commit 01b9e590559ea810fb271e91127b3de7fc26816a
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue May 26 05:02:27 2009 +0000

    Do itransform in AFR readdir.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit c1c18df3936b01ec4ea8b48b936c4087648f4b3b
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue May 26 05:01:35 2009 +0000

    Always do itransform of the inode number from the first up child.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 9a2e319114d70d076b2f219a56397e5793dc3bdf
Author: Anand Avati <avati@gluster.com>
Date:   Tue May 26 04:31:28 2009 +0000

    add booster_fstab.h in noinst_HEADERS to fix build breakage after 'make dist'
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit f6bcb43d4adca26337f9a933e61eac8d6815cc7e
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 26 03:40:27 2009 +0000

    ib-verbs: Set receive and send window size
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 78ed845bc98ced0b2edd14875f5a7ef755802984
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 26 03:40:16 2009 +0000

    socket: Set receive and send window size
    
    This is experimental. We're hoping this improve performance on
    high speed links like 10GigE.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 71406e395f5cd4da495060d5604fe7db2d4018d1
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon May 25 05:02:25 2009 +0000

    Preserve atime/mtime during data self heal.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit eee87a35383a7b2aebea0c12c418404b93a342ec
Author: Anand Avati <avati@gluster.com>
Date:   Fri May 22 03:33:41 2009 +0000

    fix crash in __socket_reset. Previously iobuf_p was an allocated pointer, but since introduction of IObuf it is no more. Now iobuf has to be unref'ed instead.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 4d4cfc6e45a34e53f236cd2dccf66407ddc57796
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Wed May 20 22:50:10 2009 +0000

    booster: Move fstab parsing into booster from libglusterfs
    
    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>

commit 7f001813bc04ede65b05d588f16e0a6c68a94cfe
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon May 18 08:19:10 2009 +0000

    Change errno to EAGAIN in readv/writev
    
    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>

commit a9d0be4f1b78d9c03e9379fc5cea0ead6114c1d0
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 04:34:11 2009 +0000

    mem-pool: Restructure mem-pool behaviour
    
    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>

commit 25dc191c51efb97ec970b137edfe4557302b7357
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 04:33:58 2009 +0000

    mem-pool: Fix #define spelling
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3aea8a66a457349e19bde40eb33510edd0597cff
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 04:33:48 2009 +0000

    mem-pool: Remove hard coded value for pad boundary
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit acf28ed1ef3565ca1321fe9647d9b065a24fa46a
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 04:33:37 2009 +0000

    mem-pool: Fix memory leak in mem-pool init phase
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d71a5601fb2cf661d973a08a4cef9a15a9ec2363
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 17:57:02 2009 +0530

    booster: Fall back to remaining real_* functors
    
    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>

commit 87b938d02b51a0b4c864fc5deba1a1f177a05a4c
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 17:56:54 2009 +0530

    booster: Dont de-init fd tables on VMP-init failure
    
    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>

commit 9189418db9e50fa20c31ac5c7c5b6aaa16a9fa1e
Author: Shehjar Tikoo <shehjart@gluster.com>
Date:   Tue May 19 17:56:47 2009 +0530

    booster: Do not read info for non-glusterfs mount points
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c5b90f75951faddf55c61f2fe57f1c26070a63b6
Author: Harshavardhana Ranganath <harsha@dev.gluster.com>
Date:   Tue May 19 06:39:42 2009 -0700

    Appropriate changes to statvfs struct for Solaris host.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 35fc174ea3a37546d7c90be8fa6076b8f9416d73
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:24:43 2009 +0530

    libglusterfsclient: Comply with EEXIST rule on rename
    
    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>

commit 95ce0a87f5fbb139f7002360d63a005bfb9c097d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:24:34 2009 +0530

    libglusterfsclient: __do_path_resolve: Fix pathname resolution bug
    
    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>

commit fe06790a3637c30dc8d5e0be7367f27ee24c36bd
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:24:21 2009 +0530

    libglusterfsclient: Wipe loc->ino in libgf_client_loc_wipe
    
    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>

commit 1279d7398c63bdad448cf0418579f6df1d9f6f34
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:24:08 2009 +0530

    booster: Add telldir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e3e7f850eda010ab8c84417e57a4fbace4073022
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:23:58 2009 +0530

    booster: Add seekdir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 358f5ba40866545ce240ed8fda77c4d2e57a4262
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:23:38 2009 +0530

    booster: Add rewinddir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e420eb2206aa773eb32f1a7146cba4d6da5d9d03
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:23:24 2009 +0530

    libglusterfsclient: Refine readdir entry parsing logic
    
    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>

commit e1ae573f73d69fe1a244ed1493793961dd4cf811
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:23:14 2009 +0530

    libglusterfsclient: Add telldir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 35bf3f058473b61605fd28cd9cbee7726adedf9d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:22:57 2009 +0530

    libglusterfsclient: Add seekdir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit dddcf498610ebd332992e9600dd728cc87e6355d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:22:42 2009 +0530

    libglusterfsclient: Add rewinddir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit aeda0a31977e8da295b913e6a306ff01ccf0ce0a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:22:29 2009 +0530

    libglusterfsclient: Revert and re-do readdir conformance
    
    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>

commit 4f1a87a245b960f1cd1fb4fe40b4254ac3793213
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 18:22:19 2009 +0530

    booster: Supplement fstab option parsing
    
    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>

commit a5301c874f978570187c3543b0c3a4ceba143c25
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon May 18 17:24:16 2009 +0530

    workaround for not including sys/cdefs.h -- including sys/cdefs.h breaks build on solaris and other platforms

commit 0346e3e889d854f6f96d9f9b162a8d65ddb35f52
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon May 18 03:02:54 2009 -0700

    Bug fix in pl_readv/writev to handle the mandatory lock case properly.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 49523c834f075007352d07bf09463af9499b59f5
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Fri May 15 03:56:22 2009 -0700

    client-protocol: Fix memory corruption in client_lookup
    
    - 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>

commit 254f770af6ae6ff207fc567b6576a31469c84f67
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Fri May 15 03:55:50 2009 -0700

    dict.c: make dict_serialized_length and dict_serialize to hold locks.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9669c70c901474dc21ef08e49478b5f5dead8f64
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Fri May 15 03:55:20 2009 -0700

    dict.c: Add dict_allocate_and_serialize
    
    - 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>

commit dec2674685da30d6cef157748bcf52454ec97208
Author: Csaba Henk <csaba@gluster.com>
Date:   Sat May 16 04:28:40 2009 +0200

    make getxattr fail with ERANGE if reply is bigger than what was requested
    
    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>

commit b4651c4b8c7ebbcee7bfc7ef50afebf7e25d5744
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu May 14 00:21:02 2009 -0700

    apache/2.2/mod_glusterfs: port to use new glusterfs_readdir interface.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 43a568d732962c8e095d3072f672451bcbe95f47
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Wed May 13 12:46:29 2009 -0700

    avoid duplicate mounts while using mount.glusterfs
    
    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>

commit ce653eadc2d13e9f4d3748d217ef7614539a2f34
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri May 15 02:39:15 2009 -0700

    modified init scripts to honour @prefix@
    
    fixes http://savannah.nongnu.org/bugs/?26581
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 11cae446e0c115bbfa5ee3e6b18ef0e2c45b84fe
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu May 14 02:12:20 2009 -0700

    Edited log message for --volfile-check
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 19a1ce89421b7f066168059e972c906b8c194e54
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Wed May 13 01:26:24 2009 -0700

    minor log enhancement in 'ib-verbs' transport.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 92a84f8c0f0925f85ad40db1212ff5ef0c1fc809
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Mon May 11 13:19:49 2009 -0700

    replace BIG_FUSE_CHANNEL_SIZE with 'this->ctx->page_size'
    
    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>

commit 4f7552c23bc4d0691062bd6a90fa76aa53bdf97c
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Fri May 8 01:33:02 2009 -0700

    default log file different per mount (or if server, per volumefile)
    
    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>

commit f4fbc7200c32c50501df7a84b4ddeb4eeb0f5525
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon May 11 11:25:40 2009 +0530

    posix: Fix build warning on incorrect type
    
    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>

commit 5c1d9108c1529a1155963cb1911f8870a674ab5b
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Thu May 7 17:21:21 2009 -0700

    stripe init 'block-size' pattern parsing bug fixed.
    
    ref: http://savannah.nongnu.org/bugs/?26416
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 20e8fc7a61fd22af1657cffa674c287ad29a7699
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu May 7 04:16:28 2009 -0700

    scheduler-nufa: fix initialization of refresh-interval
    
    - 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>

commit 124f02ed49615e8337d249a2c56e95a5298a856b
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu May 7 05:05:03 2009 -0700

    Set op_errno properly in afr_flush.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b3f7efe247ad114b6071ba6a2d6816f783d4aa15
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri May 8 15:45:24 2009 +0530

    booster: Add fstab parsing support
    
    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>

commit 5f4c102297bae265a7c9a16a86ee032ffbd44830
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri May 8 15:45:09 2009 +0530

    booster: Standardize conf file and env variable
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit adb56cb5e0f0d718764b25f1b37397be720f8750
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu May 7 15:02:09 2009 +0530

    backend-xattr-sanitize.sh: script added to extras/
    
    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

commit babc4dfb08504e41a35cf06e8c297a19c87ac397
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu May 7 13:28:21 2009 +0530

    valid_host_name(): accept string lengths upto 75 chars (the limit accepted by glibc resolver)

commit fd2e7d9ebb94ccf5faf5c9d9891978e09fce0b05
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed May 6 05:40:15 2009 -0700

    symlink-cache: fix return value of readlink
    
    - sc_readlink wrongly returned strlen (link) + 1 when link was present in
        cache.
      - this fixes rt #828. Since fuse_readlink_cbk does link[op_ret] = '\0', there
        was a memory corruption.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 542d9ed6c1758df85fc0e252952cfb80669f4a70
Author: Amar Tumballi <amar@gluster.com>
Date:   Wed May 6 08:59:21 2009 -0700

    fix in mount.glusterfs for proper direct io mode option.
    
    fixes the bug which causes GlusterFS not to have valid 'direct-io'
    option through mount command or /etc/fstab entries.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 92a84a43e057ce2448c235d3bf66a0b694338d65
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu May 7 11:59:23 2009 +0530

    protocol/client: indentation fixes

commit 2ff188571e94831b389f5677e06b94d11eb5fc62
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu May 7 11:06:34 2009 +0530

    protocol/client: removed conf->child

commit f9f5519b66a25651eb03de577f68d481abdd4c40
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu May 7 01:24:41 2009 +0530

    transport shortcut b/w client and server
    
    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.

commit 12eb832e255a1abb90434ab3e0d1e1632ae7ce03
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed May 6 14:40:45 2009 +0530

    fix log message from transport-timeout to frame-timeout

commit cba961e9f4ff3452f5e8e6152c632a258b737576
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed May 6 12:23:54 2009 +0530

    libglusterfsclient: Improve readdir conformance on re-entrancy
    
    readdir is supposed to be non-re-entrant only with respect to the
    given dir stream, not the whole process.
    
    What that means is the static struct dirent that we maintain in
    libglusterfsclient should be per-directory handle and not
    process-wide.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f82651ef4ff5a9e94fa9c0d1f9cf091345440b56
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed May 6 12:23:14 2009 +0530

    libglusterfsclient: Fix large directory reading bug
    
    As of now, we use 1024 bytes as the buffer for reading directory
    entries. If a directory as many files, then its possible that it does
    not fit into this buffer, thereby requiring more than one call to
    readdir. Now suppose the last bunch of directories fit more or less
    exactly int the 1024 byte buffer. If this happens, the offset
    extracted by the current logic(in libgf_client_readdir) never gets
    updated beyond the first entry in this last block, because the last
    block's first entry always remains same. This explanation is
    convoluted, I know, but I too found out the hard way.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8d1b62393b58ff3ac5b157e0adea15578c949bbf
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 20:45:48 2009 +0530

    booster: Use CONFDIR as booster.conf default location
    
    This commit changes the default location of the booster.conf
    file from /etc/booster.conf to a directory defined
    during the build process.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit faef6fded892c310a3debdce273a382286a4ec19
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 20:45:26 2009 +0530

    booster: Change booster conf env var name
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f6862d75d1ca50b12372d5f9c3e651d6f74c5900
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed May 6 11:43:33 2009 +0530

    afr self-heal: update file size of the returning stat buf with source file's size

commit 3f3dea5f23e2b49ac8ad14bf8dd34dfadf6a72f5
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue May 5 20:04:50 2009 +0530

    log level fixes in read-ahead

commit 9cb93f58be9d032bec12ca04275e84904bf22c0b
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue May 5 20:03:36 2009 +0530

    log level fix in storage/posix

commit f62628af61f5ef72c6af2b807c1bba71f291a366
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue May 5 19:19:30 2009 +0530

    io-cache logging level fixes

commit e9800f8915257f8e3fc94dea8257e20a5561dfd7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:57 2009 +0530

    libglusterfsclient: Add 0-byte size/count guards
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fe94d6e4992d7b7f2bcee73dfd2b0af76e1f2611
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:50 2009 +0530

    booster: Add lchown API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8a3495e7d4b2273746d9e38aefbae583131951ca
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:43 2009 +0530

    booster: Add remove API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bddbe5f7a4437fc4c295b7830fa2916011ab799a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:37 2009 +0530

    booster: Add getxattr,lgetxattr API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ad8e8fa72f287da034027bf26fc1fbfb1437d47e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:29 2009 +0530

    booster: Add readdir64 API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c803febb9b013e384bcccf37a2c68dc90deea444
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:23 2009 +0530

    booster: Add statvfs API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fe6a39da3cd7370e9a7d9f7908e06cbdce64ce6a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:15 2009 +0530

    booster: Add statfs API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4de7dc7151d307021177107fcf8dd636b306bb59
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:08 2009 +0530

    booster: Add lstat API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 13a58f94a781d91ab3d7854996df66c9802d972b
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:04:00 2009 +0530

    booster: Add fstat API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 938191c57f0ef3a657a764033f70df6595dc736c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:52 2009 +0530

    booster: Add stat API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cec18ef672700dea563a8c899170ece4730257e5
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:42 2009 +0530

    booster: Add closedir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit abeec15e1da0c40bee134253035af88739e09960
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:32 2009 +0530

    booster: Add readdir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 792cd732264d751895e8469e7c5f3cb172574180
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:24 2009 +0530

    booster: Add opendir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fc602c0c17064dfbd81d3d85141b55a40c45d8d9
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:16 2009 +0530

    booster: Add realpath API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e749da85ec67dfa62af5702d199b8f1bcc53d1d7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:09 2009 +0530

    booster: Add readlink API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1504e1d50c7efcf20fe55fc7db526bb1d364244a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:03:02 2009 +0530

    booster: Add symlink API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 48e30d6715574c34bc760798e1657b5900129c25
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:55 2009 +0530

    booster: Add unlink API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 62b29b0db6f7d417a3281c3937bd5af20e1bf201
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:48 2009 +0530

    booster: Add mkfifo API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7d87f8f5ce56278f56427196b5e2c5e4c0be02ad
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:38 2009 +0530

    booster: Add mknod API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4311e7f01dc244baa1a1b8fc50f74a823dbd38c4
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:31 2009 +0530

    booster: Add utime API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 48ee90ab87cf0c01fee0188728d70d67c6724b97
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:24 2009 +0530

    booster: Add utimes API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit acac22c87374310544b3a4bb301e9bfa3ea26001
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:17 2009 +0530

    booster: Add rename API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 11cdc6e5282d4c7d906da3e20b50df78ddba2efd
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:10 2009 +0530

    booster: Add link API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9b012b098915c8bdbdcb8a4c38fb353fa39e82d4
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:02:02 2009 +0530

    booster: Add ftruncate API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e4e97f2bdaf6d98c5a133491efdffebb64fae4d6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:54 2009 +0530

    booster: Add fsync API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e6f4a6879a6f9bb11e6774182b211b57f1a827fa
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:47 2009 +0530

    booster: Add fchown API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8fa2a984c315418b940c481ea7729c00ed0b033a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:40 2009 +0530

    booster: Add fchmod API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ad4f864c448a3bbcec67d3fb3c44e07993cd70e7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:32 2009 +0530

    booster: Add chown API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 13610ba31d3b5a60c4d03343438f696725558e65
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:24 2009 +0530

    booster: Add chmod API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 76aa5e491dc3577bf8471cb649fee7b3d0a3dc9d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:16 2009 +0530

    booster: Add rmdir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 93c3a887695fc4fa7a65d6556398cffcf22d099e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:09 2009 +0530

    booster: Add mkdir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 358d3e7f99ecdc48c044f11f9f6011805d061ec4
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:01:02 2009 +0530

    booster: Add log message
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 83ae751616ce18d3010664f13ac8b8ecf8dd313d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:56 2009 +0530

    booster: Clean-up pwrite64
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 00b1e268fb0d3696820bd2e849c42deebe80a3cd
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:49 2009 +0530

    booster: Clean-up pwrite
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6696009a6662cc77458246ffc3dccc22f8d6c185
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:41 2009 +0530

    booster: Clean-up lseek64
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 513a2d15c16a9b5c96ceb321bed08d34d659e12b
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:34 2009 +0530

    booster: Clean-up lseek
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 24b360d865dbf344f8369e656d282739f07c18e8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:27 2009 +0530

    booster: Clean-up write
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8cacf5455bc97e84f62605df60a6ae5f66b61a1c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:20 2009 +0530

    booster: Clean-up writev
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 0c86f9686f2c91ef8838972ad038ba0c587cd09d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:12 2009 +0530

    booster: Clean-up pread64
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2763f86eea23898501c5299f58edc37e2c1262e5
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 16:00:04 2009 +0530

    booster: Clean-up pread
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a35a80b79702d3a81a9d62fc200ae61c6ec67b74
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:55 2009 +0530

    booster: Clean-up readv
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 61201d40bc22f1299bc49202433664664ec23ce6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:47 2009 +0530

    booster: Clean up read
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f0bef18b788c8beadc4131c5a6534761857c7f46
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:40 2009 +0530

    booster: Support VMP-based creat
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d470dd599c8dbf609411e52e587ea5c171214b21
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:32 2009 +0530

    booster: Add VMP-based open support
    
    In brief, when an open is called the VMP-based open is called first.
    If that fails, the fallback is the Mount-Point Bypass(MBP) technique
    which uses entended attributes to determine if the given
    path is a gluster mount. If it is, it goes ahead to create a
    glusterfsclient handle. All subsequent calls to this real mount point
    get redirected to the glusterfsclient handle. The other fallback is
    the actual open syscall on the local file system itself. This happens
    when the absence of an extended attribute tells us that the path is
    not even a glusterfs mount point.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3364e5eb2d5f5110e86924112dfe3f10597c9c9f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:25 2009 +0530

    booster: Remove fcntl.h from include path
    
    We define the O_CREAT, etc. flags so that we can remove fcntl.h from the
    include path. fcntl.h has certain defines and other lines of
    code that redirect application's open and open64 calls to the
    syscalls defined by libc.
    
    For us, thats not a Good Thing (TM).
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 313713a254e193623807d019f4c0e17e637ed316
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:18 2009 +0530

    booster: Integrate VMP-based mounting
    
    This commit brings into booster the use of VMP based operations
    which will allow users of booster to specifiy a VMP and use it
    for transparently operating on a glusterfs client context.
    
    Since applications are oblivious to booster's presence, because it is
    LD_PRELOAD'ed, we need to specify the VMPs and the corresponding
    options like volfile, logfile, loglevel, through a conf file.
    
    By default, this conf file is the /etc/booster.conf. This can be
    over-ridden through the GLFS_BOOSTER_CONF environment variable
    for the application.
    
    The format of the conf file is very simple for now. Each VMP is
    described on a single line with space separated fields.
    
    Format: <Virtual Mount Point> <volfile-path> <log-file> <log-level>
    
    <log-level> takes the string representation of the usual glusterfs
    log levels.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 42d5355a6221ea473372c891544e4cc7b265bbe9
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:11 2009 +0530

    libglusterfsclient: A Fix deadlock in ftruncate
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7eb61fb44986fc834a19d9f38754f1be54d07e09
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:59:03 2009 +0530

    libglusterfsclient: Conform'ify glusterfs_readdir
    
    This commit does two things:
    1. Changes glusterfs_readdir prototype to conform to the POSIX
    readdir().
    2. Uses a 1024-byte value instead of sizeof(struct dirent) for the
    @size for libgf_client_readdir. This allows even larger names to fit
    into a single readdir request to the server.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b48df70c58f52878d58f3e1a0adc870688cdfcdc
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:56 2009 +0530

    libglusterfsclient: Add VMP-based lchown
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit dec408299ea7a2cb9aa9aa3ea3a3c72ee79169de
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:48 2009 +0530

    libglusterfsclient: Add remove API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4353ba5cdf0dab29e30997ce5b67055c8f1e1cba
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:38 2009 +0530

    libglusterfsclient: Add lightweight path resolution
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e57175c0177ecc8b9ff80d3ce6c5f9a3f8248214
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:30 2009 +0530

    libglusterfsclient: Add lgetxattr API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d18d2550484f3d930557fed038a6bf9ffa23de48
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:23 2009 +0530

    libglusterfsclient: Add setxattr,lsetxattr API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 84d5566fab6daaffe3ad5da76d87a9c9e20e7170
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:16 2009 +0530

    libglusterfsclient: Make stat resolve all symlinks
    
    We want to resolve even nested symlinks when calling stat,
    therefore, we need to depend on realpath-like functionality
    and not just a readlink.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a0cd85c307f3576291829beb825323d43aeca7f8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:09 2009 +0530

    libglusterfsclient: Fix realpath operation
    
    This commit does two things:
    1. Ensures we go on to traverse nested symlinks by calling realpath
    recursively on the symlink.
    
    2. Makes glusterfs_realpath, a VMP-based operation, return a resolved
    /real path that actually has the VMP pre-fixed to the resolved path.
    If this is not done, we'll be returning a path that is valid only
    within the glusterfs context, i.e. the path will point to a real
    file/dir only if a glusterfs handle identifies which glusterfs context
    the file is in.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d1e74d7faa8670d6a7bf47ab9105af03d7dcf9a6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:58:03 2009 +0530

    libglusterfsclient: Dont lookup oldpath on symlink
    
    The target of the symlink does not have to be interpreted in
    any way. It should be sent across as it is.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5cfa7a3a5ee9199399137e217597b1b97f7a4e38
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:57:56 2009 +0530

    libglusterfsclient: Improve path matching heuristic
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b46296282155281768407c93f878ba3823118463
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:57:49 2009 +0530

    libglusterfsclient: Guard against un-inited VMP searches
    
    On my system, an selinux module gets inited before
    booster even though the FS calls from the selinux module
    get routed through our LD_PRELOAD'ed wrappers. In this
    scenario, the VMP list is un-inited, resulting in a seg-fault
    if it is dereferenced. The list_empty check does not help
    because the pointers in the list have non-NULL values.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4ecd27aed126b20012abe1449bc49b4c646cb9d0
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:57:42 2009 +0530

    libglusterfsclient: Add comments to API
    
    Some of the functions have also been moved within
    the header to reflect the order in which users will
    read through and try to understand how to use the lib.
    
    For eg. the init, mount and umount functions have been moved to
    the beginning to clarify how to start by init and de-initing.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 90f854f470b354bc36d46397d39a065cbe89e27d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:57:34 2009 +0530

    libglusterfsclient: Expose a few remaining APIs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b12fde2b06c4701970201aaebc7f45a8b964812c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue May 5 15:57:27 2009 +0530

    libglusterfsclient: Add VMP-based rename
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6fdf8f4c7d5cced776c925052eb8a81c332a3573
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon May 4 10:59:18 2009 -0700

    Do not lock entire file for metadata operations.
    
    Metadata operations now lock only a single byte at offset
    (LLONG_MAX - 1) instead of the whole file, to avoid contention
    with writev().
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1a5bcf508b22c1f9f5bd2f555e290f6725035cd2
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon May 4 10:50:48 2009 -0700

    Made afr_flush a 'quick-unwind' transaction.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9aea45a0e1338a10558c4f3f434d172c4bc8c209
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Sat May 2 14:37:04 2009 +0530

    io-threads: Clarify thread count range
    
    This patch cleans up io-threads behaviour regarding the
    range values that can be specified for min-threads
    and max-threads. THe major change is that the min threads
    have been reduced to 2 to signify that io-threads needs minimum
    two threads for its operation, while keeping the default number of
    threads at 16. The idea is to decouple the default thread count
    from the minimum thread count.
    
    Note to Avati:
    This applies over Raghu's indentation and logging take-3 patch.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 80c30634da16f7b333d07eeff9839b70d577e39f
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon May 4 10:33:11 2009 -0700

    io-cache: indentation and logging fixes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5d417f0f8853e4f17caf25255f98c559f3670434
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu Apr 30 07:09:42 2009 -0700

    io-threads: indentation and logging fixes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bed4717a1b41e3e9af47ff1673e28925ba351f92
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 30 10:42:14 2009 -0700

    Cleaned up log messages in storage/posix.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f9d689ef3dd7040e09f704d24696b268ac1bdff6
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 29 05:23:17 2009 -0700

    write-behind: indentation and logging fixes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 60d91b69768bd97cd83adc6edb4e1f7d6c13b6ba
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 29 04:21:59 2009 -0700

    read-ahead: indentation and logging fixes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 946436dc17f7df47608b9a64aa11b77d7caf309d
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri Apr 24 05:47:39 2009 -0700

    Fix a conditional during dependency check
    
    Conditional was wrong and dependency check would fail.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ce6fa580af849b03c4641baf77bf07c590be934a
Author: Amar Tumballi <amar@gluster.com>
Date:   Wed Apr 29 08:51:41 2009 -0700

    bug fix in server protocol segfault when the volume file key is NULL
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 78aa2ee7d2f646a41f19858db9c48a8afc82e83f
Author: Vikas Gorur <vikas@gluster.com>
Date:   Wed Apr 29 03:23:55 2009 -0700

    Cleaned up log messages in features/locks.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d22b495e0c4c180de63082add3e3e3168f1a0e1f
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Wed Apr 29 02:16:51 2009 +0530

    cluster/unify - unify_forget() should not try to access inode->ctx, if inode->st_mode is not set.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2de8717247d3dc1dcda4e3e8b3c260887c3e5891
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Sun Apr 26 22:51:18 2009 -0700

    mod_glusterfs/apache/2.2: fix segmentation fault
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3e3fa81c3465bc329d448aac78de8e556d9d513f
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Sun Apr 26 21:36:33 2009 -0700

    memory leak fix in auth/login.c
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f827d1536635c53dbee27ade459f1e207c1115e8
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 19:29:50 2009 +0530

    protocol/server indentation fixes

commit 604f38b8df4ac8427f55bc708bb72d8700924122
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 16:02:22 2009 +0530

    protocol/server log level fixes

commit 7bbbc9c8786d079055138ac4f8ea98b576c73ce0
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 15:11:21 2009 +0530

    protocol client log cleanup

commit 7ce91b4e860b7c077c64e54f49943b2f77972967
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 15:11:05 2009 +0530

    fuse-bridge log cleanup

commit d2ed893e3a526506ef302281d6bc936e6219063d
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 15:10:38 2009 +0530

    socket transport logging cleanup

commit 702affac485649f9509b1d6912e1a7737dbb23ca
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 15:10:16 2009 +0530

    dht logging cleanup

commit a76ce13ce29249f4622fcfef39bcd087c1cd050a
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 15:09:57 2009 +0530

    afr logging cleanup

commit 34f9a0b30043cf7836601cb620b4bcc4239357ac
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 28 15:09:22 2009 +0530

    libglusterfs log cleanup

commit 29f111a22fe574eaa6938bf0bd3516796abe597d
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 21 19:39:24 2009 +0530

    log message cleanup in distribute
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 53f4af3aad6601ded97b5ef19d2383fe8efa7984
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 21 21:36:27 2009 +0530

    log message supressing in DNS resolution
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3699c3b966dec936bbbe9ec610d48feb41e0880a
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Apr 21 21:34:38 2009 +0530

    cleanup of logs in socket and ib-verbs transports
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9c540ee5bf8a620db3855814db7b0f0f71644aac
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:08 2009 -0700

    Cleaned up log messages in replicate.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 04532fe34c582f551ec7d81b3fa6168f3a4a4d21
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:07 2009 -0700

    Cleaned up log messages in client-protocol.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f99f41b67e500a38015b61781b59224a8395dd98
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:06 2009 -0700

    Cleaned up log messages in mount/fuse.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8825c34d14e76914f7357c773c86b89ff03592cc
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:05 2009 -0700

    Cleaned up log messages in xlator.c
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit add02343dd4d9a095552a703f8fa732455b0ff8d
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:04 2009 -0700

    Cleaned up log messages in spec.y
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 0651c3a12c30f21067111498e9710864698c028b
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:03 2009 -0700

    Cleaned up log messages in inode.c
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c3e4bb1bc8c7aac727a236f101c5d9f36a536c5a
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:02 2009 -0700

    Changed logging format to remove line number & function name from NORMAL and higher levels.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b52a5a408b82496a295c1065f2286c6755a04689
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:34:01 2009 -0700

    Introduce new log level GF_LOG_TRACE.
    
    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>

commit 174872b3644d36f6d0f8a34d9c06092abc126e4f
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 21 02:18:38 2009 -0700

    Remove log level TRACE and the macro GF_TRACE.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e0c284c6e7c98b3a2fbd5c60d59b928d6e7af88a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 24 15:28:40 2009 +0530

    iobuf: Define MAP_ANONYMOUS
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7b2e459db65edd302aa12476bc73b3b7a17b1410
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 24 15:18:15 2009 +0530

    rename transport-timeout to frame-timeout, and set default to 30mins

commit d892c56c1d0b1de466ee4cf4071ab7b722808c00
Author: Vikas Gorur <vikas@gluster.com>
Date:   Fri Apr 24 00:57:42 2009 -0700

    Revised README
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 689347f278e5acfda95a24f7804a1450043311f3
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 23 06:53:02 2009 -0700

    Do not fail lookup() in case of split-brain.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 99351618cd15da15ee875f143154ea7f8e28eaf4
Author: krishna <krishna@gluster.com>
Date:   Wed Apr 22 23:43:58 2009 -0700

    "option unhashed-sticky-bit on/off"
    
    "option unhashed-sticky-bit on/off" will configure distribute to set or not
    the S_ISVTX bit in the stat.st_mode of the actual file in case it is
    pointed to by the link file. This can be enabled during migration.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b6f634f602559cfe0c4609f16c9f33a32243b578
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Apr 23 11:20:17 2009 +0530

    fix build warning in locks translator

commit d886ceb9cbf45434ea0218f0098862daafb26ecb
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Apr 23 11:09:37 2009 +0530

    minor build fix - set EXTRA_DIST to point to MacOSX/Portfile instead of Portfile

commit b0acbf09c21ff898ad3315811974e49cc80e6f2b
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 23 04:05:00 2009 +0530

    fix bdb_db_get() to return exactly read bytes and to copy the read data to given buffer only when needed.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e5686c440f3c03fbb24759342e5badf102579634
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:33:59 2009 -0700

    mod_glusterfs/lighttpd/1.4: port to use virtual mountpoints.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5f0bf570069770ee5c98fea728f0231f93eaab5c
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:34:10 2009 -0700

    mod_glusterfs/lighttpd/1.4: ensure each line is no more than 80 characters
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7a77bad6d583ee9266e6e3f566bf19d579177e3e
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:32:30 2009 -0700

    mod_glusterfs: port apache/1.3/mod_glusterfs to use virtual mount points
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e26b63ccfc3aa0b29afb7235b863b7b4a7c8ae95
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:32:42 2009 -0700

    apache/1.3/mod_glusterfs: ensure each line is of maximum 80 characters.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3c68984b6f8dbb772a858fcf829d6c6f81503912
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:32:53 2009 -0700

    libglusterfsclient: implement glusterfs_umount
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b817670c609dda2a1038fb94bd5a7dc6fa522518
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:33:03 2009 -0700

    mod_glusterfs: port apache/2.2/mod_glusterfs to use virtual mount points
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 725a1fcb1e84507c28f009d0f83692e0b57e474b
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 22 07:33:15 2009 -0700

    mod_glusterfs: coding guidelines related changes
    
    - make sure code fits into 80 character lines.
      - proper indentation of declarations.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c8e9a96e2c3801701e7f218f1b12fef16071b088
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Apr 23 10:20:06 2009 +0530

    replicate dir self-heal - when creating a missing dir/file, set pending xattrs on source subvolume for that dir/file

commit bb592b1a8465fa078d0cd5f445f08280b78a93e4
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Apr 23 02:18:52 2009 +0530

    fix in afr directory self-heal (partial healing)
    
    impunge loop was 'continued' on a different subvolume in certain cases, resulting in healing of partial files

commit 86fff0e75b445dee3cda6b788699930eb649334e
Author: Harshavardhana <harsha@zresearch.com>
Date:   Tue Apr 21 02:24:22 2009 -0700

    Add MacOSX based packaging file into repo
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 38a6a5b1a12eff04f26ded17ce4585a6ebdc7986
Author: Vikas Gorur <vikas@gluster.com>
Date:   Wed Apr 22 04:31:36 2009 -0700

    Bug fix in releasing inode locks when transport gets disconnected.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit df6d9e16817d952c17700d44ab478e6d6af704a0
Author: Vikas Gorur <vikas@gluster.com>
Date:   Wed Apr 22 01:02:09 2009 -0700

    Release all pending locks in pl_forget().
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7eb63e30f22f7a9d785f6620be22d2b3aab77ada
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Apr 22 12:55:47 2009 +0530

    iobuf_pool->arenas_cnt should be incremented in iobuf_arena_alloc, and not iobuf_pool_add_arena (to avoid counting of unpruned arenas)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4877476fa1a591c51f4b3ee76082766f38a33b23
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Apr 22 04:01:06 2009 +0530

    0-byte write guard
    
    guard server_writev from 0-byte writes from client where iobuf will be NULL. This is possible only via libglusterfsclient (not fuse)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bc1dff620cc185c3e08853b9b7fb4c5a04c48ebe
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Apr 22 03:59:30 2009 +0530

    handle iobuf NULL return case in fuse-bridge, by waiting 10 seconds and trying again
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cf508025fe506a507fe16ed52df74dc7e0ca7c64
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Apr 22 03:44:01 2009 +0530

    fd leak fix
    
    steps:
      - server_finodelk uses req->volume pointer into state->volume
      - finodelk is queued by locks translator
      - c call returns from server_pollin and hdr is FREE'd
      - now state->volname is pointing to FREE'ed region (junk)
      - server_finodelk_cbk calls gf_add_locker
      - gf_add_locker remembers lock with junked path along with fd_ref
      - gf_del_locker from new server_finodelk cannot string match with junked volume thus
        lock is not deleted, hence fd_ref remains as a leak
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8d2e5d8062361df451be7c6f748a23884f1cf315
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Apr 22 02:21:46 2009 +0530

    afr_lookup_cbk - self-heal getting missed
    
    compare for mismatching sizes and attributes before overwriting local->stbuf for read-child subvolume. This causes files with differing sizes on backed not to get self-healed if xattrs were missing.
    
    Also add the ESTALE check for compulsorily failing revalidates in case of 2nd unwind and beyond
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 07f1524165f864e09033b7f78e921c5375d4e2d6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:50:33 2009 -0700

    posix: Ensure EINVAL return on NULL args
    
    Initing op_errno to EINVAL ensures that this is the value
    that gets returned on STACK_UNWIND, in case any of the VALIDATE macros
    result in exit from "out" due to a NULL argument. If this is not done
    , we get op_ret as -1 with errno set to 0 in the application's
    syscall.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 27e1c9fbd3fb6eda4f7d64ff04dad9d306c237e7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:50:20 2009 -0700

    call-stub: Check for NULL in the correct variable
    
    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>

commit 31643eb227a5dfba11d23068e9626bf9546283bd
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:50:08 2009 -0700

    io-threads: Add fxattrop fop
    
    -- added some indentation fixes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e246a3131676197aff0430429db1e7d7cc00be65
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:49:55 2009 -0700

    io-threads: Add xattrop fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a9b4360d889097e8ea25497eb669daebcaf1e381
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:49:45 2009 -0700

    io-threads: Add readdir fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d1eb9b13d2e50485e69301ade12afe5ea8636af8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:49:24 2009 -0700

    io-threads: Add removexattr fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 609c5aff6faa21cf3aaefa6b7a2a31a91590d726
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:49:10 2009 -0700

    io-threads: Add fsetxattr fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a77340b94147a078918536a5297746803c846809
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:48:56 2009 -0700

    io-threads: Add fgetxattr fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d7753849cc66c3aef66dc1270920389d3c42e7ce
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:48:45 2009 -0700

    io-threads: Add getxattr fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6b426bc53e2e6106e32568f09354d4e4ce382f11
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:48:33 2009 -0700

    io-threads: Add setxattr fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1cb8064b2a653f06062c226dc12d524d8f1a2da2
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:48:21 2009 -0700

    io-threads: Add statfs fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d769066ddcb7b3fab456a57704b184d0617b8d52
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:48:08 2009 -0700

    io-threads: Add fsyncdir fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 282a39c19ee15f8908eb28f0b2d6983b665d57a7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:47:56 2009 -0700

    io-threads: Add opendir fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cdbeb01abbfc26345df98e5a98a0e5ed513b7cf8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 21 04:47:42 2009 -0700

    io-threads: Add link fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6bff99a8f92befa78ddea62519a05f945db5cdfa
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:36:44 2009 -0700

    libglusterfsclient: Add VMP-based realpath
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cf22fd1d0430705e226d61ff8d9492925ce95d46
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:36:21 2009 -0700

    libglusterfsclient: Add VMP-based readlink
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a9febb4bd30f41681755a0ee925ae3de6f0fa292
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:36:05 2009 -0700

    libglusterfsclient: Add VMP-based symlink
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cb95018adab1377c862dca32f58825b336adafd0
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:35:50 2009 -0700

    libglusterfsclient: Add VMP-based unlink
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6f91c9dc86be9c10467ccb5bc3edde2c5d767b9f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:35:32 2009 -0700

    libglusterfsclient: Add VMP-based mkfifo
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bcc9a67fc22147f54a27a81ee35f4c081a0e6b73
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:35:17 2009 -0700

    libglusterfsclient: Add VMP-based mknod
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a7205e78bfb962d9e5ff11db2a0b394e6db03256
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:34:58 2009 -0700

    libglusterfsclient: Add VMP-based utime
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e707afad9f6282bc425f8b0262ea5a6db018ec92
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:34:41 2009 -0700

    libglusterfsclient: Add VMP-based utimes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b4259400090a28a5dbe27922ad8bc309db2a7c4a
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:34:20 2009 -0700

    libglusterfsclient: Add VMP-based statvfs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6cb3159ef38428572b81160e91e7c685ed44acb0
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:34:02 2009 -0700

    libglusterfsclient: Add VMP-based statfs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit de2192ea754883ea6ae643f63c44c2cbeb20f981
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:33:43 2009 -0700

    libglusterfsclient: Add VMP-based link
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 12d9b4cccd559776f125440a232ff5b944ab3442
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:33:26 2009 -0700

    libglusterfsclient: Add VMP-based opendir
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e2ba80403c3e73220a2b48b813df1561a9081e09
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:33:06 2009 -0700

    libglusterfsclient: Add VMP-based chown
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 74a46284e17045db302e5bcde0052ea6c7b4c038
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:32:46 2009 -0700

    libglusterfsclient: Add VMP-based chmod
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 721783da4f9705331356328b8082873aec1ced0e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:32:29 2009 -0700

    libglusterfsclient: Add VMP-based rmdir
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 07da4292a8678a415acfec130c40febc9a63b6b4
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:32:06 2009 -0700

    libglusterfsclient: Add VMP-based mkdir
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit dc53183708d6d9ff998487427312000f30dcb7ee
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:31:49 2009 -0700

    libglusterfsclient: Add VMP-based lstat
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 84eb262529ea5389df2296d182ecd5e0582602a7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:31:31 2009 -0700

    libglusterfsclient: Add VMP-based stat
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit aa1e2fd37ab93b194308f94edd8ab0a342c7830e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:31:09 2009 -0700

    libglusterfsclient: Fix stat cache bug
    
    The way stat cache gets updated was not consistent across
    all syscalls. Consequently, I was running into a bug that
    returned a 0 st_ino. The fix actually resides in the hunk
    that changes the lines in libgf_client_lookup but similar
    changes were also required in other users of stat cache.
    
    This commit fixes the bug and also cleans up the way stat
    cache is updated.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f29383ef35d210f2a72883cb6157e915200f7c7c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:30:51 2009 -0700

    libglusterfsclient: Add VMP-based setxattr
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4074769dd2435ab3521ab39eb2775c3e80fc32b4
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:30:36 2009 -0700

    libglusterfsclient: Add VMP-based creat
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d875df0c5c095488db29a202eac74d10d540aa3b
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:30:15 2009 -0700

    libglusterfsclient: Add VMP-based open
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bb2ca0ec0da700f600d1fa30d111c2aa42804f70
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:29:57 2009 -0700

    libglusterfsclient: Add VMP-based getxattr
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6cd656152901ba19ef52f762d000e329e3f7dbc6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:29:40 2009 -0700

    libglusterfsclient: Add VMP-based get
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 86a1c646eeea353643bd6bd5eb040cf584b407c1
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:29:21 2009 -0700

    libglusterfsclient: Add virtual mount point support
    
    One part of the glusterfsclient library requires users
    to use a handle to address a particular glusterfs context.
    This can become cumbersome for applications that need to use multiple
    such context. For such applications, we make it easy by letting them
    define virtual mount points(VMPs), which are just paths that identify
    a particular glusterfs context. This is done through a new
    glusterfs_mount(..) interface.
    
    Subsequenly, any path based operations, that pre-pend a VMP before
    the files and directories inside the glusterfsd export, get internally
    routed to the correct glusterfs context. This helps users do away
    with the need to maintain their own path-to-glusterfs_handle_t
    mapping.
    
    The old handle-based interface still exists for whoever wishes to use
    it.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7c7fd9039b0d0ba17190677f864c5a22d46ab4d6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:29:00 2009 -0700

    libglusterfsclient: Must return size from readv
    
    The line being removed made libgf_client_readv return
    a 0 on successfull return when the return should really
    be the size of data read.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7bc1747de75d7a65059fbcb191c3776210de1491
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 20 12:28:40 2009 -0700

    libglusterfsclient: Expose glusterfs_realpath
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 82394d484803e02e28441bc0b988efaaff60dd94
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Apr 20 03:54:04 2009 -0700

    Check return value of afr_sh_select_source.
    
    If select_source returns -1, abort self-heal.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fbefbfee743a01b5ad9977ad24de372258aeb65c
Author: Harshavardhana <harsha@zresearch.com>
Date:   Mon Apr 20 04:59:54 2009 -0700

    change errno EINVAL to ENOENT in case of all fuse_* calls for fuse_reply_err ()
    
    Seen "rm -rf" returns EINVAL in case fuse_loc_fill fails when there is a race condition which can happen when multiple "rm -rf" are done on a same directory listing from multiple terminals.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2f5ee29248f4eafcd1c2f5cc31432d22739349d0
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Apr 20 03:38:15 2009 -0700

    Minor fix in afr_sh_build_pending_matrix.
    
    Remove incorrect check for xattr[i] being NULL.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit aa085b10678c01693d0f7222bd4054bb8e8836cc
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon Apr 20 13:15:12 2009 +0530

    inode.c - NULL check for the extra __inode_search performed, when presented inode is not hashed.
    
    This bug fixes #967

commit 8660bb2bef59c00df194087ed75ba81f34555a73
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon Apr 20 12:00:50 2009 +0530

    afr-transaction: handle double flushes
    
    __if_fd_pre_op_done - reset fd_ctx->pre_op_done to 0 so that double flushes do not result in two xattrop() calls

commit 3b8f7ed4c080dc45da02dc751478863007199c26
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon Apr 20 08:08:26 2009 +0530

    client_protocol_reconnect - do not send notify of CHILD_DOWN event if errno from transport_connect() was EINPROGRES
    
    This bug was racing between a CHILD_UP from poll thread resulting from the event_register() of the new socket called in fuse thread. CHILD_UP would sometimes overtake the CHILD_DOWN for EINPROGRESS. So replicate would receive CHILD_DOWN as the latest event. This resulted in self-heal not happening etc.

commit 42617775a2821dc74300b89dd14a08b068575b2b
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 18 13:27:21 2009 +0530

    keep ctx->page_size fixed at 128KB but only add the margin for iobufs which are created

commit fb5cc405ae45b4e573d6acbe3383349a278f2bdf
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 18 11:19:34 2009 +0530

    enhancement to migrate-unify-to-distribute.sh

commit 093141a74962f11654c44fe2292605f9cf65e709
Author: Amar Tumballi <amar@gluster.com>
Date:   Fri Apr 17 16:07:00 2009 -0700

    added migration script from unify based setup to distribute based setup
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9a4a2e2286cb372ca462f6f25f78de686ea3e4ce
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 18 02:49:03 2009 +0530

    pruning buffer margin - do not destroy if no other non-filled arenas are in the pool

commit 307528ef9a33a4d294b3ea49bbf5f0b16b27aa0f
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 18 01:09:31 2009 +0530

    disconnect transport peer if system is out of memory while allocating iobuf

commit 50b2291e3b046ea6b8fdfcb7e206c772eae64f0e
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 17 23:35:43 2009 +0530

    iobuf - account with iobref_size() instead of iov_length (vector)

commit 1d6dfe94fb970b51d96653da6c3361533d697fc3
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 17 23:12:37 2009 +0530

    added 2 APIs iobuf_size and iobref_size to return the system memory usage by an iobuf, and by all iobufs in an iobref respectively

commit 7867577b346c7f003be67ad202f4085cf35fdf7c
Author: Vikas Gorur <vikas@gluster.com>
Date:   Fri Apr 17 06:15:16 2009 -0700

    Destroy old ping timer before setting new one.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7b1beca0a3b60a8b9347a3122d77aea081ccb773
Author: Vikas Gorur <vikas@gluster.com>
Date:   Fri Apr 17 05:42:23 2009 -0700

    Fix two memory leaks in afr self heal code.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 98a872df828aa2786c7bf595d430ef64351f4192
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 17 17:52:07 2009 +0530

    add 4KB margin in iobuf to accommodate fuse header

commit 0b20c24a399eb03fdc431ea2761e1334e0032651
Author: Vikas Gorur <vikas@gluster.com>
Date:   Fri Apr 17 04:23:58 2009 -0700

    Fixed parameter to finodelk in STACK_WIND in dht
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4e3eae6561b38b53bef2d20177ab62602db45c14
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 17 02:33:01 2009 -0700

    libglusterfsclient: Fix typecast to fix build warning
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4a632ea96be3012c583165865bbde392f99a327b
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Fri Apr 17 14:19:18 2009 +0530

    protocol/client - set remote inode number in inode context for root inode also, during lookup_cbk().
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6bd53940d198e55780cbc7d8678da6d67df80265
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri Apr 17 01:08:00 2009 -0700

    Renamed abs_top_srcdir to top_srcdir for older versions of autotool
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4e68cf7c4d912556e25eb1226669d7b438ff8a3f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:59:02 2009 -0700

    libglusterfsclient: Remove unused variables
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 27d73ca503b2e508c682fca2848f8ae38390a146
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:58:50 2009 -0700

    libglusterfsclient: Add realpath API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4ada36f9bd6e008dfea65d708d785907b993b946
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:58:39 2009 -0700

    libglusterfsclient: Add lstat API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7cd3cc24c8f3178382074c8a3a319df17b85769d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:58:26 2009 -0700

    libglusterfsclient: Add readlink API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a6f0446541e917979a697edd06dd28634bf3ec6d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:58:13 2009 -0700

    libglusterfsclient: Add symlink API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7aff8936f9c86677ee205e1cf9cb41f4ea9edecd
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:58:00 2009 -0700

    libglusterfsclient: Add unlink API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 42528875cdaee764070e54b8fcd5e91ba8733e98
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:57:40 2009 -0700

    libglusterfsclient: Add mkfifo API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 933c3eee81f843db1fb8a2eda491d49cfc04efea
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:57:24 2009 -0700

    libglusterfsclient: Add mknod API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 169976dfafeb714f3c94b9a2f635f36759334b9c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:57:13 2009 -0700

    libglusterfsclient: Add utime API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c9017ae0de2531342125eaf2a6aca3b9a251b16e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:57:01 2009 -0700

    libglusterfsclient: Add utimes API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 366bd140f3f0fbc6b343aab067713c398ae601af
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:56:51 2009 -0700

    libglusterfsclient: Add rename API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5feab82f0c228410d94f3dfa53025f85d6eac8b1
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:56:40 2009 -0700

    libglusterfsclient: Add statvfs API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ff2bacf3466ddd4473ae3774e1f822981f4d8198
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:56:29 2009 -0700

    libglusterfsclient: Add statfs API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f199ebf5d0c4d90abbc5d0dafd67561f39f398b8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:56:08 2009 -0700

    libglusterfsclient: Add link API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e18b8031ab4c7ce763e1e7d57bf5c98a1cbe7167
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:55:55 2009 -0700

    libglusterfsclient: Add ftruncate API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9193494d20a8555a90126b9d23e848b0b8ca196e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:55:40 2009 -0700

    linglusterfsclient: Add fsync API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 912f1a8492c8c20743c8d7f0a75aeb31f2483932
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:55:26 2009 -0700

    libglusterfsclient: Add fchown API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 67561c965210f299b8a7e4ea1be0a702095b19f6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:55:12 2009 -0700

    libglusterfsclient: Add fchmod API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 01a48790c4a0c9805eb55bfe1c60860ee91f48a1
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:54:58 2009 -0700

    libglusterfsclient: Add closedir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit eb4d5f0074ab6430973188906a8083d26e24e790
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:54:42 2009 -0700

    libglusterfsclient: Add opendir API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f6ebe58492095a5d7ceb5762cb35defca945ab45
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:54:27 2009 -0700

    libglusterfsclient: Add chown API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e7d7a19d5733dfcea87467c5f96e1aaa812d5df8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:54:14 2009 -0700

    libglusterfsclient: Add chmod API
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f887fd6f7c6a5b740ebbf220706ebc44a938d67e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:54:00 2009 -0700

    libglusterfsclient: Abstract away inode attr cache updates
    
    This commit creates a separate function that allows users of
    the inode attribute cache to update the cache when required.
    Major users are lookup, stat and fstat functions.
    
    The function libgf_update_iattr_cache(..) allows updating the lookup
    and stat caches separately using flags.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4c98eaf4c464e7e2f1c6ce66414fd7864f5c8bfa
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:53:51 2009 -0700

    libglusterfsclient: Replace dict based inode ctx with array based one
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c71110fb153adfd4628718f634348b7a5712bf32
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:53:39 2009 -0700

    libglusterfsclient: Fix fd_ctx leak on release cbks
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit adb677be13e6b755c3eeb685759d2522f6c466a7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:53:24 2009 -0700

    libglusterfsclient: Replace dict-based fd ctx with array-based one
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 00968db3069e7b145f108d53a62d1899c9c1f3f9
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:53:12 2009 -0700

    libglusterfsclient: Generalize [RW] checks on dirs
    
    This patch moves the read-write permission check on directory
    inode into libgf_client_opendir, so that when I am next adding support
    for the opendir syscall, I dont have to perform similar checks again,
    outside this function.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1873d0bdb53af0311e8ad344116c0923448a6ff5
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:52:54 2009 -0700

    libglusterfsclient: Check for directory on O_CREAT
    
    If we have received an O_CREAT for a name where that basename is a
    directory, and if we have successfully looked up the inode for this directory,
    then we can check for S_ISDIR in libglusterfsclient and prevent sending a message
    to the server through libgf_client_creat. See also the comment inline.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 79215d4f2487e6db87e5fd637f0262037c1d230b
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:52:43 2009 -0700

    libglusterfsclient: Create and use LIBGF_REPLY_NOTIFY macro
    
    All reply notifications can now be abstracted away through
    this macro and all cbk functions should now call this.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ba4833355a1ee77f828b538a357e07c46f36b037
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:52:27 2009 -0700

    libglusterfsclient: Fix segfault on non-NULL loc->name
    
    The gf_log message actually assumes that loc->name will have a valid
    non-NULL name in it, whereas if the loc_t being passed to it was
    actually created on a function stack, i.e. a local function variable
    and was then passed down the code path to do_path_resolve without ever
    initing it or zeroing the structure, its possible that the name member
    has a non-NULL but corrupted address. This leads to a segfault.
    Whereas, we know loc->path will always have the full path.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c1b3deff1186c581cb8d9893a3a0de6bf00d3adc
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:52:04 2009 -0700

    libglusterfsclient: Use macros for argument checks
    
    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>

commit b3e3fc79d4e7008a27d935decefcca51ba89dc17
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 16 23:51:45 2009 -0700

    libglusterfsclient: Rename XLATOR_NAME define
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 41011cdb4c9f76a1805f0b908d1d7f77cef545b2
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Fri Apr 17 00:32:17 2009 +0530

    protocol/client - NULL check for loc->inode added in statfs(), before trying to retrieve remote inode number from loc->inode's context.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4c4021bea2d9f484321066518e10d2b139af2a3a
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Apr 16 06:15:48 2009 -0700

    RPM spec file updates for RHEL,CentOS,Fedora,SLES and OpenSUSE for upcoming 2.0.0 stable release
    
    * Updates to ahere to RPM standards hugely driven by Fedora dist-f11.
    * RPM spec file portable across RHEL, Fedora, CentOS, SLES, OpenSUSE.
    * RPM spec build options made compact and removed unnecessary.
    * %changelog old entries removed as they were giving many warnings
      during rpmlint.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7ae141bb054494c86cfb60b377ab989c30938f66
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Apr 16 17:32:05 2009 +0530

    add NULL check in iobuf_arena_destroy

commit 6bc3f3c19b9e720ade3702ce409a8a99cc13f1dc
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu Apr 16 03:41:54 2009 -0700

    logging enhances to commit d77279ef04ca75ab9715864274567d1ce0ce66a6
    
    - logging made more relevent.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8a00ad080cbea0d01470c5f724d7d8ff54b0e254
Author: Vikas Gorur <vikas@gluster.com>
Date:   Wed Apr 15 06:02:22 2009 -0700

    Use original pid when calling the FOP in afr transaction.
    
    Save the original pid while locking and restore it
    after the FOP is done. This ensures posix-locks can
    release locks (fcntl) properly.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 34f8f0b3e1f992cf59da2c2d410471e440e6ed92
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 15 03:11:21 2009 -0700

    write-behind aggregate-size related changes
    
    This patch brings in following changes:
       1. make aggregate-size as non-configurable and make it to be equal to
          maximum iobuf size.
       2. best effort to write data in chunks of length as close to aggregate-size
          as possible but not greater than aggregate-size, since aggregate-size is
          made equal to Maximum size of iobuf.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ffb863c3a8cbfb2105ac23ce5fc5be1df372458c
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Apr 15 03:12:17 2009 -0700

    write-behind: adhere to coding guidelines.
    
    - make sure lines are not greater than 80 characters in length
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e77eb62f253bc2288b1b4ff582f99ebf16a28c47
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 16 14:38:02 2009 +0530

    cluster/distribute bug fix - try to create linkfile in dht_lookup_everywhere_cbk(), only if hashed subvolume can be determined, else error out with ENOENT.
    
    -- with local fixes (avati)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d1703344735d9c4df89b84310deaf1b9703f8c49
Author: Harshavardhana <harsha@zresearch.com>
Date:   Wed Apr 15 01:00:01 2009 -0700

    Fixed the build problems observed
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e6c22c0587bbd9cb84969f5673db043c32e485ef
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Tue Apr 14 15:28:34 2009 +0530

    eliminate this_ino_get(), this_ino_set(). handle inode_ctx_{get,set}() at the fop level itself.
    
    they used to log ambiguously
    and was of no use. logging is now more precise and will help in debugging,
    in case of errors.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f7902b7072015c9c20f47e999af85c923f202d33
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 14 08:15:50 2009 -0700

    Changed xattr format of afr changelog to support adding and removing of subvolumes while keeping existing data.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d77279ef04ca75ab9715864274567d1ce0ce66a6
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Tue Apr 14 02:53:09 2009 -0700

    server-helpers: Add check for NULL connection arguement being passed in helpers.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3baa437e9980e7dac9893d6c11ccc1623a5faee2
Author: Anand V. Avati <avati@gluster.com>
Date:   Tue Apr 14 15:09:37 2009 +0530

    remove unused variable @ret in ib_verbs_options_init
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 54c40bbfb48e2f7469149d6724e2ac77bce0690a
Author: Anand V. Avati <avati@gluster.com>
Date:   Tue Apr 14 14:51:26 2009 +0530

    use MAP_FAILED macro to free mem_base in arena_destroy
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1ce5acccf5186e70424826d4f22cee3a29ac114e
Author: Anand V. Avati <avati@gluster.com>
Date:   Tue Apr 14 14:51:16 2009 +0530

    FREE arena->iobufs in iobuf_arena_destory
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8b32e03f87599bd3d87ec99c5718d40ff10831ff
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Tue Apr 14 14:20:04 2009 +0530

    cluster/unify link() should be sent to only one subvolume.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7a4bc3fbb352396b27489b0e97327d0fc82b85d5
Author: Amar Tumballi <amar@gluster.com>
Date:   Tue Apr 14 00:41:43 2009 -0700

    minor bug fix in posix_create() when 'o-direct enable' option is given.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 33e81bc94986929caab14a05231b25787a25a41b
Author: Amar Tumballi <amar@gluster.com>
Date:   Mon Apr 13 23:40:22 2009 -0700

    bug fixes in dht-disk-usage feature.
    
    fixes bugs seen with dht's disk usage.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d8bc2834d056a23f55bd86a5fd704bd81e35836d
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Apr 13 07:23:59 2009 -0700

    Send statbuf from the same subvolume, even across revalidates.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8e0d48cbb23cf056277ebc609d47b5184b95fa87
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon Apr 13 18:42:36 2009 +0530

    use ctx->page_size in all translators and transports instead of having their own configurations
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 451620e0ec88f717e7046ebb27fe1f29d73796d9
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon Apr 13 17:50:21 2009 +0530

    introduce page_size in glusterfs_ctx_t to be used by all translators set it to 128KB in main()
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3093ff0b125c520fdac3db627af708f495c9a47e
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Mon Apr 13 15:41:01 2009 +0530

    client_readv_cbk - when op_ret is 0, iobuf comes NULL from transport, handles this case
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a0bb8a02cd334aeda02e6146ea541a7dae4223d5
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:03:43 2009 +0530

    bug fix in iobuf_select_arena - call __iobuf_pool_add_arena (unlocked version)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3fb7252c5ec7edd8c9234d4fcc369fd10707a613
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:03:35 2009 +0530

    bug fix - arena destruction now calls munmap and not FREE
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit dc9cdbdc1c03c231ba405e540fac7d6483159bb2
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:03:28 2009 +0530

    add purge list support to make iobuf_pool_purge() in expensive, and actually call it in iobuf_put :-)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b9a210a419ff28f2d75b10a680520fd6cc37ac5a
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:03:21 2009 +0530

    bug fix in iobuf_select_arena - never created a new arena
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 688db6452befde5d7cd2b35f86b770b4c19c53fc
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:03:13 2009 +0530

    add @filled list in iobuf_pool to keep away filled list from getting searched in iobuf_select_arena
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4f0d487c96b84123289d3c48fd84188efe136293
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:03:02 2009 +0530

    change arena size to 8MB
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 00dff3bddc375e88e710a751f47843f9da77a70c
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:02:57 2009 +0530

    use MAP_FAILED macro to check for mmap failure instead of (void *) -1
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 014cdf385642947d0592102b2c7338a8ad1c2d4e
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Apr 13 14:02:47 2009 +0530

    fixed sizeof parameter in CALLOC of a new arena
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5dd850ae840ddb402ca4aaae19c668094947507e
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Mon Apr 13 11:21:20 2009 +0530

    switch scheduler to validate the subvolume specified for a pattern, against the given subvolumes of cluster/unify.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ec06475f22db2a3683167c5ffbe236c8e4aaf0ab
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Mon Apr 13 04:47:39 2009 +0530

    changes to database read interface, to make use of a given buffer instead of allocating internally.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 945f438d393297cf72a3157532625b6b02e87268
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Mon Apr 13 02:09:25 2009 +0530

    log formatting fixes. use GF_PRI_SIZET for size_t.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3f1e93c29856ec1e75327525899d1f0d6a81c0a3
Author: Amar Tumballi <amar@gluster.com>
Date:   Sun Apr 12 04:16:09 2009 -0700

    minor initialization bug fix in quota's build_loc
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ecead44b5c8d1215e7c398ca1132a4b0b11a44bb
Author: Amar Tumballi <amar@gluster.com>
Date:   Sun Apr 12 04:12:00 2009 -0700

    in dht, initialize the free available space properly, so the first few creates are not confused.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e00bdb4a323b60ced500df59071d2a940b976ae9
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 8 02:28:16 2009 -0700

    Coding Style: Add a few points
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4a62b5af1c9add4a74ea38ab9008bf129e2b4110
Author: Amar Tumballi <amar@gluster.com>
Date:   Fri Apr 10 00:34:34 2009 -0700

    feature to disable volumefile's checksum
    
    in server volume define, "option verify-volfile-checksum no" to disable
    the checksum feature.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit be9909606428d78ec23ea02900640c68ca2a40d2
Author: Anand V. Avati <avati@gluster.com>
Date:   Fri Apr 10 09:22:18 2009 +0530

    reset errno to 0 before calling first fuse_lowlevel_new() to reliably detect for unsupported params
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fa9eb588fbe758cbc1ebe727d2455f1dcd0b065f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 10 07:09:49 2009 -0700

    io-threads: Remove unnecessary call to pthread_attr_setstacksize
    
    We do not need to explicitly set the stack size to its default
    value.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4f81149489ae80b20ac28d1fdbe48ee56d0a181b
Author: Anand V. Avati <avati@gluster.com>
Date:   Sat Apr 11 00:54:29 2009 +0530

    prefix ULL to large constants (to fix bdb build warning)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 45c4fb76dfd0756ebd86bf431f5b5761068901b5
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 23:32:24 2009 +0530

    updated glusterfsd to create iobuf pool at initialization
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6d94a368e061afeeac6fb57c5910c71f60791dc3
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 23:22:26 2009 +0530

    updated libglusterfsclient with IOBUF/IOBREFs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 77714c065d99767f5a3820bc1c62b22522681821
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 23:09:15 2009 +0530

    updated transport/ib-verbs to use IOBUF/IOBREFs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 07e8f887547c1b9fd71a3ca45b2c1ac974c939ad
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 23:00:59 2009 +0530

    updated transport/socket to use IOBUF/IOBREFs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 19cac9a1b3d7d4f5720049c4fb2b5e08b27d27e8
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 22:04:44 2009 +0530

    updated mount/fuse with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1650945f2379cc33eab1b21c033d42152fa2592f
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:53:57 2009 +0530

    updated encryption/rot-13 with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5617f5e3a3840b59263ede767c53f80088593c66
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:52:08 2009 +0530

    update features/quota with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 91e3976e99523908541932c02b2c4e9df28a9510
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:48:35 2009 +0530

    updated features/filter with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5d80832d2dc0127b8f380afd7d49ff7b27ac79ec
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:46:54 2009 +0530

    updated features/locks with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d7b12cdc8d2bcbf89530e00710da308bd757e35d
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:43:51 2009 +0530

    updated debug/error-gen with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit aed3aaef43589633f2a43d48435ef234582f37e0
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:42:45 2009 +0530

    updated debug/trace with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d720afb836ecd22c13859356261e85334422f119
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:40:19 2009 +0530

    updated performance/io-cache with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit be1d7c1e3b61477a82152a07a11993061e89b894
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 21:23:00 2009 +0530

    updated performance/io-threads with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 795fb95f42697796008e34790e0768929d478a3a
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 19:00:45 2009 +0530

    update performance/read-ahead with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c29b1710529fb52724ba37e09ca0f10cd7fcffa8
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 18:51:39 2009 +0530

    update performance/write-behind with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e062dd5c2f76106593829ebbb86003de966f00f2
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 18:43:35 2009 +0530

    update protocol/server with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ad86fba6e22b10b06aa44426c2ab3591c54ed0a7
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 18:15:11 2009 +0530

    updated protocol/client with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2e743ddc4a89f8a4d0c9ff0f16a6faf0218e453f
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 18:14:10 2009 +0530

    updated transport interface functions to accommodate IOBUF/IOBREF
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 0e9cda6d77a63723014bb2c040d8215fd7180a10
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 02:33:49 2009 +0530

    update storage/bdb with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6e641226df9a90a4d88c859d4bc1c27fdacc2037
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 02:17:25 2009 +0530

    update storage/posix with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fa5847401431f62013f1ef66363b5a0c1b29a0c5
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 02:02:52 2009 +0530

    update cluster/map with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 645c60e308de5290b9059eae557a320bd6a294d9
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:59:56 2009 +0530

    update cluster/ha with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 89cacef43e843c7563ed5d4ebb6ec16a3b81df3e
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:57:14 2009 +0530

    update cluster/dht with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f33f0669efd89216a528bab3694ac4645a7f523b
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:52:08 2009 +0530

    update cluster/afr with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e0e6acd6fbdcbd294c89e61cbe108fc1b96a62a8
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:39:34 2009 +0530

    update cluster/stripe with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f551e72584b3525d5a55c6fb4456d7b9ca5cb5f3
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:25:26 2009 +0530

    update cluster/unify with new readv writev prototypes
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c723c0dae5fd2887b714a08bcaeadb663e4de44b
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:21:57 2009 +0530

    do away with frame->root->{req,rsp}_refs members
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4554d82bbe2ecec6c79b6a791522358c8855408d
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 01:12:10 2009 +0530

    update prototype of writev and readv_cbk to use IOBREF in parameter (step towards elmination of frame->root->{req,rsp}_refs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3524572538e5abe839fa29fe94da8f7591cedce8
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Apr 11 00:09:08 2009 +0530

    IOBREF support for holding iobuf refs along with fops (replacement for frame->root->{req,rsp}_refs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e953968683d988c8fc3020ede2cb8e5229a548a6
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 10 23:11:33 2009 +0530

    use 128Kbyte as the channel transfer size in fuse-bridge
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 124fb0c752530322e6311dde668422afef6b2afe
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 3 15:17:04 2009 +0530

    IOBUF support (to be used by transports and fuse)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a31e26f8df26b1229e9fbca60ff8bf462b234241
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 10 04:22:37 2009 -0700

    io-threads: Reduce default min and max threads
    
    Going by the memory usage for each threads, it is prudent to
    have lower number of threads by default and let users who understand
    the memory consequences increase the thread count for themselves.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e1977a4e75637109889b581201e44e24506398c8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 10 04:21:53 2009 -0700

    io-threads: Use non-default thread stack size
    
    The default stack size on Linux is around 8 MiB for each
    thread. This is clearly too high for our purpose. This commit reduces
    the stack size down to 1 MiB.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bf7b4623821c8ffe8070297949e18dc6e3757e9c
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu Apr 9 07:59:21 2009 -0700

    posix_unlink: make unlinking in background configurable through volume spec file
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fb034ba3036fadc7cf35edc5cae7481149a67ca0
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 9 03:54:51 2009 -0700

    Compulsorily do self heal if file sizes differ.
    
    If file sizes differ, then compulsorily do self-heal. If no 'wise'
    sources are found, then pick a 'fool' with the biggest file size.
    If even 'fools' aren't found, pick the 'innocent' source with the
    biggest file size.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bfbcde78924fc5847b31ae56fe8d14ea52b60dfd
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 9 03:53:59 2009 -0700

    Handle files which have no pending xattrs at all.
    
    If a pending xattr key is non-existent on a file (call such
    files 'ignorant'), make all other non-ignorant subvolumes point
    towards the ignorant one.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ec35b79f746d8a9451d7a3b9894025fdad7382f4
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 9 03:53:26 2009 -0700

    Erase xattr during self-heal based on original dict.
    
    Decrement xattr during self-heal based on the original dict instead
    of pending_matrix, as the pending_matrix might have been
    altered later.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 445b57bf7207107a9ef078697b7d03bb9349747a
Author: Csaba Henk <csaba@zresearch.com>
Date:   Tue Apr 7 02:14:20 2009 +0200

    niftify mount(8) output for glusterfs mounts
    
    Originally, mount(8) shows a glusterfs mount like this:
    
    glusterfs on <mp> type fuse
    
    With this patch, mount(8) will show a glusterfs mount like this:
    
    <volfile> on <mp> type fuse.glusterfs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8123c907015e6ad6e2975ba77eadd4db32e08628
Author: Harshavardhana <harsha@zresearch.com>
Date:   Tue Apr 7 00:43:23 2009 -0700

    Commit package making files for FreeBSD and Solaris platform.
    
    Commit for package making related files for FreeBSD and Solaris. These files
    are supposed to be in repository to not loose track and update them as needed.
    I will update them soon for upcoming release where we support Solaris on
    ib fabric also.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b976536e616e6dd23dd4a3981d150b168f9d2bef
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:43:31 2009 -0700

    libglusterfsclient: Complete support for rmdir fop
    
    glusterfs_rmdir code path wasnt implemented completely. Here is an
    attempt to complete it.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ca32040f350a7b8ad2e24ee68b417d6bec266038
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:42:14 2009 -0700

    libglusterfsclient: Create new directory inode
    
    Make sure we give an allocated inode in the loc so that the underlying
    callbacks are able to fill it with the relevant information about the
    directory being created.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 364af2266e9cd9d1f4d88763e61a5b28d1336414
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:41:50 2009 -0700

    libglusterfsclient: Return ENOENT on missing ancestor component
    
    If any of the path's components, except the basename, are missing
    from the dentry cache and the corresponding lookup from the server
    also fails, return an ENOENT.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 353f30ad17c9ace576df47abedf71054d8eb434e
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:40:12 2009 -0700

    libglusterfsclient: Return EEXIST on lookup success in glusterfs_mkdir
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 957ae7ba2ba7b8276dab963b7af7dbf16eeb5888
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:36:57 2009 -0700

    libglusterfsclient: Perform explicit create
    
    We must create the file based on the O_CREATE in the flags
    instead of depending on the return status of the lookup.
    This works because we've already handled O_EXCL earlier and
    also handled a missing file(ENOENT)
    in case this was actually an open and not create.
    Adapted from Raghu's original patch.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d4ab91b1f254a21cac538fdffa7ff37db10ae83c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:35:32 2009 -0700

    libglusterfsclient: Handle O_CREAT on lookup failure
    
    On lookup failure, if O_CREAT is required, then we must:
    
    1. explicitly lookup the parent directory.
    2. create a new inode for the new file being opened.
    
    This special case is required for file creation because:
    1. We cannot depend on the previous lookup to have reliably looked up
    the parent inode.
    
    2. inode for the new file does not exist in the itable.
    
    Patch adapted from Raghu's original fix.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e8282fd242ba4061a40b992ebe4549b4dd23fa11
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:34:56 2009 -0700

    libglusterfsclient: Dont depend on ENOENT
    
    Dont depend on the dentry and explicit lookup function, i.e.
    libgf_client_path_lookup(..), to return ENOENT on not
    finding a dentry. Just use op_ret = -1 as a lookup failure
    status.
    Patch adapted from Raghu's original fix.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ccbb9c7df1d887bc835a04e0f76799770ba3e2b8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:34:24 2009 -0700

    libglusterfsclient: Remove spurious strcmp
    
    This strcmp existed because of assumptions that do
    not hold true since the change in libglusterfsclient
    internals recently.
    
    This is another step in fixing the seg-fault on glusterfs_create.
    Patch adapted from Raghu's original fix to the problem.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2524bf2e9cb89627833b1120eac0f78b279c1751
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:33:56 2009 -0700

    libglusterfsclient: Resolve path on empty caches
    
    The earlier case was that the explicit lookups to the server
    were being sent only when the parent inode was NULL. This situation
    breaks when the parent inode is available in the i- or d-cache
    but the child dirent is not. In such a case, no explicit lookups
    were being sent to get the missing child dirent.
    
    Now, explicit path lookup happens even if the inode for parent or basename
    is not found in the caches.
    
    This also fixes a seg-fault occuring during glusterfs_open, in my test
    case, but one that could occur almost anywhere lookup code is used.
    Patch adapted from Raghu's original patch.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 47f03734685076fce51eaacb706796d2213bdbf1
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Apr 7 05:32:47 2009 -0700

    libglusterfsclient: Fix segfault in glusterfs_open
    
    libgf_client_loc_fill gets passed a name=NULL argument.
    So when this function returns the filled loc argument, this loc
    is actually missing the inode structure that was to be filled.
    
    The segfault actually occurs a few lines later when
    we try to access fd->flags but fd returned by fd_create is NULL
    because we'd passed a NULL inode to it, i.e. the loc->inode.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 07fcdfebf25c30811a9313ac3d9a0fdbbceaad6c
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Wed Apr 8 04:24:22 2009 +0530

    introduction of secondary index database in storage/bdb
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit abf35ff6c7a2cc94d9e1e738fb76f711bd2abc16
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Wed Apr 8 04:24:00 2009 +0530

    link() & rename() on storage/bdb will always return EXDEV.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8fea700263bd356e6ecacd3dabc9a9c00043a804
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Wed Apr 8 04:23:30 2009 +0530

    storage/bdb untabify, code alignment to limit to 80 characters per line.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 34ae34826cce3233402bf36cd6f0174be06a83dc
Author: Amar Tumballi <amar@gluster.com>
Date:   Tue Apr 7 17:38:07 2009 -0700

    map translator cleanup.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4e90ca853b774f64c6adde73a62ed2649bda5eab
Author: Vikas Gorur <vikas@gluster.com>
Date:   Wed Apr 8 02:30:18 2009 -0700

    Fix minor bug in afr_open_cbk.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 225e86b37492e5004eb51498b46471d74f30841d
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 3 02:06:52 2009 -0700

    io-threads: Refactor un-ordered worker exit path
    
    This is being done for the same reason as the
    previous refactoring for ordered threads.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fe1cedc1a960493337676885881018e4687c12a2
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Fri Apr 3 02:06:25 2009 -0700

    io-threads: Refactor ordered worker exit path
    
    This patch re-factors the exit path of an ordered worker
    on a time-out. Earlier we're checking for exit permission
    in such a way that required us to release and acquire
    the worker lock a second time in the worker loop opening
    a window wherein a new request could've been appended to the
    request queue.
    
    This patch makes the decision to exit while still holding on to the
    worker lock.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3acd56bec5afef9db673ae8d7dbe52bc7943b298
Author: Csaba Henk <csaba@zresearch.com>
Date:   Mon Apr 6 21:25:12 2009 +0200

    add .gitignore
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5634986f594fe75d0cd2e69cadf002a2c701f366
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 7 06:55:43 2009 -0700

    Fix in changelog logic.
    
    If a writev fails, remember it by marking it in the fd context.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d46684117a02359886e096d1bcc9f590b54144a6
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 7 06:55:15 2009 -0700

    Consider a subvolume dead if an fop fails on it
    
    Transaction fops earlier called afr_transaction_child_died only
    if an fop failed due to ENOTCONN or EBADFD. Now they consider a child
    dead regardless of the reason for failure. This handles cases such
    as ENOSPC.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d71e72248096d12ce2a8ca7ccb36ef97ae486583
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Apr 7 03:27:24 2009 -0700

    Add lock-less versions of fd_ctx_*
    
    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>

commit 27996c714f7fd6a7686f2d4a3552efbc1e54c2c7
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Apr 6 10:27:45 2009 -0700

    Enabling booster after port to work with changed libglusterfsclient interface.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2d59bde99600ecb15b7ebba9cd0283925c9f20f4
Author: Amar Tumballi <amar@gluster.com>
Date:   Mon Apr 6 10:56:52 2009 -0700

    fix to fd leak in posix_create() in case of some failures.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c7962678224374fa295d4063c2f5387c7280536e
Author: Amar Tumballi <amar@gluster.com>
Date:   Thu Apr 2 19:45:04 2009 -0700

    nufa to take care of free disk-space while creating files.
    
    nufa gets awareness about the available free-disk-space in subvolumes.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 258fec70ba2cc588f500f3e3bc16c99af212b4c9
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Apr 6 05:21:29 2009 -0700

    Fix in return value of afr_sh_mark_sources
    
    afr_sh_mark_sources now returns:
      -1   if two wise subvols conflict (split-brain)
       0   if all subvols are innocent (no self-heal needed)
      >0   if sources found
    
    Also, changes to callers of afr_sh_mark_sources to handle return
    value properly.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6b18487d2811b4fb004d0f4c5c98a101a93b35ed
Author: Csaba Henk <csaba@zresearch.com>
Date:   Mon Apr 6 14:03:21 2009 +0200

    bitrot-13 fix
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7a543c3b45139adce1189785200ad23b2ec867d2
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Apr 6 04:00:59 2009 -0700

    Fix an incorrect type-cast in libglusterfsclient.c
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 258da6cd992c279469f2288f8a3cd41be69d43c2
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 6 00:37:54 2009 -0700

    io-threads: Cleaner stub destruction
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 45dab1eefd85e38570c2c3ccfac0061245f70e74
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Apr 6 00:25:51 2009 -0700

    io-threads: Sanity check worker thread idx
    
    This patch adds sanity check for the ordered worker thread index
    returned from the inode's context. If the index is corrupted we
    STACK_UNWIND with ECANCELED.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fed1aa318dcf939326b955a8fcc2da2b1535acb9
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Apr 3 22:13:53 2009 +0530

    disabling booster

commit 8a5005ecf06f23f1607c0ff4111a21c00bd74205
Author: Amar Tumballi <amar@gluster.com>
Date:   Fri Apr 3 08:27:44 2009 -0700

    distribute to take care of available disk space while creating new dirs, and files.
    
    distribute gets awareness about disk-space while creating the files
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f235826215205ac626abb0ad475e7a89f7003da5
Author: Rommer <rommer@active.by>
Date:   Wed Mar 18 14:32:50 2009 +0200

    fix broken transport-type unix
    
    fix broken transport-type "unix"
    however unix transport not working with defined transport.socket.bind-path
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7a52d4ba1f1f8b68ecd79b4d5409f3b930b4efd4
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 30 07:25:32 2009 -0700

    libglusterfsclient - reimplement glusterfs_fgetxattr and glusterfs_fsetxattr
    
    - glusterfs_fgetxattr and glusterfs_fsetxattr earlier used lookup and setxattr
        fops for implementation. Change it to use fgetxattr and fsetxattr fops
        instead.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 475a5909f3f80a1fc91630ea22bec228bfdc676b
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 30 07:20:35 2009 -0700

    libglusterfsclient - fix bug in __do_path_resolve
    
    - add argument lookup_basename to __do_path_resolve which indicates whether to
        lookup basename(path). This is necessary for apis like glusterfs_get, which
        dont want basename(path) to be looked up by libgf_client_lookup_path.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 65bd768543c4de3d2ffd8d17efbd79e1e03666a4
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 30 06:33:06 2009 -0700

    libglusterfsclient - move lookup timeout related code to libgf_client_path_lookup
    
    - this simplifies the resolution of path to inode, the apis which receive
         path as argument just need to call libgf_client_path_lookup for
         path->inode translation.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ab534d54e4e2e1eb921c7a3c98d44137471c7ac5
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 30 04:21:59 2009 -0700

    libglusterfsclient - fix indentation
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e60d2194840b78034db1ad5c8b385a691ab3ddb6
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 30 03:57:20 2009 -0700

    libglusterfsclient - change implementation of glusterfs_get
    
    - remove redundent lookups happening in glusterfs_get.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8b8448799cc43f20f5812bf5629c8670f76f78d3
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Mar 25 23:22:55 2009 -0700

    mod_glusterfs/lighttpd/1.4 port and memory leak fixes
    
    - port owing to changes in interface of libglusterfsclient.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 38be3fda5ce27352c45475fc4de442806cbddd36
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Mar 25 23:22:28 2009 -0700

    mod_glusterfs/apache/1.3 port
    
    - port owing to changes in interface of libglusterfsclient.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e600abcb96979f80a0a20074347e8efc6cae880d
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Mar 25 23:22:03 2009 -0700

    mod_glusterfs/apache/2.2 port
    
    - port owing to changes in interface of libglusterfsclient.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cf6f21928dbe3489de5dfdc3513f3be5f5ef529d
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Mar 25 06:52:05 2009 -0700

    libglusterfsclient code changes
    
    - 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>

commit 6eb419f1ca68f536a700e63c1521e428560a0d9d
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Fri Apr 3 06:30:54 2009 -0700

    server-protocol - reimplement connection cleanup to happen in 2 phases
    
    - 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>

commit d3d7245970189629937f6330a6d946f5fbb454af
Author: Vikas Gorur <vikas@gluster.com>
Date:   Fri Apr 3 05:34:10 2009 -0700

    Made afr inode context a 64-bit packed value instead of a structure.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 75c70231fe7e13a68239dac889568d243a79a75e
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 2 08:31:23 2009 -0700

    Load balance read operations among subvolumes in afr
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1e7c9fa93716844e60d41811b8b79f8605a5044c
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 2 08:30:32 2009 -0700

    Defined afr_inode_ctx_t structure.
    
    Notification of a split-brain situation, which was earlier signalled
    by the mere presence of inode context is now signalled by
    the 'split_brain' member in the structure.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9f2ef60274dae8b302d691ba8d266cd76dcd7c4b
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 14:01:05 2009 -0700

    io-threads: Support autoscaling volfile options
    
    This commit finally makes the autoscaling feature visible to the user.
    Know that we're now using two separate thread-pools, one for data
    requests, called ordered thread-pool in io-threads, and the other
    for meta-data requests, called un-ordered thread-pool.
    We do not expose this information to the user to keep io-threads
    simple. Consequently, when the user specifies a min-threads and
    max-threads value, the number of threads assigned to each pool
    is equal, i.e. both pools start with their min threads set to half of
    the option "min-threads" and both scale up their threads at most up to
    half of option "max-threads".
    
    Volfile options will be added to the wiki and user-guide.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b1bbd77f16a13f8109d1e2e1b4ed869db1e86645
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 14:00:36 2009 -0700

    io-threads: Cleanup request queueing,thread firing
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ae53812b2ccfd7842fa6430081465ed90f18814b
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 14:00:06 2009 -0700

    io-threads: Allow scaling to be switched off
    
    The default is also to provide no scaling. For both, ordered and
    unordered request pools, when scaling is off, we maintain atleast the
    minimum number of threads specified in the volfile.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b64fa35870b54b8d9e62afd71c92e35b1f7a4cfd
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:59:43 2009 -0700

    io-threads: Add ordered threadpool state and code
    
    Now we have the remaining fops going through the ordered
    thread-pool.
    
    To route a request through ordered thread, we use
    iot_schedule_ordered(..) and the worker thread for
    ordered requests is iot_worker_ordered(..)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ee79908d3b577c061b497e35481b8d1523502077
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:59:24 2009 -0700

    io-threads: Add un-ordered thread-pool.
    
    This commit adds everything needed to:
    
    a. Get un-ordered request going through the un-ordered
    thread-pool. This happens through, the
    iot_schedule_unordered(..). The unordered thread-pool
    consists of thread running the iot_worker_unordered(..)
    function.
    
    b. Make threads in the un-ordered thread pool start-up
    and exit depending on the thread state.
    
    Note that at this point the requests that need
    ordering are still going through iot_schedule(..).
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e27f7f344e12d0885a48fcca8dfce36440f5e9e8
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:58:49 2009 -0700

    io-threads: Classify requests for threadpool type
    
    New io-threads will serve requests through two separate
    threadpools.
    
    One thread pool for requests that must be ordered
    on a file that is open. so that the server can process the requests
    in the order they were entered in the requests queue, and not in the order
    the io-thread is able to send a request, which in turn is determined
    by how the thread gets scheduled. This can also be called the
    data-intensive ops thread pool.
    
    Second thread-pool for requests that dont care about ordering, i.e.
    requests like lookup, open, create, mkdir, etc.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 42df79e2ad14053f38a12f30b29b81dd897921c9
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:58:30 2009 -0700

    io-threads: Wire in support for rename fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 369476e93e4ab99234602a5bbe2070d734b45567
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:58:11 2009 -0700

    io-threads: Wire in support for symlink fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6afeb9dd1bb9f329b5b0508d49c2e5142c6fc8cc
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:57:51 2009 -0700

    io-threads: Wire in support for rmdir fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 21363da2935615b5574cce597c95a8a7b0503766
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:57:34 2009 -0700

    io-threads: Wire in support for mkdir fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cbf8858a230b91174dc6134e4729a047db6ff914
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:57:18 2009 -0700

    io-threads: Wire in support for mknod fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ef73c3de6097c6114b5492d5972c257b849e10b7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:56:50 2009 -0700

    io-threads: Wire in support for readlink fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d767455020f9730793230a14cd9e795194c5257f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:56:27 2009 -0700

    io-threads: Wire in support for access fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit eab231f3596aa4b6ad2b9b8f3d1a4cc97bda76bc
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:56:04 2009 -0700

    io-threads: Wire in support for fchown fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3ca0a7859f6f8f7ebc6ac32b6f17035f2115d2a0
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:55:44 2009 -0700

    io-threads: Wire in support for chown
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d56683ccfa1b53c42717ff36490066cff25fd7d0
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:55:19 2009 -0700

    io-threads: Wire in support for fchmod fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f05ca55ef77fb2004b0f573aa267c92405166d9c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:54:52 2009 -0700

    io-threads: Wire in support for chmod fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit dffa5a92c70732e790b6c789e2aacb7f8c5c34cc
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Wed Apr 1 13:54:33 2009 -0700

    io-threads: Wire in support for lookup fop
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b91e83aa0d3891b4cd725b6044131096405dfba8
Author: Anand V. Avati <avati@gluster.com>
Date:   Thu Apr 2 16:37:37 2009 +0530

    wb_flush - keep reference on fd for process_frame to perform STACK_WIND of flush.
    
    This patch fixes bug report by Greg <greg@easyflirt.com> on gluster-users@ with subject 'glusterfsd crash'
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f2cdc5d10c56ef8010ab83acf31b3fb6c4c2fd1f
Author: Anand V. Avati <avati@gluster.com>
Date:   Thu Apr 2 16:49:37 2009 +0530

    change char to int in execute_cmd (based on comment on #26006 from Giorgio Marinelli <gio@reversiva.net>
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1e9b5a5a35e8d53e631788443dadf1fe30853743
Author: Bharat Shetty Barkur <bharat.shetty@gmail.com>
Date:   Thu Apr 2 01:41:55 2009 -0400

    Changed few lines to ensure Optimization (lesser code).
    
    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>

commit aa0fd06dad70a7ecfc3dab819e9b3fab8baad2a9
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Apr 2 02:49:42 2009 -0700

    Build fixes for ib-verbs compilation on solaris
    
    Build fixes for solaris on ib-verbs with recent OFUV Update 3 release.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 63115897fe77e584552624c88f84eaeac55d9b57
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Apr 2 04:05:50 2009 -0700

    unify-self-heal: Fix un-ref'ing of incorrect dict
    
    dict_unref'ing of the dict in local
    results in a crash due to de-referencing a NULL spinlock.
    That is because after a STACK_UNWIND(..), we cannot expect
    the frame->local to be allocated still.
    
    Fix by using the other available reference to local->dict.
    
    Ref: https://savannah.nongnu.org/bugs/?26058
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 26af4e1229106e3d4d311fcfa1646f1ce9f3f271
Author: Vikas Gorur <vikas@gluster.com>
Date:   Thu Apr 2 03:39:24 2009 -0700

    Print log message when AFR receives CHILD_UP/DOWN notification
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 522b2bdb540bef4911e0874030d1f9b3003ba104
Author: Anand V. Avati <avati@gluster.com>
Date:   Thu Apr 2 15:51:34 2009 +0530

    socket_connect() - if socket is already created, do not fail transport_connect() -- causes spurious CHILD_DOWN events to be sent up when reconnect() thread misinterprets the failure of transport_connect() to be an actual teardown of the transport
    
    the spurious CHILD_DOWN events cause self-heal in replicate to not heal files in that subvolume, writev to not modify that subvolume etc, accounting for a lot of discrepencies in replicate which are being in the mailing lists recently.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3acfb275879fb8392f8cb4ea2a58766afbc42baa
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Apr 2 02:50:33 2009 -0700

    Fixes server goes into infinite loop on Solaris when poll_err is not set.
    
    Server goes into infinite loop when poll_err is not set.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cda677a98d039de6381887422d0b482ed412daaf
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 2 06:09:56 2009 +0530

    mount/fuse to silently send fresh lookup for ESTALEd revalidates. log only in DEBUG level.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8e621bdfff915f40d67ed5b2d17914226c601108
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 2 06:09:26 2009 +0530

    cluster/stripe to propogate ESTALE to parent.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2b63980c5da5e82c1a80fe91115fb8d8af201755
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 2 06:08:57 2009 +0530

    cluster/unify propogates ESTALE to parent translator, if any subvolume returns ESTALE during revalidate.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 60615a0a78ab8bc93dd027c1338c588c4f3d49a7
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 2 06:08:17 2009 +0530

    cluster/replicate should propogate the ESTALE error to parent, when at least one subvolume returns ESTALE.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 705c7c9bacafc22b714ac15e3925cb5eaeb45b0a
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 2 06:07:25 2009 +0530

    cluster/{dht,nufa} propogate ESTALE (when at least one subvolume returns ESTALE for revalidate) to parent translator.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e8cce0bed6e5e6bd926ee465c5ec7a00b0b37793
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Apr 2 06:07:04 2009 +0530

    cluster/{nufa,dht} fail revalidates with ESTALE, in case a stale layout is found in inode->ctx.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 905b9fd38a3da787de3f30d1cbdd5e85d56e2f81
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Apr 2 01:10:03 2009 +0530

    Review comment from Krishna was missed out in previous commit of fix for sending first_lookup in 2nd call

commit 25d415e1917df1cac363142fb6fd3768f3e7d2af
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Apr 1 21:54:43 2009 +0530

    use (fgetc() != EOF) instaed of feof() in parser
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 978174fd7362b6c425db78c8d316b96050603844
Author: Amar Tumballi <amar@gluster.com>
Date:   Mon Mar 30 23:36:41 2009 -0700

    Bug fix in posix-init(), when span-devices is set above 1
    
    removed the extra '!' in if statement, which was a typo earlier.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 39d67cbf8921db55e7205a94bce5c6d154a3a3d5
Author: Amar Tumballi <amar@gluster.com>
Date:   Tue Mar 31 15:49:57 2009 -0700

    fix a segfault with io-threads when iot-schedule is called with NULL inode
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit db365c30d07f5faae4197e37148f64e75b54a7ec
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Tue Mar 31 10:56:10 2009 -0700

    Enable glusterfs client to exit after a configured number of failed connects \ while fetching volume specification file from server
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit aa63a122433d51e89148af27dab98cf68846dab4
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Tue Mar 31 11:18:55 2009 -0700

    Avoid infinite loop while parsing volume specification files on Linux/ARM.
    
    - patch submitted by anonymous user (ref: bug #26006 on savannah).
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 96b687b9b8d58fc70dfaaed42dbe1b35799117f8
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Tue Mar 31 06:22:16 2009 -0700

    Add new type of option type INTERNET_ADDRESS for validation
    
    - 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>

commit c8ddd2588ae7d9890b2d30fd1dadc6f9b054d7f4
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Tue Mar 31 12:25:58 2009 +0530

    log message changes in mount/fuse for SETLK, GETLK, GETXATTR, SETXATTR fops
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9922b37658d7d996321382c5157bf33bbbb1330d
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 30 21:14:45 2009 -0700

    Add support for log-level NORMAL in fuse mount helper script.
    
    - patch submitted by John Feuerstein <john@feurix.com>.
      - copying changes in the patch verbatim to
        xlators/mount/fuse/utils/mount.glusterfs.in and
        xlators/mount/fuse/utils/mount_glusterfs.in
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a0c1de7c9cf41d37f95660fe45da66418e263340
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Mar 28 14:17:55 2009 +0530

    first call of fuse is INIT internal call, and not first system call. 2nd call is the system call where first_lookup() has to be done.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3276e650f8af676ed602279f4be85d053aa6065d
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sat Mar 28 00:32:34 2009 +0530

    memory leak (of header) when frame is attempted to be xfer'ed when transport is disconnected
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3baa99ebef316c6a9947c17c6d0c4bca863a8c82
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Mar 27 22:11:31 2009 +0530

    ping-pong timer: - share last_sent and last_received between channels so that any activity ensures the remote host being alive (useful under heavy loads) - timer expiry disconnects both transports
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6c28cb81b2a326a416968932919ea9d19f3b56ab
Author: Anand V. Avati <avati@gluster.com>
Date:   Thu Mar 26 17:29:52 2009 +0530

    fix duplicate setting of values in inode->ctx and fd->ctx
    
    this patch avoids setting of duplicate key/value pairs in the context.
    note that consumers have to explicitly check for previous existance of key
    to avoid any kind of resource leak resulting from this overwrite.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 675e8b4a1f07668a6145c16283b68daa165a7a0c
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Mar 26 08:47:13 2009 -0700

    libglusterfsclient: Fix NULL argument bug
    
    inode_ctx_get was being passed a xlator_t type
    that was initialized to NULL resulting in a
    EINVAL return from glusterfs_fstat.
    
    Reported on gluster-devel
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a59582c3faed3efcf713caeb990ea5c35479dd8d
Author: Anand V. Avati <avati@gluster.com>
Date:   Thu Mar 26 16:26:21 2009 +0530

    posix_unlink - open/unlink/close only regular files
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 36e39bf9cb4b7c712ef411d60203bf05af7e129f
Author: Anand V. Avati <avati@gluster.com>
Date:   Wed Mar 25 18:08:43 2009 +0530

    Enhancements to distribute selfheal
    
    - create missing directories instead of creating linkfiles when
      entry missing  on hashed subvol
    
    - detect cases where there are dirs and linkfiles for a name and
      make them all dirs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a2d44f8cd32988ad52ad924b61a2ef5fc41e4b0e
Author: Csaba Henk <csaba@zresearch.com>
Date:   Wed Mar 25 02:19:14 2009 +0100

    make the location of the mount utility tunable at configure time
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ec5a5fa20823aed3127bdbea4e754ef308d81d89
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Mar 23 05:16:16 2009 -0700

    Fixed typo in warning string in afr.c
    
    Fixed typo.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3df266c278ab74c6bf1980bd17a545595bd04344
Author: Bharat Shetty Barkur <bharat.shetty@gmail.com>
Date:   Sun Mar 22 13:57:37 2009 -0400

    Changed the gf_log warning for return of null via CALLOC from 'old' to 'newdata'
    
    Fixed the warning message to be more clearer for return of the null by CALLOC, by changing old to newdata.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 4e5c297d7c3480d0d3ab1c0c2a184c6a4fb801ef
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Tue Mar 24 03:46:08 2009 -0700

    fix to rm of large file blocking other operations on the same directory containing file (ref: rt #779)
    
    posix_unlink follows the below procedure to avoid client noticing delay during
    unlink of large file
    1. open file
    2. unlink file
    3. stack_unwind
    4. close file
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6e8017479fd9997ae47e7c8cbb74247d7e2b4fd0
Author: Vikas Gorur <vikas@gluster.com>
Date:   Tue Mar 24 05:44:59 2009 -0700

    Made self heal logic more precise.
    
    Discard earlier patch sent for the same error. This patch fixes
    it more comprehensively.
    
    This solves the spurious split-brain seen by many users.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8f590ad883c170827cc06dcbcb17e5aaa1788996
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Mon Mar 23 23:45:53 2009 -0700

    dht memory leak fix
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 270621b34af7528755373e04b07f959c8dca274b
Author: Amar Tumballi <amar@gluster.com>
Date:   Sat Mar 21 19:04:15 2009 -0700

    fixes crash in write-behind
    
    in wb_flush, there was a chance that wb_process_queue()
    was called with NULL frame, which causes crash.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 617fa2504283b63dde7f27186648ef9a9f060f52
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Fri Mar 20 12:50:51 2009 -0700

    when the both channels in client protocol is disconnected, fd's are marked as bad
    
    patch solves the problem of fds being valid even in the case of server
    disconnection, which causes operations on wrong fd when server comes back up.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cf15c8ab0fab3ad9e37cab544ccbbccd59ab03db
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Fri Mar 20 12:49:12 2009 -0700

    fixes issue of hashing to wrong subvolumes in case when a subvolume is down
    
    When a hashed subvolume is down, variable 'subvol' was NULL, but was sent to itransform.
    This patch solves this, and readdir is sent to proper subvolume now.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c20359b5b2a564e83b5830b9a17013e780096e2d
Author: Amar Tumballi <amar@gluster.com>
Date:   Wed Mar 18 18:31:30 2009 -0700

    fixed sys_<fops> related warnings. (on mac os x and opensolaris)
    
    The fix in posix will fix 'unresolved' symbol errors in Mac/Solaris/FreeBSD
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 103d82700483bf744f86719e97846b065ca3394c
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Wed Mar 18 17:10:51 2009 +0530

    dht_layout_dir_cmp - if xattr is missing, it is an error only if cached layout has entry for that subvolume.

commit b9fef00edbe7272d31be0ca22f3b2794918300e0
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Tue Mar 17 21:59:30 2009 -0700

    Add return after STACK_UNWIND
    
    We must add a 'return' after a STACK_UNWIND due to a stub creation
    failure, because if we dont, we'll end up adding a NULL stub to the
    worker thread request queue.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2d7f44e39792c71e4f7bb768acffc2f5a76c80e0
Author: Amar Tumballi <amar@gluster.com>
Date:   Tue Mar 17 19:05:43 2009 -0700

    Moving few translators which are not well tested, are in beta stage to 'testing/' directory.
    
    This way, users will be aware which are in 'beta' stage, and we can keep on
    adding new translators (if any) seemlessly to stable codebase and once tested
    can move them to proper places.
    
    To use these translators, everyone will have to prefix 'testing/' to existing
    type of translator (in volumefile)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b947dc7161427b8c84f47b0a97861a36557f5748
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Tue Mar 17 18:15:19 2009 -0700

    ib-verbs recv-size and send-size argument takes SIZET arguments now.
    
    With this patch, to specify recv-size and send-size of ib-verbs to <n>KB, we need not give
    the option as integer value of 'n * 1024' value. This is neater to do deployments.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 0a7f4cfc1c516da573949a9521248744ce97c4e9
Author: Amar Tumballi <amar@gluster.com>
Date:   Tue Mar 17 16:08:10 2009 -0700

    afr data self heal bug fix
    
    fixes the issue of corrupting self-healed copy in AFR
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ac8fe9901b3215c27ef8bc0971bf2bd140bbfcd5
Merge: 8e0453e 1601bb6
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Mar 17 22:38:26 2009 +0530

    Merge branch 'master' of ssh://avati@git.sv.gnu.org/srv/git/gluster

commit 8e0453e615255a5f64777a68d873a6f46262b5b3
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Mar 16 07:05:33 2009 -0700

    IO-threads Cleanup: Remove useless data structures.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit babf82427ce19aee091259b25613c426c696c330
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Mar 16 07:04:21 2009 -0700

    IO-threads Cleanup: Clean-up request scheduling and queueing interface.
    
    This patch does two things:
    
    1. Cleans up the request scheduling and queueing interface so that all
    fops only need to call iot_schedule and not iot_queue and in some
    cases iot_schedule.
    
    2. Till now, we've had open and create calls go through the main
    glusterfsd thread when sending open and create fops. This patch makes
    them also go through the worker threads. But since the open and
    creates requests would not be called with a valid inode number in the
    loc_t, these requests will get assigned to the worker at index 0.
    This will be fixed RSN, when we introduce various techniques of
    distributing the inodes(..not requests..) over the worker threads.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8e3e0e776cc04ad9f840383c4693ee73adc79558
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Mar 16 07:03:02 2009 -0700

    IO-threads Cleanup: Change workers list to dynamically allocated array
    
    Worker threads were represented as a list in iot_conf_t
    which made us traverse the list of workers in order to
    decide which thread gets the request. Now we represent the
    workers as a dynamically allocated array so that we can just index
    into the array to schedule the file.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3a83fdc459a620d5ce0360bcf5fa071118d5430f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Mar 16 07:01:33 2009 -0700

    IO-threads Cleanup: Change request queue into a struct list_head
    
    This patch changes the per-thread request queue from a custom circular
    linked list, into the standard list.h list which is easier to
    understand and has a cleaner interface.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3099d29e8e65554af31927c8f767b9b6103ca58e
Author: Vikas Gorur <vikas@gluster.com>
Date:   Mon Mar 16 04:03:55 2009 -0700

    Add system call abstraction layer
    
    - syscall.c provides platform-independent system calls
    - previous code for this from compat.c removed
    - posix xlator uses new functions from syscall.c
    - solaris_flistxattr added to compat.c
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7d61f9d69309ccb0f9aa787caacfef77bc4e32d2
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu Mar 12 04:41:23 2009 -0700

    write behind preserves order of fops with respect to writes
    
    - the execution order of fops like read, stat, fsync, truncate etc whose results
     are affected by writes, are preserved.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 473d02d1698259b4a0a6c22fdf70071e69c6e987
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Fri Mar 13 01:12:20 2009 +0530

    implement forget for cluster/unify
    
    inode_ctx_put() would set a list allocated on heap and would not be free()ed anywhere.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 215a91c4729bff06899375c02ae1568f24d683a9
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Mar 12 20:29:56 2009 +0530

    unify revalidate should propogate the error from any of the subvolume upto the parent, so that parent sends a fresh lookup.
    
    unify revalidate fails if one of the subvolume returns error.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1601bb69f48b79572789c67d12753fcaa0bd2f24
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu Mar 12 04:41:23 2009 -0700

    write behind preserves order of fops with respect to writes
    
    - the execution order of fops like read, stat, fsync, truncate etc whose results
     are affected by writes, are preserved.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7af8d8edbd8554235348e0f54348edf222c0b46e
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Thu Mar 12 16:21:51 2009 +0530

    Add extra 'volume' parameter to inodelk/entrylk calls
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 31c817836c9c56eca1441b3b6f8b83db41c67f94
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Wed Mar 11 18:57:17 2009 +0530

    xlator.c option validation should check for empty valid options list (for strings).
    
    'if (!opt->value)' always fails as 'value' member is an array of size ZR_OPTION_MAX_ARRAY_SIZE and is always non-null. it should have been 'if (opt->value[0] == NULL)' instead.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b1c6a8507d59d16f9691652703be48f4539ca093
Author: Amar Tumballi <amar@gluster.com>
Date:   Mon Mar 9 22:37:57 2009 -0700

    feature to span the export directory across different mountpoints
    
    This feature enables exported directory containing different mountpoints.
    With, 'option span-devices <n>' where n is number of different mountpoints
    export directories can have, one can enable this feature. By default the
    number will be 1, and the inode scaling won't come into picture.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3b45b4c922a5f5835afa4e9211d64da2c6868633
Author: Krishna Srinivas <krishna@zresearch.com>
Date:   Tue Mar 10 00:00:58 2009 -0700

    ping timer will not timeout if we recently got POLLOUT on the socket i.e if ((cur - (sent|received)) < timeout)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6a70225b69e7c617cb0ff62124b2687a7027c64a
Author: Bharat Shetty Barkur <bharat.shetty@gmail.com>
Date:   Sun Mar 8 12:54:25 2009 -0400

    Fixed two more occurrences of poll_out variables used for logging.
    
    Changed the poll_in variable to poll_out variable at two more places in the code.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d4adb2b0f5e7cd8e91d384f3f9047deab2464647
Author: Harshavardhana <harsha@zresearch.com>
Date:   Mon Mar 9 10:31:53 2009 -0700

    removed word "tla" from last of the remaining files
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 2323b92d9b7b679c84cab64697fc715434e28ac9
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Mar 10 00:27:52 2009 +0530

    failover to any active transport when requested channel is not connected
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ae378b63c0ae93d8077d250de6a035b92bac8697
Author: Harshavardhana <harsha@zresearch.com>
Date:   Mon Mar 9 03:19:31 2009 -0700

    Fixed build problems for init script installation.
    
    Fixed build problem for init scripts (Reported by Krishna and Vikas).
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fdfdd7cf05b7378c879917acb9129d69a407aee9
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Mar 9 16:16:02 2009 +0530

    dht_readdir_cbk - retry on same subvol if no entries match the hash
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5e4e99f4c1aa09b9e323c6fd23fcc3517447a6d7
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Thu Mar 5 07:55:43 2009 -0800

    changing the conversion specifier from 'd' to 'o' while printing st_mode
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 0991858fca6dc93de685e9527fb9ff47d77f616f
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Tue Mar 3 16:00:58 2009 +0530

    added fgetxattr and fsetxattr FOPs
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d092dff9a6e23d5fdef64154b6f3d6211f7482a6
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Thu Mar 5 17:05:35 2009 +0530

    fixed deadlock in io-cache
    
    ioc_create_cbk was holding inode->lock and calling inode_ctx_put,
    which also holds the same lock.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit cb602a1d7d41587c24379cb2636961ab91446f86
Author: Krishna Srinivas <krishna@zresearch.com>
Date:   Tue Mar 3 02:54:20 2009 -0800

    Changed the default transport-timeout to 600
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit eab182e8a8b2f9a89147334f39e51db60aafa953
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Mar 5 02:04:28 2009 +0530

    disable building of user-guide
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 762b1f9aefe07971178e584e288833bf142f402b
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Mar 4 04:00:24 2009 -0800

    code changes in the usage of inode_ctx_get and inode_ctx_put after their implementation is changed to hold inode->lock.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c8340e70f881dbb95d5238e588a7e985f6f04816
Author: Amar Tumballi <amar@gluster.com>
Date:   Tue Mar 3 20:13:45 2009 -0800

    Change to fix the build problems with bison 1.28 (in RHEL 4.6)
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1b51e542b9aa7996e2753a7686c7743ffc8ecefd
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Tue Mar 3 20:10:47 2009 +0530

    inode_ctx_t locks added
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 5ed5ea9bffe018512edc6babff18fd4d44bcdd70
Author: Amar Tumballi <amar@gluster.com>
Date:   Mon Mar 2 15:47:37 2009 -0800

    create fuse thread after setvolume cbk happens, not only in case of success
    
    This patch fixes the 'hang' effect when client protocol fails to authenticate
    to servers (it may be problem with volume file, or server process would have
    not started yet).
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 130ae0dee7f1ed1292c32df52276833a9fa187b2
Author: Amar Tumballi <amar@gluster.com>
Date:   Mon Mar 2 09:16:45 2009 -0800

    changes in patchset and repo version
    
    noticed that if anyone pulls from git repo, the version says 'tla' and
    patchset also shows tla's patch.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit da71d1359c1335997595935dbaa07c5747231861
Author: Harshavardhana <harsha@zresearch.com>
Date:   Sun Mar 1 05:35:18 2009 -0800

    Added proper handling for the init scripts for (Debian, Ubuntu, SuSE, Redhat), SuSE init script also added.
    
    * Init scripts added for Debian, Redhat, SuSE distribution, each are installed
      by checking each distribution specific.
    
    Tested on
    1. Debian, Ubuntu.
    2. Redhat, CentOS.
    3. OpenSUSE.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b29a555c0be1c0db47c290d61f8c4dfe1e6fecbf
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri Feb 27 05:03:50 2009 -0800

    now user-guide.info is built only when "makeinfo" found
    
    user-guide info is built only when "makeinfo" found
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 7d7610007aeb3e31e9d51996a2234659de792a25
Author: Bharat Shetty Barkur <bharat.shetty@gmail.com>
Date:   Mon Mar 2 14:31:39 2009 -0500

    Fixed small error regarding the poll_out variable
    
    Changed the poll_in variable to poll_out variable, so that the logging is relevant to the case of invalid poll_out value.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit fd524dda532a05cb2485935212d1a66f4130256c
Author: Harshavardhana <harsha@zresearch.com>
Date:   Sat Feb 28 01:49:40 2009 -0800

    Fix solaris server segfault in recent "rc3" release.
    
    typecasting from uint64_t directly over pl_inode structure segfaults
    are all the calls from posix-locks.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b6bf3b8d6efb995d4ca7b91ff41709c57753d632
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri Feb 27 10:23:45 2009 -0800

    CALLOC changed to calloc in rdd.c and several other cleanup and moved rdd.c into more appropriate "benchmarking" directory.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 24f80a408cbf5214664efe12466929d50575c963
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri Feb 27 10:23:29 2009 -0800

    Removed unncessary EXTRA_DIST entries and updated benchmarking directory
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b2db5d966f210be72250fb87e513d187d3de7fdd
Author: Harshavardhana <harsha@zresearch.com>
Date:   Fri Feb 27 10:23:08 2009 -0800

    Added /etc/init.d/glusterfsd for rpmbuilds
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3aff44fab8ba7a109bd691b8675dbfd9842237a3
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Fri Feb 27 22:35:25 2009 +0530

    check for fd ctx set in changelog_needed_post_op for flush() in afr
    
    Earlier the check was in afr_flush(), which caused race conditions
    with writev()
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1e5ac91d05e89356ac63fb07cc09bed7a979289f
Author: krishna <krishna@guest-laptop>
Date:   Fri Feb 27 03:31:13 2009 -0800

    send a lookup on root as soon as we get CHILD_UP to fuse.
    
    send a lookup on root as soon as we get CHILD_UP to fuse. This fixes the
    case where some of the fuse versions do not send a lookup on the root
    directory when one of the "sub-dir" or "sub-file" is accessed just after mount.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8462dd88ad3531837ebfccd17a083467faa40227
Author: Amar Tumballi <amar@gluster.com>
Date:   Thu Feb 26 08:09:25 2009 -0800

    volumefile modification awareness to make sure there are no inconsistencies.
    
    Complete (including feature to properly umount) in my sense.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit da9664587d414ba703c46839e3a4831ad3784a19
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Feb 27 10:34:03 2009 +0530

    Skip self-heal when subvolumes are down
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 596b48e14e5797deca35915edb047471d7c15a00
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Feb 27 02:50:48 2009 +0530

    fixing warnings in previous patch (typecasting pointer to long)

commit 0601a2d6631983cbce39982dfcbecae23a4fa629
Merge: 2dbcb3c b4ff0d5
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Fri Feb 27 02:39:49 2009 +0530

    Merge branch 'master' of ssh://avati@git.sv.gnu.org/srv/git/gluster
    
    Conflicts:
    	xlators/features/locks/src/common.c

commit 2dbcb3c79338dc4f4c45c21e4bf62e61e455ae19
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Fri Feb 27 02:14:15 2009 +0530

    reverting nested locks in posix-locks for inodelk
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b4ff0d5c88b886dbe841cdcfdb71ac936522f9c3
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Fri Feb 27 02:14:15 2009 +0530

    reverting nested locks in posix-locks for inodelk
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f097e77ffb386dc73e3639af4a9cd57df0d3d40d
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Fri Feb 27 00:36:23 2009 +0530

    moved dht_hashfn_tea() to libglusterfs/hashfn.c as gf_dm_hashfn() (dm - davies-meyer).
    
    moved dht_hashfn_tea() to libglusterfs/src/hashfn.c as gf_dm_hashfn().
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 3d8bc3cbafa84a46e43e46f69d3e7d617d746012
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Feb 26 21:14:23 2009 +0530

    updated copyright header to extend copyright upto 2009
    
    updated copyright header to include 2009.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6fb7cda0a92b333e9c3861eb35f6f9ae3a1c03a2
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Feb 26 20:47:16 2009 +0530

    removed unnecessary README.git file
    
    removed README.git file
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d3a318973c9613cfef8b1a14256fb5178e417fb0
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Feb 26 20:36:50 2009 +0530

    fd->lock added to protect transactions for accessing and modifying fd->_ctx.
    
    fd->_ctx access and modifications are now protected by fd->lock.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 431617ef19244272797106f2356ef31591e9c7b9
Author: krishna <krishna@guest-laptop>
Date:   Thu Feb 26 06:11:48 2009 -0800

    Layout is sorted on volume names before forming the layout ranges. But when anomalies are to be detected layout is sorted based on "start" of the range (done in the selfheal during lookup).
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit c445012fa990be5dbc0ccbace04187484ccd92f3
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Thu Feb 26 17:51:47 2009 +0530

    protect fd_ctx get/set in afr_transaction and afr.c with locks
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 523d23b94c21cf5cfdfd087409371d9d2dcf25a4
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Thu Feb 26 17:13:25 2009 +0530

    Unset fd_ctx in afr_flush if it is set
    
    If fd_ctx is set, it means pending array needs to be decremented.
    However, flush might be called many times and it used to lead
    to multiple decrements. Fix is to unset fd_ctx on the first flush
    received
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b5377787903109dd5aea408e7b3a8e772b2be4f5
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Feb 26 13:38:33 2009 +0530

    __inode_unlink() should not be sent a NULL inode.
    
    unlink_inode might be NULL in inode_unlink() under the following circumstances:
    1. 'inode' got forget() and was unhashed.
    2. 'inode' was replaced by a new inode object and the new object got forget() or was pruned out of the inode table.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 417dfa48df166bfcd3f8a6da56c189de6e7a6aff
Author: Krishna Srinivas <krishna@zresearch.com>
Date:   Thu Feb 19 12:39:04 2009 -0800

    DHT clean up. Lot of selfheal code is not applicable to newly created directory. Newly created directory will use only relavant part of DHT selfheal code - only for xattr application.
    
    DHT clean up. Lot of selfheal code is not applicable to newly created directory. Newly created directory will use only relavant part of DHT selfheal
    code - only for xattr application.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 029913bbd62ed7e3c3f436afe92ad6bca9dc642c
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Wed Feb 25 00:47:43 2009 -0800

    change MALLOC to malloc
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 6609b1d37bd0254ec0eb068758862a0bb0e78515
Author: Krishna Srinivas <krishna@zresearch.com>
Date:   Tue Feb 24 06:55:39 2009 -0800

    DHT selfheal fix during lookup - create missing directories.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 1d556afdf8bf5459a1ea1a27ed5638d440439666
Author: Krishna Srinivas <krishna@zresearch.com>
Date:   Tue Feb 24 06:53:21 2009 -0800

    Ping timer does not timeout in case there is any activity (cbks) from the server side.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8479df9809107f20df31afb332b8fb6a1931b861
Author: Krishna Srinivas <krishna@zresearch.com>
Date:   Tue Feb 24 06:52:55 2009 -0800

    per frame time out - i.e individual frames are unwound instead of the transport point itself being disconnected. timeout is configured using "transport-timeout".
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit ab7fe2987fb4e2c2bd3158682fbb8c1977a049de
Author: Raghavendra G <raghavendra@zresearch.com>
Date:   Tue Feb 24 02:42:41 2009 -0800

    backtick support enhancement
    
    - text within backtick can span multiple lines
      - check exit status of command after execution
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit d47eb5d681b79b32b838505b6e22c4ab627ba934
Author: Anand V. Avati <avati@gluster.com>
Date:   Mon Feb 23 17:18:53 2009 +0530

    DHT TEA hashfn bugfix
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit f264f69ae96ade536dc6f5b8c1ce2579839d6222
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Mon Feb 23 19:36:26 2009 +0530

    Deleted xattr caching code from posix in anticipation of the xattr-cache translator.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8b1762971f8d18f73fa64a967c4cd2baa13d07fc
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Mon Feb 23 05:48:14 2009 -0800

    RE-SEND: Add braces around critical sections.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a3ed4474de9db5bda606b374f3d8cb1cdbf8a9fb
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Mon Feb 23 02:33:11 2009 -0800

    added lock_notify and lock_fnotify FOPs to everywhere necessary in libglusterfs/*
    
    fixed indentation and resubmitting
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 80066c23da120621f26d83d631e204ab2943d181
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Sun Feb 22 11:29:05 2009 +0530

    posix_releasedir flush fds from xattrcache.
    
    It would have entered cache in setdents.
    
    Proposed fix for: http://zresearch.com/pipermail/gluster-users/2009-February/001621.html
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 8b99865bb1db5e349cfdacc795ca2160a32604e1
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Sat Feb 21 15:27:03 2009 +0530

    removed to 'option cache-size <size>' in example volfiles for io-threads.
    
    io-threads translator does not take 'cache-size' option now. so removed all
    references to 'cache-size' option for performance/io-threads.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit bcd1e26a95ab75f3431be8e71d93eae9b7b6cbf8
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Fri Feb 20 18:09:02 2009 -0800

    default volume file option enhanced in server-protocolg
    
    Noticed that with current codebase, there is no proper method to have a default volume filename to choose in getspec() without printing a *lot* of warning messages. This patch tries to have a proper 'default' behavior.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 869df6de6429bd556215a2a555883cabaa4dca80
Author: Amar Tumballi <amar@gluster.com>
Date:   Sat Feb 21 13:50:01 2009 -0800

    change to make round robin dns work for getspec()
    
    Noticed that if I have just 'socket' and not the address-family, the
    round robin dns for '-s' option doesn't work. Changing it to 'tcp'
    works.
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a7b514ab8ec879a67e5a290743b4be6f0b58de1d
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Feb 19 04:59:29 2009 -0800

    command line and mount/fuse now use float attr/entry timeouts
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit a2131aeafa94d671b0121631922d823c8a7ab988
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Feb 19 04:59:06 2009 -0800

    attritbute and entry timeout values under volume now support float/double values
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit b5e0ee918fdff566e45bb255130b9efa6b8fb7b0
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Feb 19 10:34:28 2009 -0800

    new function gf_string2double for float/double values
    
    fixed warning
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit 9679f8db65de29a40f622c12c2cc538d70b052b2
Author: Harshavardhana <harsha@zresearch.com>
Date:   Thu Feb 19 10:26:17 2009 -0800

    new functions dict_{get,set}_double for float/double value
    
    fixed warning
    
    Signed-off-by: Anand V. Avati <avati@amp.gluster.com>

commit e9ac5f587763b48acc19268ce57e6bfd886a0561
Author: Amar Tumballi <amar@del.gluster.com>
Date:   Fri Feb 20 09:37:13 2009 -0800

    fix to remove ''input' defined but not used' warning in building glusterfs
    
    needed to complete the build scripts without warnings
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 99a1cac632b4325afb95cb7c183721c0a90925d7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Feb 19 05:21:47 2009 -0800

    Reduce iothreads requests queue lock granularity.
    
    iot_queue() and iot_dequeue() functions were using a io-threads
    translator-wide lock which would be contended for by every worker
    thread waiting for IO requests.
    
    This patch reduces the granularity by turning the
    lock into a per-worker lock.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 57957c59cd2925540769ae9cb58029b0125e4ae7
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Feb 19 05:20:41 2009 -0800

    Remove conf->cache_size checks
    
    Since we're not dependent on this io-thread internal state(i.e.
    cache_size and current_size) to rate limit requests, we can remove
    these two data members and code that checks for these.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 6a250d9087014551c5085a534248982b195f819f
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Feb 19 05:25:44 2009 -0800

    Remove dead code.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 91df2dbcb10813d17053f715ae40a50b7499f4bc
Author: Basavanagowda Kanur <gowda@gluster.com>
Date:   Thu Feb 19 19:38:57 2009 +0530

    cluster/ha to handle EBADFD for fd based operations as transport disconnected.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit ed1d91986cdaf0240b4e6a8c920f17b7f2d6d57b
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Thu Feb 19 04:26:47 2009 -0800

    warn on ERANGE error for lgetxattr in posix
    
    (amended to fit in 80 columns)
    
    ERANGE is usually caused by the user reducing the number of AFR's
    children but continues to use the old backend.
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 1c701badce280d8de92a5314881824725deec1e6
Author: Shehjar Tikoo <shehjart@zresearch.com>
Date:   Thu Feb 19 02:26:40 2009 -0800

    Fix the order of CALLOC() args
    
    Fix the order of  CALLOC arguments.
    
    Signed-off-by: Shehjar Tikoo <shehjart@zresearch.com>
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 0bb3a56f246082967f7a89a7ea51638babf514d1
Author: Anand V. Avati <avati@amp.gluster.com>
Date:   Thu Feb 19 02:04:17 2009 -0800

    updated commit.sh
    
    changed commit.sh for git usage
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 9a4bba3a7ad86681abc9d022fd6677f668fdf062
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Thu Feb 19 00:18:28 2009 -0800

    added lock-ahead translator design document
    
    Design document for the lock-ahead translator
    
    Vikas
    
    Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

commit 77adf4cd648dce41f89469dd185deec6b6b53a0b
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Wed Feb 18 17:36:07 2009 +0530

    Added all files

commit f3b2e6580e5663292ee113c741343c8a43ee133f
Author: Vikas Gorur <vikas@zresearch.com>
Date:   Wed Feb 18 17:01:30 2009 +0530

    Initial import
