fragment length to be stored in any brick has been fixed to 512 bytes. Otherwise, different implementations will corrupt the data (SSE2 used 128 bytes, while new implementation would have used 64). This patch also removes the '-msse2' option added on patch http://review.gluster.org/8395/ Change-Id: Iaf6e4ef3dcfda6c68f48f16ca46fc4fb61a215f4 BUG: 1125166 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8413 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* cluster/ec: Fix incorrect management of NFS requestsXavier Hernandez2014-08-023-89/+51
| | | | | | | | | | | | | | | | | | | Some operations, specially those comming from NFS, do not use a regular fd and use an anonymous fd (i.e. a previous open call has not been sent). Any context information created during open or create will not be present on these fd's, so we simply return NULL for contexts of those fd. Also it seems that NFS can send write requests with a very big buffer (higher that the default value of 128 KB). Some changes have been made to correctly handle these large buffers. Change-Id: I281476bd0d2cbaad231822248d6a616fcf5d4003 BUG: 1122417 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8367 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Add -msse2 option to avoid fedora/rawhide compilation errorsXavier Hernandez2014-07-311-1/+1
| | | | | | | | | | | | | | | | | This solves a compilation error on some compiler versions. To avoid compilation issues on non-Intel architectures, patch http://review.gluster.org/8366/ has already been merged. It disables ec on those architectures. These modifications are temporary patches until a proper solution for bug #1125166 is ready. Change-Id: I74d0b79e84601cc4f86ad08ce0f8102b99a79a68 BUG: 1125168 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8395 Reviewed-by: Niels de Vos <ndevos@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* porting: include compat-errno.h for errno'sHarshavardhana2014-07-221-0/+1
| | | | | | | | | | | | | | | disperse module fails to compile since ENODATA is non-existent on FreeBSD/Darwin Use errno conversion in compat-errno.h to avoid build issues. Change-Id: I8203b7195c198c77202bde9bbec1813a487f923a BUG: 1111774 Signed-off-by: Harshavardhana <harsha@harshavardhana.net> Reviewed-on: http://review.gluster.org/8320 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Humble Devassy Chirammal <humble.devassy@gmail.com>
* ec: Fixed coveriry scan issuesXavier Hernandez2014-07-219-39/+66
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | CID list: 1226163 Logically dead code 1226166 Missing break in switch 1226167 Missing break in switch 1226168 Missing break in switch 1226169 Missing break in switch 1226170 Missing break in switch 1226171 Missing break in switch 1226172 Missing break in switch 1226173 Missing break in switch 1226174 Missing break in switch 1226175 Missing break in switch 1226176 Missing break in switch 1226177 Missing break in switch 1226178 Data race condition 1226179 Data race condition 1226180 Data race condition 1226181 Thread deadlock 1226182 Uninitialized pointer read 1226183 Uninitialized pointer read 1226184 Read from pointer after free Change-Id: I4d33aa42289371927175c43bb29e018df64fb943 BUG: 789278 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8317 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* porting: use __builtin_ffsll() instead of ffsll()Harshavardhana2014-07-161-0/+4
| | | | | | | | | | | | | - NetBSD/Darwin doesn't implement ffsll() - use Compiler builtin Change-Id: Iee78b4b81747b0bd3877fd2fcb98746f642ce080 BUG: 764655 Signed-off-by: Harshavardhana <harsha@harshavardhana.net> Reviewed-on: http://review.gluster.org/8308 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-by: Justin Clift <justin@gluster.org>
* cluster/ec: Added erasure code translatorXavier Hernandez2014-07-1125-0/+26031
Change-Id: I293917501d5c2ca4cdc6303df30cf0b568cea361 BUG: 1118629 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/7749 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>