glusterfs.git/xlators/performance/write-behind/src, branch v3.3.1qa1

performance/write-behind: use pthread_mutex_trylock to hold mutex in statedumps

2012-08-16T05:51:59+00:00

Change-Id: I24c83b1b5e83ef3e38a019043c7fbca13b19ff43
BUG: 841543
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/3815
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

license: dual license under GPLV2 and LGPLV3+

2012-05-11T05:06:16+00:00

Note that the license was not changed in any of the following:
	.../argp-standalone/...
        .../booster/...
        .../cli/...
        .../contrib/...
        .../extras/...
        .../glusterfsd/...
        .../glusterfs-hadoop/...
        .../mod_clusterfs/...
        .../scheduler/...
        .../swift/...

The license was not changed in any of the non-building xlators. The
license was not changed in any of the xlators that seemed — to me — to
be clearly server-side only, e.g. protocol/server

Note too that copyright was changed along with the license; I did
not change the copyright in files where the license did not change.

If you find any errors or ommissions please don't hesitate to let me know.

The complete list of files with the license change is:
	libglusterfs/src/byte-order.h
	libglusterfs/src/call-stub.c
	libglusterfs/src/call-stub.h
	libglusterfs/src/checksum.c
	libglusterfs/src/checksum.h
	libglusterfs/src/circ-buff.c
	libglusterfs/src/circ-buff.h
	libglusterfs/src/common-utils.c
	libglusterfs/src/common-utils.h
	libglusterfs/src/compat-errno.c
	libglusterfs/src/compat-errno.h
	libglusterfs/src/compat.c
	libglusterfs/src/compat.h
	libglusterfs/src/daemon.c
	libglusterfs/src/daemon.h
	libglusterfs/src/defaults.c
	libglusterfs/src/defaults.h
	libglusterfs/src/dict.c
	libglusterfs/src/dict.h
	libglusterfs/src/event-history.c
	libglusterfs/src/event-history.h
	libglusterfs/src/event.c
	libglusterfs/src/event.h
	libglusterfs/src/fd-lk.c
	libglusterfs/src/fd-lk.h
	libglusterfs/src/fd.c
	libglusterfs/src/fd.h
	libglusterfs/src/gf-dirent.c
	libglusterfs/src/gf-dirent.h
	libglusterfs/src/globals.c
	libglusterfs/src/globals.h
	libglusterfs/src/glusterfs.h
	libglusterfs/src/graph-print.c
	libglusterfs/src/graph-utils.h
	libglusterfs/src/graph.c
	libglusterfs/src/hashfn.c
	libglusterfs/src/hashfn.h
	libglusterfs/src/iatt.h
	libglusterfs/src/inode.c
	libglusterfs/src/inode.h
	libglusterfs/src/iobuf.c
	libglusterfs/src/iobuf.h
	libglusterfs/src/latency.c
	libglusterfs/src/latency.h
	libglusterfs/src/list.h
	libglusterfs/src/lkowner.h
	libglusterfs/src/locking.h
	libglusterfs/src/logging.c
	libglusterfs/src/logging.h
	libglusterfs/src/mem-pool.c
	libglusterfs/src/mem-pool.h
	libglusterfs/src/mem-types.h
	libglusterfs/src/options.c
	libglusterfs/src/options.h
	libglusterfs/src/rbthash.c
	libglusterfs/src/rbthash.h
	libglusterfs/src/run.c
	libglusterfs/src/run.h
	libglusterfs/src/scheduler.c
	libglusterfs/src/scheduler.h
	libglusterfs/src/stack.c
	libglusterfs/src/stack.h
	libglusterfs/src/statedump.c
	libglusterfs/src/statedump.h
	libglusterfs/src/syncop.c
	libglusterfs/src/syncop.h
	libglusterfs/src/syscall.c
	libglusterfs/src/syscall.h
	libglusterfs/src/timer.c
	libglusterfs/src/timer.h
	libglusterfs/src/trie.c
	libglusterfs/src/trie.h
	libglusterfs/src/xlator.c
	libglusterfs/src/xlator.h
	libglusterfsclient/src/libglusterfsclient-dentry.c
	libglusterfsclient/src/libglusterfsclient-internals.h
	libglusterfsclient/src/libglusterfsclient.c
	libglusterfsclient/src/libglusterfsclient.h
	rpc/rpc-lib/src/auth-glusterfs.c
	rpc/rpc-lib/src/auth-null.c
	rpc/rpc-lib/src/auth-unix.c
	rpc/rpc-lib/src/protocol-common.h
	rpc/rpc-lib/src/rpc-clnt.c
	rpc/rpc-lib/src/rpc-clnt.h
	rpc/rpc-lib/src/rpc-transport.c
	rpc/rpc-lib/src/rpc-transport.h
	rpc/rpc-lib/src/rpcsvc-auth.c
	rpc/rpc-lib/src/rpcsvc-common.h
	rpc/rpc-lib/src/rpcsvc.c
	rpc/rpc-lib/src/rpcsvc.h
	rpc/rpc-lib/src/xdr-common.h
	rpc/rpc-lib/src/xdr-rpc.c
	rpc/rpc-lib/src/xdr-rpc.h
	rpc/rpc-lib/src/xdr-rpcclnt.c
	rpc/rpc-lib/src/xdr-rpcclnt.h
	rpc/rpc-transport/rdma/src/name.c
	rpc/rpc-transport/rdma/src/name.h
	rpc/rpc-transport/rdma/src/rdma.c
	rpc/rpc-transport/rdma/src/rdma.h
	rpc/rpc-transport/socket/src/name.c
	rpc/rpc-transport/socket/src/name.h
	rpc/rpc-transport/socket/src/socket.c
	rpc/rpc-transport/socket/src/socket.h
	xlators/cluster/afr/src/afr-common.c
	xlators/cluster/afr/src/afr-dir-read.c
	xlators/cluster/afr/src/afr-dir-read.h
	xlators/cluster/afr/src/afr-dir-write.c
	xlators/cluster/afr/src/afr-dir-write.h
	xlators/cluster/afr/src/afr-inode-read.c
	xlators/cluster/afr/src/afr-inode-read.h
	xlators/cluster/afr/src/afr-inode-write.c
	xlators/cluster/afr/src/afr-inode-write.h
	xlators/cluster/afr/src/afr-lk-common.c
	xlators/cluster/afr/src/afr-mem-types.h
	xlators/cluster/afr/src/afr-open.c
	xlators/cluster/afr/src/afr-self-heal-algorithm.c
	xlators/cluster/afr/src/afr-self-heal-algorithm.h
	xlators/cluster/afr/src/afr-self-heal-common.c
	xlators/cluster/afr/src/afr-self-heal-common.h
	xlators/cluster/afr/src/afr-self-heal-data.c
	xlators/cluster/afr/src/afr-self-heal-entry.c
	xlators/cluster/afr/src/afr-self-heal-metadata.c
	xlators/cluster/afr/src/afr-self-heal.h
	xlators/cluster/afr/src/afr-self-heald.c
	xlators/cluster/afr/src/afr-self-heald.h
	xlators/cluster/afr/src/afr-transaction.c
	xlators/cluster/afr/src/afr-transaction.h
	xlators/cluster/afr/src/afr.c
	xlators/cluster/afr/src/afr.h
	xlators/cluster/afr/src/pump.c
	xlators/cluster/afr/src/pump.h
	xlators/cluster/dht/src/dht-common.c
	xlators/cluster/dht/src/dht-common.h
	xlators/cluster/dht/src/dht-diskusage.c
	xlators/cluster/dht/src/dht-hashfn.c
	xlators/cluster/dht/src/dht-helper.c
	xlators/cluster/dht/src/dht-inode-read.c
	xlators/cluster/dht/src/dht-inode-write.c
	xlators/cluster/dht/src/dht-layout.c
	xlators/cluster/dht/src/dht-linkfile.c
	xlators/cluster/dht/src/dht-mem-types.h
	xlators/cluster/dht/src/dht-rebalance.c
	xlators/cluster/dht/src/dht-rename.c
	xlators/cluster/dht/src/dht-selfheal.c
	xlators/cluster/dht/src/dht.c
	xlators/cluster/dht/src/nufa.c
	xlators/cluster/dht/src/switch.c
	xlators/cluster/stripe/src/stripe-helpers.c
	xlators/cluster/stripe/src/stripe-mem-types.h
	xlators/cluster/stripe/src/stripe.c
	xlators/cluster/stripe/src/stripe.h
	xlators/features/index/src/index-mem-types.h ¹
	xlators/features/index/src/index.c ¹
	xlators/features/index/src/index.h ¹
	xlators/performance/io-cache/src/io-cache.c
	xlators/performance/io-cache/src/io-cache.h
	xlators/performance/io-cache/src/ioc-inode.c
	xlators/performance/io-cache/src/ioc-mem-types.h
	xlators/performance/io-cache/src/page.c
	xlators/performance/io-threads/src/io-threads.c
	xlators/performance/io-threads/src/io-threads.h
	xlators/performance/io-threads/src/iot-mem-types.h
	xlators/performance/md-cache/src/md-cache-mem-types.h
	xlators/performance/md-cache/src/md-cache.c
	xlators/performance/quick-read/src/quick-read-mem-types.h
	xlators/performance/quick-read/src/quick-read.c
	xlators/performance/quick-read/src/quick-read.h
	xlators/performance/read-ahead/src/page.c
	xlators/performance/read-ahead/src/read-ahead-mem-types.h
	xlators/performance/read-ahead/src/read-ahead.c
	xlators/performance/read-ahead/src/read-ahead.h
	xlators/performance/symlink-cache/src/symlink-cache.c
	xlators/performance/write-behind/src/write-behind-mem-types.h
	xlators/performance/write-behind/src/write-behind.c
	xlators/protocol/auth/addr/src/addr.c ¹
	xlators/protocol/auth/login/src/login.c ¹
	xlators/protocol/client/src/client-callback.c
	xlators/protocol/client/src/client-handshake.c
	xlators/protocol/client/src/client-helpers.c
	xlators/protocol/client/src/client-lk.c
	xlators/protocol/client/src/client-mem-types.h
	xlators/protocol/client/src/client.c
	xlators/protocol/client/src/client.h
	xlators/protocol/client/src/client3_1-fops.c

¹ Copyright only, license reverted to original

Change-Id: If560e826c61b6b26f8b9af7bed6e4bcbaeba31a8
BUG: 820551
Signed-off-by: Kaleb KEITHLEY 
Reviewed-on: http://review.gluster.com/3304
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

performance/write-behind: queue setattr fop with writes always.

2012-03-27T18:29:05+00:00

stat returned in setattr_cbk can be cached by the kernel. Hence it is
always necessary that we return correct stat, which implies that setattr
should not be out of order with respect to write fops.

Change-Id: I305feeb4802f8a41ffaf032100832cbd65dfc5c1
BUG: 765443
Signed-off-by: Raghavendra G 
Reviewed-on: http://review.gluster.com/3011
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

core: adding extra data for fops

2012-03-22T23:40:27+00:00

with this change, the xlator APIs will have a dictionary as extra
argument, which is passed between all the layers. This can be
utilized for overloading in some of the operations.

Change-Id: I58a8186b3ef647650280e63f3e5e9b9de7827b40
Signed-off-by: Amar Tumballi 
BUG: 782265
Reviewed-on: http://review.gluster.com/2960
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

mempool: adjustments in pool sizes

2012-02-22T12:23:48+00:00

* while creating 'rpc_clnt', the caller knows what would be the ideal
  load on it, so an extra argument to set some pool sizes

* while creating 'rpcsvc', the caller knows what would be the ideal
  load of it, so an extra argument to set request pool size

* cli memory footprint is reduced

Change-Id: Ie245216525b450e3373ef55b654b4cd30741347f
Signed-off-by: Amar Tumballi 
BUG: 765336
Reviewed-on: http://review.gluster.com/2784
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

core: utilize mempool for frame->local allocations

2012-02-21T10:42:09+00:00

in each translator, which uses 'frame->local', we are using
GF_CALLOC/GF_FREE, which would be costly considering the
number of allocation happening in a lifetime of 'fop'. It
would be good to utilize the mem pool framework for xlator's
local structures, so there is no allocation overhead.

Change-Id: Ida6e65039a24d9c219b380aa1c3559f36046dc94
Signed-off-by: Amar Tumballi 
BUG: 765336
Reviewed-on: http://review.gluster.com/2772
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

Honor O_SYNC etc. properly.

2012-02-21T10:25:22+00:00

Change-Id: I3dd90fe230386ad5571c5e639f27460e3d003f0e
BUG: 773100
Signed-off-by: Jeff Darcy 
Reviewed-on: http://review.gluster.com/2626
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

iobuf: use 'iobuf_get2()' to get variable sized buffers

2012-02-20T08:46:27+00:00

added 'TODO' in places where it is missing.

Change-Id: Ia802c94e3bb76930f7c88c990f078525be5459f5
Signed-off-by: Amar Tumballi 
BUG: 765264
Reviewed-on: http://review.gluster.com/388
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

core: add an extra flag to readv()/writev() API

2012-02-14T09:09:02+00:00

needed to implement a proper handling of open flag alterations
using fcntl() on fd.

Change-Id: Ic280d5db6f1dc0418d5c439abb8db1d3ac21ced0
Signed-off-by: Amar Tumballi 
BUG: 782265
Reviewed-on: http://review.gluster.com/2723
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

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