summaryrefslogtreecommitdiffstats
path: root/libglusterfs
Commit message (Collapse)AuthorAgeFilesLines
* booster: Move fstab parsing into booster from libglusterfstag-release-2.0Shehjar Tikoo2009-05-203-393/+2
| | | | | | | | | | | This is another attempt at fixing build problems on Solaris. I am told that booster build is disabled on Solaris and I know that it is disabled on Mac OS X also. Getting it to work on both these systems is now on my TODO list, mainly because on both these systems, we can have a glusterfs client running without requiring FUSE. Signed-off-by: Anand V. Avati <avati@dev.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>
* 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>
* booster: Add fstab parsing supportShehjar Tikoo2009-05-083-2/+393
| | | | | | | | | | | | | 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>
* valid_host_name(): accept string lengths upto 75 chars (the limit accepted ↵Anand V. Avati2009-05-071-1/+1
| | | | by glibc resolver)
* transport shortcut b/w client and serverAnand V. Avati2009-05-072-2/+118
| | | | | | This patch makes the server pass back the transport pointer of the client. If the UUID matches, the client makes the local transport 'shortcut' with the remote transport (pointer received from server) The shortcut simulates a socket queue. Instead of serialized messages going over the network and getting queued in the tcp socket queue, the messages get queued in a transport specific queue picked by a polling thread.
* libglusterfs log cleanupAnand V. Avati2009-04-282-10/+6
|
* log message supressing in DNS resolutionAnand V. Avati2009-04-241-4/+4
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Cleaned up log messages in xlator.cVikas Gorur2009-04-241-20/+20
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Cleaned up log messages in spec.yVikas Gorur2009-04-241-31/+28
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Cleaned up log messages in inode.cVikas Gorur2009-04-241-41/+4
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Changed logging format to remove line number & function name from NORMAL and ↵Vikas Gorur2009-04-241-4/+10
| | | | | | higher levels. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Introduce new log level GF_LOG_TRACE.Vikas Gorur2009-04-242-4/+5
| | | | | | | TRACE is the most verbose log level, meant to have a full trace of operation. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Remove log level TRACE and the macro GF_TRACE.Vikas Gorur2009-04-242-8/+0
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* iobuf: Define MAP_ANONYMOUSShehjar Tikoo2009-04-241-0/+11
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* iobuf_pool->arenas_cnt should be incremented in iobuf_arena_alloc, and not ↵Anand V. Avati2009-04-221-1/+2
| | | | | | iobuf_pool_add_arena (to avoid counting of unpruned arenas) Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* call-stub: Check for NULL in the correct variableShehjar Tikoo2009-04-221-1/+1
| | | | | | | | It looks like the argument fd was meant to be checked here instead of the fd in the call stub. This fixes a NULL fd bug that results in an EINVAL on opendir. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* inode.c - NULL check for the extra __inode_search performed, when presented ↵Anand V. Avati2009-04-201-0/+6
| | | | | | inode is not hashed. This bug fixes #967
* pruning buffer margin - do not destroy if no other non-filled arenas are in ↵Anand V. Avati2009-04-182-3/+26
| | | | the pool
* added 2 APIs iobuf_size and iobref_size to return the system memory usage by ↵Anand V. Avati2009-04-172-0/+46
| | | | an iobuf, and by all iobufs in an iobref respectively
* libglusterfsclient: Use macros for argument checksShehjar Tikoo2009-04-171-0/+10
| | | | | | | | | | Having those if {} blocks to check for argument validity hurts the eye so this patch replaces those checks with macros. One macro already exists in libglusterfs. The second macro is introduced by this commit for libglusterfsclient-specific check for paths. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* add NULL check in iobuf_arena_destroyAnand V. Avati2009-04-161-0/+3
|
* use MAP_FAILED macro to free mem_base in arena_destroyAnand V. Avati2009-04-141-1/+2
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* FREE arena->iobufs in iobuf_arena_destoryAnand V. Avati2009-04-141-0/+2
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* introduce page_size in glusterfs_ctx_t to be used by all translators set it ↵Anand V. Avati2009-04-131-0/+1
| | | | | | to 128KB in main() Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* bug fix in iobuf_select_arena - call __iobuf_pool_add_arena (unlocked version)Anand V. Avati2009-04-131-1/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* bug fix - arena destruction now calls munmap and not FREEAnand V. Avati2009-04-131-1/+5
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* add purge list support to make iobuf_pool_purge() in expensive, and actually ↵Anand V. Avati2009-04-132-1/+10
| | | | | | call it in iobuf_put :-) Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* bug fix in iobuf_select_arena - never created a new arenaAnand V. Avati2009-04-131-2/+5
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* add @filled list in iobuf_pool to keep away filled list from getting ↵Anand V. Avati2009-04-132-1/+20
| | | | | | searched in iobuf_select_arena Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* use MAP_FAILED macro to check for mmap failure instead of (void *) -1Anand V. Avati2009-04-131-1/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* fixed sizeof parameter in CALLOC of a new arenaAnand V. Avati2009-04-131-1/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* updated transport interface functions to accommodate IOBUF/IOBREFAnand V. Avati2009-04-122-8/+11
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* do away with frame->root->{req,rsp}_refs membersAnand V. Avati2009-04-121-2/+0
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* update prototype of writev and readv_cbk to use IOBREF in parameter (step ↵Anand V. Avati2009-04-125-27/+39
| | | | | | towards elmination of frame->root->{req,rsp}_refs Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* IOBREF support for holding iobuf refs along with fops (replacement for ↵Anand V. Avati2009-04-122-0/+152
| | | | | | frame->root->{req,rsp}_refs Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* IOBUF support (to be used by transports and fuse)Anand V. Avati2009-04-124-2/+494
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Add lock-less versions of fd_ctx_*Vikas Gorur2009-04-072-52/+104
| | | | | | | | Added __fd_ctx_get __fd_ctx_set __fd_ctx_del which do not hold any lock. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* libglusterfsclient code changesRaghavendra G2009-04-032-0/+21
| | | | | | | | | | | | - add dentry support to libglusterfsclient. - changes related to using array, to store context in inode instead of dictionary. - code changes related to cleanup of libglusterfsclient interface. - added glusterfs_mkdir and glusterfs_rmdir - other changes in libglusterfsclient to make it work with code changes in other parts of glusterfs. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* server-protocol - reimplement connection cleanup to happen in 2 phasesRaghavendra G2009-04-032-10/+55
| | | | | | | | | | | - first phase, which happens when POLLERR is received on transport, releases all locks, flushes all open fds. - second phase, which happens when both the transports of connection destroyed, destroys the containers like lock table, fd table along with the connection. - the first phase, clears up any references to transport held by translators like posix-locks(in the form of blocked locks) paving way for the second phase. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* change char to int in execute_cmd (based on comment on #26006 from Giorgio ↵Anand V. Avati2009-04-021-1/+1
| | | | | | Marinelli <gio@reversiva.net> Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Changed few lines to ensure Optimization (lesser code).Bharat Shetty Barkur2009-04-021-3/+1
| | | | | | Changed few lines to ensure lesser code optimization while checking the EOF for the file pointed to by specfp. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* use (fgetc() != EOF) instaed of feof() in parserAnand V. Avati2009-04-011-2/+1
| | | | Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Enable glusterfs client to exit after a configured number of failed connects ↵Raghavendra G2009-04-011-0/+1
| | | | | | \ while fetching volume specification file from server Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Avoid infinite loop while parsing volume specification files on Linux/ARM.Raghavendra G2009-04-011-2/+4
| | | | | | - patch submitted by anonymous user (ref: bug #26006 on savannah). Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
* Add new type of option type INTERNET_ADDRESS for validationRaghavendra G2009-04-012-0/+126
| | | | | | | | - used to validate options like remote-host, bind-address. - Also validate options of translators created during fetch of volume specification file from remote server. Signed-off-by: Anand V. Avati <avati@amp.gluster.com>
generated by cgit (git 2.34.1) at 2024-05-06 04:41:07 +0000