glusterfs.git/xlators/storage/posix/src/posix.h, branch v3.4.0alpha

core: remove all the 'inner' functions in codebase

2012-12-20T07:35:29+00:00

* move 'dict_keys_join()' from api/glfs_fops.c to libglusterfs/dict.c
  - also added an argument which is treated as a filter function if
    required, currently useful for fuse.

* now 'make CFLAGS="-std=gnu99 -pedantic" 2>&1 | grep nested' gives
  no output.

Change-Id: I4e18496fbd93ae1d3942026ef4931889cba015e8
Signed-off-by: Amar Tumballi 
BUG: 875913
Reviewed-on: http://review.gluster.org/4187
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

storage/posix: Make rchecksum O_DIRECT friendly

2012-11-20T08:30:25+00:00

Problem:
When posix-aio is enabled to perform aio fd is set with O_DIRECT
whenever possible in read, writev fops. Rchecksum does not take
this into account. If either offset/size/memory-buf passed to
pread in rchecksum fop is not aligned, pread fails with EINVAL.

Fix:
Before doing pread necessary O_DIRECT manipulation is done when
aio is enabled. Memory buffer passed to pread is now page-aligned.

Test:
1) Create replica volume with aio enabled.
2) dd if=/dev/urandom of=a bs=1M count=1
3) kill one of the bricks in the replica pair
4) dd if=/dev/urandom of=a bs=1M count=1
5) bring back the brick. Self-heal succeeds after the change.

The test above checks both rchecksum, writev fops that were
changed in this patch.

Change-Id: I186099a2854d4864c5b48086ab7bc5f1a7b27313
BUG: 866459
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/4134
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

linux-aio: fixes while setting O_DIRECT flag

2012-10-01T23:39:09+00:00

Linux AIO needs O_DIRECT to be set for effective operation. O_DIRECT
in turn has constraints on when it can work (offset, size alignment)

So use O_DIRECT (unless instructed by application) only when offset
and size alignments match. Else, io_submit() will happen over
non-O_DIRECT fd, effectively blocking till the completion of the IO.

Also fix a multithreading bug where detection/setting of O_DIRECT
for a request was not atomic with io_submit() of that request.

Change-Id: I190017e8bc78217429aff0714dca224cbe6f251d
BUG: 837495
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.org/4006
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Tested-by: Amar Tumballi

All: License message change

2012-09-13T20:19:37+00:00

License message changed for server-side, dual license GPLV2 and LGPLv3+.

Change-Id: Ia9e53061b9d2df3b3ef3bc9778dceff77db46a09
BUG: 852318
Signed-off-by: Varun Shastry 
Reviewed-on: http://review.gluster.org/3940
Tested-by: Gluster Build System 
Reviewed-by: Kaleb KEITHLEY 
Reviewed-by: Anand Avati

libglusterfs/dict: make 'dict_t' a opaque object

2012-09-06T07:34:15+00:00

* ie, don't dereference dict_t pointer, instead use APIs everywhere
* other than dict_t only 'data_t' should be the valid export from dict.h

* added 'dict_foreach_fnmatch()' API
* changed dict_lookup() to use data_t, instead of data_pair_t

Change-Id: I400bb0dd55519a7c5d2a107e67c8e7a7207228dc
Signed-off-by: Amar Tumballi 
BUG: 850917
Reviewed-on: http://review.gluster.org/3829
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

All: License message change

2012-08-28T10:45:06+00:00

The license message is changed to
  Copyright (c) 2008-2012 Red Hat, Inc. 
  This file is part of GlusterFS.

  This file is licensed to you under your choice of the GNU Lesser
  General Public License, version 3 or any later version (LGPLv3 or
  later), or the GNU General Public License, version 2 (GPLv2), in all
  cases as published by the Free Software Foundation.

Change-Id: I07d2b63ed5fbbbd1884f1e74f2dd56013d15b0f4
BUG: 852318
Signed-off-by: Varun Shastry 
Reviewed-on: http://review.gluster.org/3858
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

storage/posix: implement native linux AIO support

2012-07-15T01:09:07+00:00

Configurable via cli with "storage.linux-aio" settable option

Change-Id: I9929e0d6fc1bbc2a0fe1fb67bfc8d15d8a483d3f
BUG: 837495
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.com/3627
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi

storage/posix: Avoid excessive logging in posix.

2012-04-09T17:37:44+00:00

When quota or gsyncd is enabled, the marker translator performs setxattr on
files/directories. If the file/directory is deleted before setxattr, posix gets
an error when it does setxattr and logs it. But its not an error for marker and
it handles the case gracefully. Hence, avoid logging for these keys.

Change-Id: Ic614777399497be92ed1c2b4718d46adfb639d96
BUG: 765498
Signed-off-by: Mohammed Junaid 
Reviewed-on: http://review.gluster.com/3105
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

Introduce new extended attribute: node-uuid

2012-02-23T07:19:44+00:00

Request for trusted.glusterfs.node-uuid returns pathinfo
like string but containing the UUID of glusterd instead
of the backend path for the requested file. This info
is benificial for tasks like parallel rebalance that will
make use of the UUID for data locality.

Change-Id: I766a09cc4a5f63aebd11c73107924a1b29242dcf
BUG: 772610
Signed-off-by: Venky Shankar 
Reviewed-on: http://review.gluster.com/2614
Tested-by: Gluster Build System 
Reviewed-by: Shishir Gowda 
Reviewed-by: Vijay Bellur

core: GFID filehandle based backend and anonymous FDs

2012-01-20T13:03:42+00:00

1. What
--------
This change introduces an infrastructure change in the filesystem
which lets filesystem operation address objects (inodes) just by its
GFID. Thus far GFID has been a unique identifier of a user-visible
inode. But in terms of addressability the only mechanism thus far has
been the backend filesystem path, which could be derived from the
GFID only if it was cached in the inode table along with the entire set
of dentry ancestry leading up to the root.

This change essentially decouples addressability from the namespace. It
is no more necessary to be aware of the parent directory to address a
file or directory.

2. Why
-------
The biggest use case for such a feature is NFS for generating
persistent filehandles. So far the technique for generating filehandles
in NFS has been to encode path components so that the appropriate
inode_t can be repopulated into the inode table by means of a recursive
lookup of each component top-down.

Another use case is the ability to perform more intelligent self-healing
and rebalancing of inodes with hardlinks and also to detect renames.

A derived feature from GFID filehandles is anonymous FDs. An anonymous FD
is an internal USABLE "fd_t" which does not map to a user opened file
descriptor or to an internal ->open()'d fd. The ability to address a file
by the GFID eliminates the need to have a persistent ->open()'d fd for the
purpose of avoiding the namespace. This improves NFS read/write performance
significantly eliminating open/close calls and also fixes some of today's
limitations (like keeping an FD open longer than necessary resulting
in disk space leakage)

3. How
-------

At each storage/posix translator level, every file is hardlinked inside
a hidden .glusterfs directory (under the top level export) with the name
as the ascii-encoded standard UUID format string. For reasons of performance
and scalability there is a two-tier classification of those hardlinks
under directories with the initial parts of the UUID string as the directory
names.

For directories (which cannot be hardlinked), the approach is to use a symlink
which dereferences the parent GFID path along with basename of the directory.
The parent GFID dereference will in turn be a dereference of the grandparent
with the parent's basename, and so on recursively up to the root export.

4. Development
---------------

4a. To leverage the ability to address an inode by its GFID, the technique is
to perform a "nameless lookup". This means, to populate a loc_t structure as:

loc_t {
   pargfid: NULL
   parent: NULL
   name: NULL
   path: NULL
   gfid: GFID to be looked up [out parameter]
   inode: inode_new () result [in parameter]
}

and performing such lookup will return in its callback an inode_t
populated with the right contexts and a struct iatt which can be
used to perform an inode_link () on the inode (without a parent and
basename). The inode will now be hashed and linked in the inode table
and findable via inode_find().

A fundamental change moving forward is that the primary fields in a
loc_t structure are now going to be (pargfid, name) and (gfid) depending
on the kind of FOP. So far path had been the primary field for operations.
The remaining fields only serve as hints/helpers.

4b. If read/write is to be performed on an inode_t, the approach so far
has been to: fd_create(), STACK_WIND(open, fd), fd_bind (in callback) and
then perform STACK_WIND(read, fd) etc. With anonymous fds now you can do
fd_anonymous (inode), STACK_WIND (read, fd). This results in great boost
in performance in the inbuilt NFS server.

5. Misc
-------
The inode_ctx_put[2] has been renamed to inode_ctx_set[2] to be consistent
with the rest of the codebase.

Change-Id: Ie4629edf6bd32a595f4d7f01e90c0a01f16fb12f
BUG: 781318
Reviewed-on: http://review.gluster.com/669
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati