summaryrefslogtreecommitdiffstats
path: root/libglusterfs/src/glusterfs
Commit message (Collapse)AuthorAgeFilesLines
...
* dict.{c,h}: remove the lock from the _data structYaniv Kaul2019-10-111-1/+0
| | | | | | | | | I'm not sure why it was there and I did not see any use for it. In the hope I did not miss anything, I removed it. Change-Id: I02fa2e8e2a598b488fddbff4c7168dc4a41929b2 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* protocol/handshake: pass volume-id for extra checkAmar Tumballi2019-09-301-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With added check of volume-id during handshake, we can be sure to not connect with a brick if this gets re-used in another volume. This prevents any accidental issues which can happen with a stale client process lurking along. Also added test case for testing same volume name which would fetch a different volfile (ie, different bricks, different type), and a different volume name, but same brick. For reference: Currently a client<->server handshake happens in glusterfs through protocol/client translator (setvolume) to protocol/server using a dictionary which containes many keys. Rejection happens in server side if some of the required keys are missing in handshake dictionary. Till now, there was no single unique identifier to validate for a client to tell server if it is actually talking to a corresponding server. All we look in protocol/client is a key called 'remote-subvolume', which should match with a subvolume name in server volume file, and for any volume with same brick name (can be present in same cluster due to recreate), it would be same. This could cause major issue, when a client was connected to a given brick, in one volume would be connected to another volume's brick if its re-created/re-used. To prevent this behavior, we are now passing along 'volume-id' in handshake, which would be preserved for the life of client process, which can prevent this accidental connections. NOTE: This behavior wouldn't be applicable for user-snapshot enabled volumes, as snapshotted volume's would have different volume-id. Fixes: bz#1620580 Change-Id: Ie98286e94ce95ae09c2135fd6ec7d7c2ca1e8095 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* core/syncop: Bail out if frame creation failsSoumya Koduri2019-09-121-0/+6
| | | | | | | | | | There could be cases (either due to insufficient memory or corrupted mem-pool) due to which frame creation fails. Bail out with error in such cases. Change-Id: I8cc0a5852f6f04d2bac991e4eb79ecb42577da11 Fixes: bz#1748448 Signed-off-by: Soumya Koduri <skoduri@redhat.com>
* cluster/ec: quorum-count implementationPranith Kumar K2019-09-081-1/+3
| | | | | | fixes: #721 Change-Id: I5333540e3c635ccf441cf1f4696e4c8986e38ea8 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* graph/cleanup: Fix race in graph cleanupMohammed Rafi KC2019-09-052-0/+3
| | | | | | | | | | | | | | | | | We were unconditionally cleaning up the grap when we get child_down followed by parent_down. But this is prone to race condition when some of the bricks are already disconnected. In this case, even before the last child down is executed in the client xlator code,we might have freed the graph. Because the child_down event is alreadt recevied. To fix this race, we have introduced a check to see if all client xlator have cleared thier reconnect chain, and called the child_down for last time. Change-Id: I7d02813bc366dac733a836e0cd7b14a6fac52042 fixes: bz#1727329 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* ctime: Fix incorrect realtime passed to frame->root->ctimeKotresh HR2019-08-221-0/+2
| | | | | | | | | | | | On systems that don't support "timespec_get"(e.g., centos6), it was using "clock_gettime" with "CLOCK_MONOTONIC" to get unix epoch time which is incorrect. This patch introduces "timespec_now_realtime" which uses "clock_gettime" with "CLOCK_REALTIME" which fixes the issue. Change-Id: I57be35ce442d7e05319e82112b687eb4f28d7612 Signed-off-by: Kotresh HR <khiremat@redhat.com> fixes: bz#1743652
* logging: Structured logging reference PRAravinda VK2019-08-201-10/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | To convert the existing `gf_msg` to `gf_smsg`: - Define `_STR` of respective Message ID as below(In `*-messages.h`) #define PC_MSG_REMOTE_OP_FAILED_STR "remote operation failed." - Change `gf_msg` to use `gf_smsg`. Convert values into fields and add any missing fields. Note: `errno` and `error` fields will be added automatically to log message in case errnum is specified. Example: gf_smsg( this->name, // Name or log domain GF_LOG_WARNING, // Log Level rsp.op_errno, // Error number PC_MSG_REMOTE_OP_FAILED, // Message ID "path=%s", local->loc.path, // Key Value 1 "gfid=%s", loc_gfid_utoa(&local->loc), // Key Value 2 NULL // Log End ); Key value pairs formatting Help: gf_slog( this->name, // Name or log domain GF_LOG_WARNING, // Log Level rsp.op_errno, // Error number PC_MSG_REMOTE_OP_FAILED, // Message ID "op=CREATE", // Static Key and Value "path=%s", local->loc.path, // Format for Value "brick-%d-status=%s", brkidx, brkstatus, // Use format for key and val NULL // Log End ); Before: [2019-07-03 08:16:18.226819] W [MSGID: 114031] [client-rpc-fops_v2.c \ :2633:client4_0_lookup_cbk] 0-gv3-client-0: remote operation failed. \ Path: / (00000000-0000-0000-0000-000000000001) [Transport endpoint \ is not connected] After: [2019-07-29 07:50:15.773765] W [MSGID: 114031] \ [client-rpc-fops_v2.c:2633:client4_0_lookup_cbk] 0-gv1-client-0: \ remote operation failed. [{path=/f1}, \ {gfid=00000000-0000-0000-0000-000000000000}, \ {errno=107}, {error=Transport endpoint is not connected}] To add new `gf_smsg`, Add a Message ID in respective `*-messages.h` file and the follow the steps mentioned above. Change-Id: I4e7d37f27f106ab398e991d931ba2ac7841a44b1 Updates: #657 Signed-off-by: Aravinda VK <avishwan@redhat.com>
* posix: In brick_mux brick is crashed while start/stop volume in loopMohit Agrawal2019-08-201-0/+3
| | | | | | | | | | | | | | | Problem: In brick_mux environment sometime brick is crashed while volume stop/start in a loop.Brick is crashed in janitor task at the time of accessing priv.If posix priv is cleaned up before call janitor task then janitor task is crashed. Solution: To avoid the crash in brick_mux environment introduce a new flag janitor_task_stop in posix_private and before send CHILD_DOWN event wait for update the flag by janitor_task_done Change-Id: Id9fa5d183a463b2b682774ab5cb9868357d139a4 fixes: bz#1730409 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* client_t.c: removal of dead code.Yaniv Kaul2019-08-201-3/+0
| | | | | | Change-Id: Id9f5f448db305f3135a1fdca61b1d7ec898c63a4 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* libglusterfs: remove dependency of rpcAmar Tumballi2019-08-162-11/+15
| | | | | | | | | | | | | | | | | | Goal: 'libglusterfs' files shouldn't have any dependency outside of the tree, specially the header files, shouldn't have '#include' from outside the tree. Fixes: * Had to introduce libglusterd so, methods and structures required for only mgmt/glusterd, and cli/ are separated from 'libglusterfs/' * Remove rpc/xdr/gen from build, which was used mainly so dependency for libglusterfs could be properly satisfied. * Move rpcsvc_auth_data to client_t.h, so all dependencies could be handled. Updates: bz#1636297 Change-Id: I0e80243a5a3f4615e6fac6e1b947ad08a9363fce Signed-off-by: Amar Tumballi <amarts@redhat.com>
* fuse: Set limit on invalidate queue sizeN Balachandran2019-08-142-0/+2
| | | | | | | | | | | | | If the glusterfs fuse client process is unable to process the invalidate requests quickly enough, the number of such requests quickly grows large enough to use a significant amount of memory. We are now introducing another option to set an upper limit on these to prevent runaway memory usage. Change-Id: Iddfff1ee2de1466223e6717f7abd4b28ed947788 Fixes: bz#1732717 Signed-off-by: N Balachandran <nbalacha@redhat.com>
* fuse: rate limit reading from fuse device upon receiving EPERMCsaba Henk2019-08-081-0/+2
| | | | | | Fixes: bz#1644322 Change-Id: I53e8fa362cd8c7d04fb1c4abb606a9abb642c592 Signed-off-by: Csaba Henk <csaba@redhat.com>
* event: rename event_XXX with gf_ prefixedXiubo Li2019-07-291-12/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I hit one crash issue when using the libgfapi. In the libgfapi it will call glfs_poller() --> event_dispatch() in file api/src/glfs.c:721, and the event_dispatch() is defined by libgluster locally, the problem is the name of event_dispatch() is the extremly the same with the one from libevent package form the OS. For example, if a executable program Foo, which will also use and link the libevent and the libgfapi at the same time, I can hit the crash, like: kernel: glfs_glfspoll[68486]: segfault at 1c0 ip 00007fef006fd2b8 sp 00007feeeaffce30 error 4 in libevent-2.0.so.5.1.9[7fef006ed000+46000] The link for Foo is: lib_foo_LADD = -levent $(GFAPI_LIBS) It will crash. This is because the glfs_poller() is calling the event_dispatch() from the libevent, not the libglsuter. The gfapi link info : GFAPI_LIBS = -lacl -lgfapi -lglusterfs -lgfrpc -lgfxdr -luuid If I link Foo like: lib_foo_LADD = $(GFAPI_LIBS) -levent It will works well without any problem. And if Foo call one private lib, such as handler_glfs.so, and the handler_glfs.so will link the GFAPI_LIBS directly, while the Foo won't and it will dlopen(handler_glfs.so), then the crash will be hit everytime. The link info will be: foo_LADD = -levent libhandler_glfs_LIBADD = $(GFAPI_LIBS) I can avoid the crash temporarily by linking the GFAPI_LIBS in Foo too like: foo_LADD = $(GFAPI_LIBS) -levent libhandler_glfs_LIBADD = $(GFAPI_LIBS) But this is ugly since the Foo won't use any APIs from the GFAPI_LIBS. And in some cases when the --as-needed link option is added(on many dists it is added as default), then the crash is back again, the above workaround won't work. Fixes: #699 Change-Id: I38f0200b941bd1cff4bf3066fca2fc1f9a5263aa Signed-off-by: Xiubo Li <xiubli@redhat.com>
* ctime: Set mdata xattr on legacy filesKotresh HR2019-07-224-1/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | Problem: The files which were created before ctime enabled would not have "trusted.glusterfs.mdata"(stores time attributes) xattr. Upon fops which modifies either ctime or mtime, the xattr gets created with latest ctime, mtime and atime, which is incorrect. It should update only the corresponding time attribute and rest from backend Solution: Creating xattr with values from brick is not possible as each brick of replica set would have different times. So create the xattr upon successful lookup if the xattr is not created Note To Reviewers: The time attributes used to set xattr is got from successful lookup. Instead of sending the whole iatt over the wire via setxattr, a structure called mdata_iatt is sent. The mdata_iatt contains only time attributes. Change-Id: I5e535631ddef04195361ae0364336410a2895dd4 fixes: bz#1593542 Signed-off-by: Kotresh HR <khiremat@redhat.com>
* Replace usleep() with nanosleep()Vijay Bellur2019-07-111-0/+6
| | | | | | | | | | | | | | | | | | | As usleep has been obsoleted, changed all invocations of usleep to nanosleep. From man 3 usleep: "4.3BSD, POSIX.1-2001. POSIX.1-2001 declares this function obsolete; use nanosleep(2) instead. POSIX.1-2008 removes the specification of usleep()." Added a helper function gf_nanosleep() to have a single place for handling edge cases that might arise from the conversion of usleep to nanosleep and allow the sleep to resume with right remaining value upon being interrupted. Fixes: bz#1721686 Change-Id: Ia39ab82c9e0f4669d2c00d4cdf25e38d94ef9f62 Signed-off-by: Vijay Bellur <vbellur@redhat.com>
* Remove hadoop related code from the codebaseVijay Bellur2019-07-091-1/+0
| | | | | | | | | As Hadoop is no longer supported, dropping code for handling Hadoop access. Fixes: bz#1728417 Signed-off-by: Vijay Bellur <vbellur@redhat.com> Change-Id: I8fcf4faacb364f1c9a8abb0c48faec337087f845
* glusterd/svc: update pid of mux volumes from the shd processMohammed Rafi KC2019-07-092-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | For a normal volume, we are updating the pid from a the process while we do a daemonization or at the end of the init if it is no-daemon mode. Along with updating the pid we also lock the file, to make sure that the process is running fine. With brick mux, we were updating the pidfile from gluterd after an attach/detach request. There are two problems with this approach. 1) We are not holding a pidlock for any file other than parent process. 2) There is a chance for possible race conditions with attach/detach. For example, shd start and a volume stop could race. Let's say we are starting an shd and it is attached to a volume. While we trying to link the pid file to the running process, this would have deleted by the thread that doing a volume stop. Change-Id: I29a00352102877ce09ea3f376ca52affceb5cf1a Updates: bz#1722541 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* glusterfs-fops: fix the modularityAmar Tumballi2019-07-024-22/+248
| | | | | | | | | | | | | | | | | | | | | | | | | | glusterfs-fops.h was moved to rpc/xdr to support compound fops. (ref: https://review.gluster.org/14032, 2f945b86d3) This was fine as long as all these header files were in single include directory after 'install'. With the move to separate out glusterfs specific header files into another directory inside /usr/include (ref: https://review.gluster.org/21746, 20ef211cfa), glusterfs-fops.h file was not in the proper path when an external .c file tried to include any of glusterfs specific .h file (like xlator.h). Now, we have removed compound-fops, with that, none of the enums declared in glusterfs-fops.h are actually getting used on wire anymore. Hence, it makes sense to get this to libglusterfs/src as a single point of definition. With this change, the external programs can use glusterfs header files. also remove some enum definitions which are not used in code anymore. Updates: bz#1636297 Change-Id: I423c44d3dbe2efc777299c544ece3cb172fc7e44 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* core: fix memory allocation issuesXavi Hernandez2019-06-261-1/+4
| | | | | | | | | | | | | | | | | | | | | | Two problems have been identified that caused that gluster's memory usage were twice higher than required. 1. An off by 1 error caused that all objects allocated from the memory pools were taken from a pool bigger than required. Since each pool corresponds to a size equal to a power of two, this was wasting half of the available memory. 2. The header information used for accounting on each memory object was not taken into consideration when searching for a suitable memory pool. It was added later when each individual block was allocated. This made this space "invisible" to memory accounting. Credits: Thanks to Nithya Balachandran for identifying this problem and testing this patch. Fixes: bz#1722802 Change-Id: I90e27ad795fe51ca11c13080f62207451f6c138c Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* * core: do not assert in inode_unref if the inode table cleanup has startedRaghavendra Bhat2019-06-251-0/+4
| | | | | | | | | | | | | | | | | | | | | | There is a good chance that, the inode on which unref came has already been zero refed and added to the purge list. This can happen when inode table is being destroyed (glfs_fini is something which destroys the inode table). Consider a directory 'a' which has a file 'b'. Now as part of inode table destruction zero refing of inodes does not happen from leaf to the root. It happens in the order inodes are present in the list. So, in this example, the dentry of 'b' would have its parent set to the inode of 'a'. So if 'a' gets zero refed first (as part of inode table cleanup) and then 'b' has to zero refed, then dentry_unset is called on the dentry of 'b' and it further goes on to call inode_unref on b's parent which is 'a'. In this situation, GF_ASSERT would be called as the refcount of 'a' has been already set to zero. So, return the inode (in the function inode_unref without doing anything) if the inode table cleanup has already started and inode's refcount is zero. Change-Id: I91e0a807d5c9ce0daae5a611c38da379fd11076e fixes: bz#1722546 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com>
* compat.h: fix a \#pragma poisoning errorv8devDan2019-06-251-0/+3
| | | | | | | | | | | | | | | | | | Fixes a failure to compile glusterfs with glibc 2.25 (on Gentoo and other systems) Making all in src CC libglusterfs_la-dict.lo In file included from iatt.h:16:0, from common-utils.h:44, from dict.c:20: /usr/include/sys/sysmacros.h:57:45: error: attempt to use poisoned "system" directly. If you did not intend to use a system-defined macro\n\ ^ make[4]: *** [Makefile:959: libglusterfs_la-dict.lo] Error 1 Fixes: bz#1494654 Change-Id: I09b910b5772f52e853f87d81f3923eed9a90f7a1 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* core: improve timer accuracyXavier Hernandez2019-06-171-2/+3
| | | | | | | | Also fixed some issues on test ec-1468261.t. Change-Id: If156f86af986d9eed13cdd1f15c5a7214cd11706 Updates: bz#1193929 Signed-off-by: Xavier Hernandez <jahernan@redhat.com>
* multiple files: another attempt to remove includesYaniv Kaul2019-06-1414-45/+24
| | | | | | | | | | | | | | | | | | There are many include statements that are not needed. A previous more ambitious attempt failed because of *BSD plafrom (see https://review.gluster.org/#/c/glusterfs/+/21929/ ) Now trying a more conservative reduction. It does not solve all circular deps that we have, but it does reduce some of them. There is just too much to handle reasonably (dht-common.h includes dht-lock.h which includes dht-common.h ...), but it does reduce the overall number of lines of include we need to look at in the future to understand and fix the mess later one. Change-Id: I550cd001bdefb8be0fe67632f783c0ef6bee3f9f updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* libglusterfs: cleanup iovec functionsXavi Hernandez2019-06-111-64/+164
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch cleans some iovec code and creates two additional helper functions to simplify management of iovec structures. iov_range_copy(struct iovec *dst, uint32_t dst_count, uint32_t dst_offset, struct iovec *src, uint32_t src_count, uint32_t src_offset, uint32_t size); This function copies up to 'size' bytes from 'src' at offset 'src_offset' to 'dst' at 'dst_offset'. It returns the number of bytes copied. iov_skip(struct iovec *iovec, uint32_t count, uint32_t size); This function removes the initial 'size' bytes from 'iovec' and returns the updated number of iovec vectors remaining. The signature of iov_subset() has also been modified to make it safer and easier to use. The new signature is: iov_subset(struct iovec *src, int src_count, uint32_t start, uint32_t size, struct iovec **dst, int32_t dst_count); This function creates a new iovec array containing the subset of the 'src' vector starting at 'start' with size 'size'. The resulting array is allocated if '*dst' is NULL, or copied to '*dst' if it fits (based on 'dst_count'). It returns the number of iovec vectors used. A new set of functions to iterate through an iovec array have been created. They can be used to simplify the implementation of other iovec-based helper functions. Change-Id: Ia5fe57e388e23392a8d6cdab17670e337cadd587 Updates: bz#1193929 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* features/shard: Fix block-count accounting upon truncate to lower sizeKrutika Dhananjay2019-06-041-0/+2
| | | | | | | | | | | | | | | | | The way delta_blocks is computed in shard is incorrect, when a file is truncated to a lower size. The accounting only considers change in size of the last of the truncated shards. FIX: Get the block-count of each shard just before an unlink at posix in xdata. Their summation plus the change in size of last shard (from an actual truncate) is used to compute delta_blocks which is used in the xattrop for size update. Change-Id: I9128a192e9bf8c3c3a959e96b7400879d03d7c53 fixes: bz#1705884 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
* glusterd: Optimize code to copy dictionary in handshake code pathMohit Agrawal2019-05-311-0/+6
| | | | | | | | | | | | | Problem: While high no. of volumes are configured around 2000 glusterd has bottleneck during handshake at the time of copying dictionary Solution: To avoid the bottleneck serialize a dictionary instead of copying key-value pair one by one Change-Id: I9fb332f432e4f915bc3af8dcab38bed26bda2b9a fixes: bz#1711297 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* ec/fini: Fix race with ec_fini and ec_notifyMohammed Rafi KC2019-05-211-0/+3
| | | | | | | | | | | | | | | During a graph cleanup, we first sent a PARENT_DOWN and wait for a child down to ultimately free the xlator and the graph. In the ec xlator, we cleanup the threads when we get a PARENT_DOWN event. But a racing event like CHILD_UP or event xl_op may trigger healing threads after threads cleanup. So there is a chance that the threads might access a freed private variabe Change-Id: I252d10181bb67b95900c903d479de707a8489532 fixes: bz#1703948 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* glusterd/store: store all key-values in one shotYaniv Kaul2019-05-081-0/+3
| | | | | | | | | | | | Instead of saving each key-value separately, which is slow ( especially as we fflush() after each!), store them all as one string and write all together. Implements https://github.com/gluster/glusterfs/issues/629 Change-Id: Ie77a272446b0b6785584b710a4fdd9c613dd9578 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat,.com>
* tests: validate volfile grammar - strings in volfileAmar Tumballi2019-05-061-4/+0
| | | | | | | | * libglusterfs/graph-print: remove unused code updates: bz#1693692 Change-Id: Iae81bb6a3af5911c3da07ab8f1d8f58f27e06905 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* options.c,h: minor changes to GF_OPTION_RECONFYaniv Kaul2019-04-301-28/+16
| | | | | | | | | | | Minor code changes (less variables and if statements) and use dict_get_strn(), since all options are fixed strings. Similar changes could be done to GF_OPTION_INIT() as well. Change-Id: I4a523f67183f4c4852a3d4de5e3cac52df68d3cf updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* libglusterfs: remove compound-fop helper functionsAmar Tumballi2019-04-291-36/+0
| | | | | | updates: bz#1693692 Change-Id: If69702990af273be1f38855ba56b3b89fabff167 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* cloudsync/cvlt: Cloudsync plugin for commvault storeAnuradha Talur2019-04-261-0/+1
| | | | | | Change-Id: Icbe53e78e9c4f6699c7a26a806ef4b14b39f5019 updates: bz#1642168 Signed-off-by: Anuradha Talur <atalur@commvault.com>
* logging.c/h: aggressively remove sprintfs()Yaniv Kaul2019-04-251-6/+6
| | | | | | | | | | | | | | | | | | | | | | Try to reduce the number of sprintf() and string copies until we finally log a log line. Specifically, do not sprintf separately the timestr string and do not sprintf/strcpy the appmsgstr separately - just stick it with the header. Hoping I did not leak anything or changed the log line formatting. Also, allocate 4K (GF_LOG_BACKTRACE_SIZE) of memory dynamically for trace output - only if trace was actually requested (previously, it was unconditionally) In addition, some minor code formatting (unrelated to the above). updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com> Change-Id: Id2ccc85f9213a2b1c6eaa4a2f58ce043eac1824f
* core: avoid dynamic TLS allocation when possibleXavi Hernandez2019-04-242-7/+6
| | | | | | | | | | | | | | | | | | | Some interdependencies between logging and memory management functions make it impossible to use the logging framework before initializing memory subsystem because they both depend on Thread Local Storage allocated through pthread_key_create() during initialization. This causes a crash when we try to log something very early in the initialization phase. To prevent this, several dynamically allocated TLS structures have been replaced by static TLS reserved at compile time using '__thread' keyword. This also reduces the number of error sources, making initialization simpler. Updates: bz#1193929 Change-Id: I8ea2e072411e30790d50084b6b7e909c7bb01d50 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* core: handle memory accounting correctlyXavi Hernandez2019-04-221-0/+2
| | | | | | | | | | | | | | | | | | | | When a translator stops, memory accounting for that translator is not destroyed (because there could remain memory allocated that references it), but mutexes that coordinate updates of memory accounting were destroyed. This caused incorrect memory accounting and even crashes in debug mode. This patch also fixes some other things: * Reduce the number of atomic operations needed to manage memory accounting. * Correctly account memory when realloc() is used. * Merge two critical sections into one. * Cleaned the code a bit. Change-Id: Id5eaee7338729b9bc52c931815ca3ff1e5a7dcc8 Updates: bz#1659334 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* core: Log level changes do not effect on running client processMohit Agrawal2019-04-151-0/+1
| | | | | | | | | | | | | | | | | | | Problem: commit c34e4161f3cb6539ec83a9020f3d27eb4759a975 set log-level per xlator during reconfigure only for a brick process not for the client process. Solution: 1) Change per xlator log-level only if brick_mux is enabled.To make sure about brick multiplex introudce a flag brick_mux at ctx->cmd_args. Note: There are two other changes done with this patch 1) Ignore client-log-level option to attach a brick with already running brick if brick_mux is enabled 2) Add a log to print pid of the running process to make easier debugging Change-Id: I39e85de778e150d0685cd9a79425ce8b4783f9c9 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com> Fixes: bz#1696046
* graph.c: remove extra gettimeofday() - reuse the graph dob.Yaniv Kaul2019-04-151-2/+2
| | | | | | | | | | | | | It was written just before fill_void() call. Note that there was a possible overflow if the hostname was too long (unrelated to this patch), but it is now also fixed, as we use a smaller buffer for the hostname. This, in turn, forces us to check if gethostname() failed and add explicitly the terminating null to it. Change-Id: I45fbc0a8e105f1247f3cbf61befac06fabbaea06 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* Replace memdup() with gf_memdup()Vijay Bellur2019-04-122-14/+1
| | | | | | | | | memdup() and gf_memdup() have the same implementation. Removed one API as the presence of both can be confusing. Change-Id: I562130c668457e13e4288e592792872d2e49887e updates: bz#1193929 Signed-off-by: Vijay Bellur <vbellur@redhat.com>
* libglusterfs: define macros needed for cloudsyncAnuradha Talur2019-04-041-0/+4
| | | | | | Change-Id: Iec5ce7f17fbf899f881a58cd20c4c967e3b71668 fixes: bz#1642168 Signed-off-by: Anuradha Talur <atalur@commvault.com>
* logging: Fix GF_LOG_OCCASSIONALLY APIAtin Mukherjee2019-04-021-1/+1
| | | | | | | | | | | GF_LOG_OCCASSIONALLY doesn't log on the first instance rather at every 42nd iterations which isn't effective as in some cases we might not have the code flow hitting the same log for as many as 42 times and we'd end up suppressing the log. Fixes: bz#1694925 Change-Id: Iee293281d25a652b64df111d59b13de4efce06fa Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* mgmt/shd: Implement multiplexing in self heal daemonMohammed Rafi KC2019-04-013-1/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Shd daemon is per node, which means they create a graph with all volumes on it. While this is a great for utilizing resources, it is so good in terms of performance and managebility. Because self-heal daemons doesn't have capability to automatically reconfigure their graphs. So each time when any configurations changes happens to the volumes(replicate/disperse), we need to restart shd to bring the changes into the graph. Because of this all on going heal for all other volumes has to be stopped in the middle, and need to restart all over again. Solution: This changes makes shd as a per volume daemon, so that the graph will be generated for each volumes. When we want to start/reconfigure shd for a volume, we first search for an existing shd running on the node, if there is none, we will start a new process. If already a daemon is running for shd, then we will simply detach a graph for a volume and reatach the updated graph for the volume. This won't touch any of the on going operations for any other volumes on the shd daemon. Example of an shd graph when it is per volume graph ----------------------- | debug-iostat | ----------------------- / | \ / | \ --------- --------- ---------- | AFR-1 | | AFR-2 | | AFR-3 | -------- --------- ---------- A running shd daemon with 3 volumes will be like--> graph ----------------------- | debug-iostat | ----------------------- / | \ / | \ ------------ ------------ ------------ | volume-1 | | volume-2 | | volume-3 | ------------ ------------ ------------ Change-Id: Idcb2698be3eeb95beaac47125565c93370afbd99 fixes: bz#1659708 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* mem-pool: remove dead code.Yaniv Kaul2019-03-261-11/+0
| | | | | | Change-Id: I3bbda719027b45e1289db2e6a718627141bcbdc8 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* glusterd: change the op-versionSanju Rakonde2019-03-111-0/+2
| | | | | | | | | | as commit 073444 is backported to release-5.4 branch, op-version for this change should 5.4 instead of 6. fixes: bz#1685120 Change-Id: Id504b9a1446125cea7c6a32117ccc44f28e73aa7 Signed-off-by: Sanju Rakonde <srakonde@redhat.com>
* core: make compute_cksum function op_version compatibleSanju Rakonde2019-03-071-2/+2
| | | | | | | | | | | | | | | Problem: commit 5a152a changed the mechansim of computing the checksum. In heterogeneous cluster, peers are running into rejected state because we have different cksum computation mechansims in upgraded and non-upgraded nodes. Solution: add a check for op-version so that all the nodes in the cluster follow the same mechanism for computing the cksum. Change-Id: I1508f000e8c9895588b6011b8b6cc0eda7102193 fixes: bz#1685120 Signed-off-by: Sanju Rakonde <srakonde@redhat.com>
* core: implement a global thread poolXavi Hernandez2019-02-184-2/+213
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements a thread pool that is wait-free for adding jobs to the queue and uses a very small locked region to get jobs. This makes it possible to decrease contention drastically. It's based on wfcqueue structure provided by urcu library. It automatically enables more threads when load demands it, and stops them when not needed. There's a maximum number of threads that can be used. This value can be configured. Depending on the workload, the maximum number of threads plays an important role. So it needs to be configured for optimal performance. Currently the thread pool doesn't self adjust the maximum for the workload, so this configuration needs to be changed manually. For this reason, the global thread pool has been made optional, so that volumes can still use the thread pool provided by io-threads. To enable it for bricks, the following option needs to be set: config.global-threading = on This option has no effect if bricks are already running. A restart is required to activate it. It's recommended to also enable the following option when running bricks with the global thread pool: performance.iot-pass-through = on To enable it for a FUSE mount point, the option '--global-threading' must be added to the mount command. To change it, an umount and remount is needed. It's recommended to disable the following option when using global threading on a mount point: performance.client-io-threads = off To enable it for services managed by glusterd, glusterd needs to be started with option '--global-threading'. In this case all daemons, like self-heal, will be using the global thread pool. Currently it can only be enabled for bricks, FUSE mounts and glusterd services. The maximum number of threads for clients and bricks can be configured using the following options: config.client-threads config.brick-threads These options can be applied online and its effect is immediate most of the times. If one of them is set to 0, the maximum number of threads will be calcutated as #cores * 2. Some distributions use a very old userspace-rcu library (version 0.7) for this reason, some header files from version 0.10 have been copied into contrib/userspace-rcu and are used if the detected version is 0.7 or older. An additional change has been made to io-threads to prevent that threads are started when iot-pass-through is set. Change-Id: I09d19e246b9e6d53c6247b29dfca6af6ee00a24b updates: #532 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* socket: socket event handlers now return voidMilind Changire2019-02-181-3/+3
| | | | | | | | | | | | | | Problem: Returning any value from socket event handlers to the event sub-system doesn't make sense since event sub-system cannot handle socket sub-system errors. Solution: Change return type of all socket event handlers to 'void' Change-Id: I70dc2c57f12b7ea2fae41120f71aa0d7fe0b2b6f Fixes: bz#1651246 Signed-off-by: Milind Changire <mchangir@redhat.com>
* inode: make critical section smallerAmar Tumballi2019-02-131-3/+0
| | | | | | | | | | | | | | | | do all the 'static' tasks outside of locked region. * hash_dentry() and hash_gfid() are now called outside locked region. * remove extra __dentry_hash exported in libglusterfs.sym * avoid checks in locked functions, if the check is done in calling function. * implement dentry_destroy(), which handles freeing of dentry separately, from that of dentry_unset (which takes care of separating dentry from inode, and table) Updates: bz#1670031 Change-Id: I584213e0748464bb427fbdef3c4ab6615d7d5eb0 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* fuse: correctly handle setxattr valuesXavi Hernandez2019-02-071-1/+1
| | | | | | | | | | The setxattr function receives a pointer to raw data, which may not be null-terminated. When this data needs to be interpreted as a string, an explicit null termination needs to be added before using the value. Change-Id: Id110f9b215b22786da5782adec9449ce38d0d563 updates: bz#1193929 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* glusterd: Update op-version for release 7ShyamsundarR2019-02-051-1/+3
| | | | | | Change-Id: I0f3978d7e603e6e767dc7aa2a23ef35b1f2b43f7 Updates: bz#1193929 Signed-off-by: ShyamsundarR <srangana@redhat.com>
* mount/fuse: expose auto-invalidation as a mount optionRaghavendra Gowdappa2019-02-021-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Auto invalidation is necessary when same (meta)data is shared/access across multiple mounts. However, if (meta)data is not shared, all relevant I/O goes through the cache of single mount and hence is coherent with (meta)data on bricks always. So, fuse-auto-invalidation can be disabled for this case which gives a huge performance boost for workloads that write data and then immediately read the data they just wrote. From glusterfs --help, <snip> --auto-invalidation[=BOOL] controls whether fuse-kernel can auto-invalidate attribute, dentry and page-cache. Disable this only if same files/directories are not accessed across two different mounts concurrently [default: "on"] </snip> Details on how disabling auto-invalidation helped to reduce pgbench init times can be found at [1]. Time taken for pgbench init of scale 8000 was 8340s. That will be an improvement of 86% (59280s vs 8340s) with auto-invalidations turned off along with other optimizations. Just disabling auto-invalidation contributed 56% improvement by reducing the total time taken by 33260s. [1] https://www.spinics.net/lists/gluster-devel/msg25907.html Change-Id: I0ed730dba9064bd9c576ad1800170a21e100e1ce Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com> updates: bz#1664934
generated by cgit (git 2.34.1) at 2025-06-17 22:44:35 +0000