glusterfs.git/libglusterfs, branch v4.0.0rc0

gfapi : New APIs have been added to use lease feature in gluster

2018-02-01T11:39:52+00:00

Following APIs glfs_h_lease(), glfs_lease() added, so that gfapi applications
can set and get lease which enables more efficient client side caching.

Updates: #350
Change-Id: Iede85be9af1d4df969b890d0937ed0afa4ca6596
Signed-off-by: Poornima G 
Signed-off-by: Soumya Koduri 
Signed-off-by: Jiffin Tony Thottan

build: use libtirpc by default, even if ipv6 is not the default

2018-01-30T18:36:28+00:00

Another error snuck in with Change-Id I86f847dfd, or more
accurately I think, with Change-Id: Ic47065e9c2...

All libs, not just libgfrpc, need to be linked with libtirpc,
especially on systems that still have xdr functions in (g)libc
where you will get a mixture of calls to libtirpc functions
and glibc functions, with catas

Change-Id: I97dc39c7844f44c36fe210aa813480c219e1e415
BUG: 1538723
Signed-off-by: Kaleb S. KEITHLEY

dentry fop serializer: added new server side xlator for dentry fop serialization

2018-01-30T18:36:01+00:00

Problems addressed by this xlator :

[1]. To prevent race between parallel mkdir,mkdir and lookup etc.

Fops like mkdir/create, lookup, rename, unlink, link that happen on a
particular dentry must be serialized to ensure atomicity.

Another possible case can be a fresh lookup to find existance of a path
whose gfid is not set yet. Further, storage/posix employs a ctime based
heuristic 'is_fresh_file' (interval time is less than 1 second of current
time) to check fresh-ness of file. With serialization of these two fops
(lookup & mkdir), we eliminate the race altogether.

[2]. Staleness of dentries

This causes exponential increase in traversal time for any inode in the
subtree of the directory pointed by stale dentry.

Cause :  Stale dentry is created because of following two operations:

      a. dentry creation due to inode_link, done during operations like
         lookup, mkdir, create, mknod, symlink, create and
      b. dentry unlinking due to various operations like rmdir, rename,
         unlink.

       The reason is __inode_link uses __is_dentry_cyclic, which explores
       all possible path to avoid cyclic link formation during inode
       linkage. __is_dentry_cyclic explores stale-dentry(ies) and its
       all ancestors which is increases traversing time exponentially.

Implementation : To acheive this all fops on dentry must take entry locks
before they proceed, once they have acquired locks, they perform the fop
and then release the lock.

Some documentation from email conversation:
[1] http://www.gluster.org/pipermail/gluster-devel/2015-December/047314.html

[2] http://www.gluster.org/pipermail/gluster-devel/2015-August/046428.html

With this patch, the feature is optional, enable it by running:

 `gluster volume set $volname features.sdfs enable`

Also the feature is tested for a month without issues in the
experiemental branch for all the regression.

Change-Id: I6e80ba3cabfa6facd5dda63bd482b9bf18b6b79b
Fixes: #397
Signed-off-by: Sakshi Bansal 
Signed-off-by: Amar Tumballi 
Signed-off-by: Sunny Kumar

libglusterfs: Reset errno before call

2018-01-23T18:08:27+00:00

This was causing Gluster to return a failure when testing on Centos7.

BUG: 1536913
Change-Id: Idb90baef05058123a7f69e94a51dd79abd371815
Signed-off-by: Nigel Babu

libgfapi: Add new api for supporting mandatory-locks

2018-01-22T09:54:02+00:00

The current API for byte-range locks [glfs_posix_lock()] doesn't
allow applications to specify whether it is advisory or mandatory
type locks. This particular change is to introduce an extended
byte-range lock API with an additional argument for including
the byte-range lock mode to be one among advisory(default) or
mandatory. Patch also includes a gfapi test case which make use
of this new api to acquire mandatory locks.

Ref: https://github.com/gluster/glusterfs-specs/blob/master/done/GlusterFS%203.8/Mandatory%20Locks.md

Change-Id: Ia09042c755d891895d96da857321abc4ce03e20c
Updates #393
Signed-off-by: Anoop C S

md-cache: Implement dynamic configuration of xattr list for caching

2018-01-22T04:10:52+00:00

Currently, the list of xattrs that md-cache can cache is hard coded
in the md-cache.c file, this necessiates code change and rebuild
everytime a new xattr needs to be added to md-cache xattr cache
list.

With this patch, the user will be able to configure a comma
seperated list of xattrs to be cached by md-cache

Updates #297

Change-Id: Ie35ed607d17182d53f6bb6e6c6563ac52bc3132e
Signed-off-by: Poornima G

protocol: make on-wire-change of protocol using new XDR definition.

2018-01-19T17:18:39+00:00

With this patchset, some major things are changed in XDR, mainly:

* Naming: Instead of gfs3/gfs4 settle for gfx_ for xdr structures
* add iattx as a separate structure, and add conversion methods
* the *_rsp structure is now changed, and is also reduced in number
  (ie, no need for different strucutes if it is similar to other response).
* use proper XDR methods for sending dict on wire.

Also, with the change of xdr structure, there are changes needed
outside of xlator protocol layer to handle these properly. Mainly
because the abstraction was broken to support 0-copy RDMA with payload
for write and read FOP. This made transport layer know about the xdr
payload, hence with the change of xdr payload structure, transport layer
needed to know about the change.

Updates #384

Change-Id: I1448fbe9deab0a1b06cb8351f2f37488cefe461f
Signed-off-by: Amar Tumballi

gfapi : added glfs_setfsleaseid() for setting lease id

2018-01-19T09:27:40+00:00

A new function glfs_setfsleaseid() added in gfapi. Currently lock owner
is saved in the thread context. Similarly the leaseid attribute can be
saved using glfs_setfsleaseid().

Updates: #350
Change-Id: I55966cca01d0f2649c32b87bd255568c3ffd1262
Signed-off-by: Poornima G 
Signed-off-by: Soumya Koduri 
Signed-off-by: Jiffin Tony Thottan

cluster/afr: Adding option to take full file lock

2018-01-19T00:15:19+00:00

Problem:
In replica 3 volumes there is a possibilities of ending up in split
brain scenario, when multiple clients writing data on the same file
at non overlapping regions in parallel.

Scenario:
- Initially all the copies are good and all the clients gets the value
  of data readables as all good.
- Client C0 performs write W1 which fails on brick B0 and succeeds on
  other two bricks.
- C1 performs write W2 which fails on B1 and succeeds on other two bricks.
- C2 performs write W3 which fails on B2 and succeeds on other two bricks.
- All the 3 writes above happen in parallel and fall on different ranges
  so afr takes granular locks and all the writes are performed in parallel.
  Since each client had data-readables as good, it does not see
  file going into split-brain in the in_flight_split_brain check, hence
  performs the post-op marking the pending xattrs. Now all the bricks
  are being blamed by each other, ending up in split-brain.

Fix:
Have an option to take either full lock or range lock on files while
doing data transactions, to prevent the possibility of ending up in
split brains. With this change, by default the files will take full
lock while doing IO. If you want to make use of the old range lock
change the value of "cluster.full-lock" to "no".

Change-Id: I7893fa33005328ed63daa2f7c35eeed7c5218962
BUG: 1535438
Signed-off-by: karthik-us

rpc/*: auth-header changes

2018-01-17T06:00:39+00:00

Introduce another authentication header which can now send more data.
This is useful because this data can be common for all the fops, and
we don't need to change all the signatures.

As part of this, made rpc-clnt.c little more modular to support multiple
authentication structures.

stack.h changes are placeholder for the ctime etc, can be moved later
based on need.

updates #384

Change-Id: I6111c13cfd2ec92e2b4e9295896bf62a8a33b2c7
Signed-off-by: Amar Tumballi