summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* add xlator debug/io-statsCsaba Henk2009-05-205-1/+1536
| | | | Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* add 'non-blocking-io' to the options array in sockets.Amar Tumballi2009-05-201-0/+3
| | | | Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* io-threads: Use boolean enums instead of integer 1Shehjar Tikoo2009-05-201-2/+2
| | | | Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* io-threads: Change mutexes/condvars to spinlocks/semaphoresShehjar Tikoo2009-05-202-36/+80
| | | | | | | | | | | | | | | | | It seems that use of mutexes is resulting in pretty high thread sleep and wake-up cost. What is worse, if a worker thread has acquired a lock, there is a possibility of the main glusterfs thread being put to sleep. We change the use of mutexes into spinlock. At the same time, we cannot anymore use condvars for notification since the condvar interface depends on mutexes itself. Semaphores come to out rescue. Luckily, even the pthread semaphores have a timedwait interface to allow our idle worker threads to make an exit decision. Further, it is possible that spinlocks are not available on all systems so all this is curtained behind #defines so we can fall back to mutexes and condvars implementation. Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* io-threads: Reduce default max for threads to 64Shehjar Tikoo2009-05-201-1/+1
| | | | | | | | | We've had complaints from users who've used autoscaling option with default settings for min and max threads, about high memory consumption because of the large default value for max-threads. Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* io-threads: Support mem-pool allocator for iot_request_tShehjar Tikoo2009-05-202-23/+44
| | | | | | | | | | | | | | | | This commit brings in support for allocation of iot_request_t's in io-threads through the use of the mem-pool. We're hoping that the overheads of hundreds and thousands of small allocations can be avoided through this. The important point to note is that the memory pool is not for the translator as a whole but there is one small memory pool for each worker thread. Not only does that help us avoid malloc overheads for small allocations like iot_request_t but also avoid contention on the heap data structures when multiple threads want an iot_request_t from the pool. Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* io-threads: Add graceful shutdown of worker threadsRaghavendra G2009-05-202-25/+79
| | | | Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* io-threads: handle memory allocation failuresRaghavendra G2009-05-201-197/+760
| | | | Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
* Change errno to EAGAIN in readv/writevVikas Gorur2009-05-191-6/+7
| | | | | | | | When mandatory locks are enabled and a read/write would block due to a lock and if the fd is opened with O_NONBLOCK, return EAGAIN (previously EWOULDBLOCK). Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* mem-pool: Restructure mem-pool behaviourShehjar Tikoo2009-05-192-31/+55
| | | | | | | | | | | | | | | | | | This commit changes mem-pool behaviour to return a directly usable address by performing the required adjustment on the address being returned. This is different from the previous behaviour where we're trying to fit into the requested size, the list_head*2 also. This is not efficient enough in terms of space but hopefully works better than not having any mem-pool at all. Besides, I am not comfortable with mem-pool meta-data and caller-useable memory area being the same because of the potential for mem-pool's data structure corruption. PS: Please do read the comments in the code for more info during review. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* mem-pool: Fix #define spellingShehjar Tikoo2009-05-191-3/+3
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* mem-pool: Remove hard coded value for pad boundaryShehjar Tikoo2009-05-191-1/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* mem-pool: Fix memory leak in mem-pool init phaseShehjar Tikoo2009-05-191-1/+3
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Fall back to remaining real_* functorsShehjar Tikoo2009-05-191-13/+36
| | | | | | | | | It is possible that some of the real_* functors for stat family of syscalls are NULL. I've seen this on libc. In that case, this commit attempts to use any available function that performs an equivalent operation. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Dont de-init fd tables on VMP-init failureShehjar Tikoo2009-05-191-17/+5
| | | | | | | | In case the init procedure for VMP fails, we want to continue using booster through the old approach, which means leaving the fd-table intact. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Do not read info for non-glusterfs mount pointsShehjar Tikoo2009-05-191-0/+3
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Appropriate changes to statvfs struct for Solaris host.Harshavardhana Ranganath2009-05-191-0/+13
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Comply with EEXIST rule on renameShehjar Tikoo2009-05-181-8/+0
| | | | | | | | During a rename, if the new file exists, the old name needs to over-write the new name. We're returning EEXIST, which is wrong behaviour. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: __do_path_resolve: Fix pathname resolution bugShehjar Tikoo2009-05-181-1/+1
| | | | | | | | | | | In __do_path_resolve, we need to use the new_loc.path as the input for resolution rather than the resolved variable, simply because we're not interested in resolving the names that have been resolved, as pointed out by the variable name 'resolved'. Instead, we need to resolve new_loc, which stores the next component in the path to be looked up. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Wipe loc->ino in libgf_client_loc_wipeShehjar Tikoo2009-05-181-0/+1
| | | | | | | | | | | | | | | | Not cleaning up the ino member of a loc_t results in SIGABRT in __inode_link because in some cases, the loc->ino is different from loc->inode->ino. This happens especially in code blocks which re-use a loc_t structure for pointing at different inodes/files. For eg, if a loc_t has been assigned an inode and an ino, and followed by a libgf_client_loc_wipe, then re-use of this loc in say libgf_client_lookup results the SIGABRT because libgf_client_lookup calls inode_link with the same loc_t. However, this loc_t has just been assigned a new inode pointer but the ino member still contains a previous inode's inode number. This difference in inode numbers results in an assertion failure, so the SIGABRT. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Add telldir APIShehjar Tikoo2009-05-182-0/+38
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Add seekdir APIShehjar Tikoo2009-05-182-0/+36
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Add rewinddir APIShehjar Tikoo2009-05-182-0/+37
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Refine readdir entry parsing logicShehjar Tikoo2009-05-181-25/+19
| | | | | | | | Here I am only refining the entry parsing code in order to clarify the exit conditions from the loop. There were a few workloads where this loop went infinite. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Add telldir APIShehjar Tikoo2009-05-182-0/+35
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Add seekdir APIShehjar Tikoo2009-05-182-0/+32
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Add rewinddir APIShehjar Tikoo2009-05-182-1/+33
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient: Revert and re-do readdir conformanceShehjar Tikoo2009-05-182-61/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This commit basically reverts the previous readdir conformance patch I sent a few days back. That commit had a completely retarded and broken way of maintaining per-directory dirent. It was broken for two reasons: 1. Creating a wrapper structure around the directory's fd_t only for storing a struct dirent is not clean enough. This commit takes a better approach by storing the dirent in fd_t context. This dirent is valid only if the fd_t refers to a directory. 2. That commit was made and tested under the assumption (..stupidity is a better word..) that only opendir call is used for opening a directory. That is not correct. Directories are also opened using the open syscall. The point is, glusterfs_open returns an fd_t and so did glusterfs_opendir. The previous patch actually changed opendir to return a new wrapper structure. That is fine, if we go by the POSIX definition of open and opendir because, they're both supposed to return different types, an int and a DIR*. However, in libglusterfsclient, all other code assumes that directory handles corresponding to DIR* and file descriptors corresponding to int types are the same type, resulting in use of the same locking and fd context addition/extraction code. So a directory opened using opendir returned a wrapper structure which went down into the libglusterfsclient stack where some function called a lock on the handle assuming it was an fd_t, since it is not and dereferencing of the supposed fd->inode->lock results in a seg fault. Obviously, this didnt show up till unfs3 used open() to open a directory and not opendir. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Supplement fstab option parsingShehjar Tikoo2009-05-181-6/+14
| | | | | | | | Previous fstab option parsing logic was completely retarded and did not handle all cases. This fixes the situation so we now work without any problems. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* workaround for not including sys/cdefs.h -- including sys/cdefs.h breaks ↵Anand V. Avati2009-05-181-1/+16
| | | | build on solaris and other platforms
* Bug fix in pl_readv/writev to handle the mandatory lock case properly.Vikas Gorur2009-05-181-23/+21
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* client-protocol: Fix memory corruption in client_lookupRaghavendra G2009-05-161-13/+7
| | | | | | | | - memory corruption was due to new members being added between allocation of buffer for serializing xattr_req dictionary and dict_serialize of xattr_req. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* dict.c: make dict_serialized_length and dict_serialize to hold locks.Raghavendra G2009-05-161-120/+10
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* dict.c: Add dict_allocate_and_serializeRaghavendra G2009-05-162-0/+230
| | | | | | | | | - this procedure atomically allocates a buffer and serializes dict into it. - this procedure helps avoid memory corruptions due to race conditions where in new members are added into dict between allocating a buffer for serializing and actually serializing buffer into it. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* make getxattr fail with ERANGE if reply is bigger than what was requestedCsaba Henk2009-05-161-31/+25
| | | | | | Edited by avati: make the function signature of fuse_xattr_reply_buf() use 'const char *value' instead of 'char *value' Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* apache/2.2/mod_glusterfs: port to use new glusterfs_readdir interface.Raghavendra G2009-05-161-5/+5
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* avoid duplicate mounts while using mount.glusterfsAmar Tumballi2009-05-161-1/+1
| | | | | | | This change is needed as the format of how the /etc/mtab entry of glusterfs mount looks is now changed. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* modified init scripts to honour @prefix@Harshavardhana2009-05-164-3/+12
| | | | | | fixes http://savannah.nongnu.org/bugs/?26581 Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Edited log message for --volfile-checkVikas Gorur2009-05-161-1/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* minor log enhancement in 'ib-verbs' transport.Amar Tumballi2009-05-161-0/+5
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* replace BIG_FUSE_CHANNEL_SIZE with 'this->ctx->page_size'Amar Tumballi2009-05-161-9/+9
| | | | | | | Send the struct stat's 'blksize' variable same as GlusterFS's page-size, instead of BIG_FUSE_CHANNEL_SIZE. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* default log file different per mount (or if server, per volumefile)Amar Tumballi2009-05-161-8/+54
| | | | | | | | This feature is required becuase when more than one glusterfs process is started with default log file, all logs will be going to same file, which after a while gets more confusing. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* posix: Fix build warning on incorrect typeShehjar Tikoo2009-05-161-1/+1
| | | | | | | | | This fixes a build warning due to use of incorrect type for size_t, for Core 2 Duo. Extra fix from avati: change %ld to GF_PRI_SIZET Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* stripe init 'block-size' pattern parsing bug fixed.2.0.1Amar Tumballi2009-05-081-59/+78
| | | | | | ref: http://savannah.nongnu.org/bugs/?26416 Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* scheduler-nufa: fix initialization of refresh-intervalRaghavendra G2009-05-081-8/+10
| | | | | | | | - refresh-interval was being reported as not provided in the options even when configured. - fixes bug reported in rt #1007 Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Set op_errno properly in afr_flush.Vikas Gorur2009-05-081-0/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Add fstab parsing supportShehjar Tikoo2009-05-084-59/+467
| | | | | | | | | | | | | This commit changes the booster.conf format from a simple custom format to that of the /etc/fstab.c See booster_mount(..) for the mount options supported/required for LD_PRELOADing booster. I'll write a small help doc soon. This commit also brings in fstab parsing code into libglusterfs because Darwin libc only supports reading the hardcoded /etc/fstab. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* booster: Standardize conf file and env variableShehjar Tikoo2009-05-081-2/+2
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* backend-xattr-sanitize.sh: script added to extras/Anand V. Avati2009-05-072-1/+67
| | | | | | | | Run the script as: sh$ ./backend-xattr-sanitize.sh /data/export0 and it will remove all the known stale xattrs on the backend files and dirs
* valid_host_name(): accept string lengths upto 75 chars (the limit accepted ↵Anand V. Avati2009-05-071-1/+1
| | | | by glibc resolver)