glusterfs.git/geo-replication, branch v4.0.0-2

geo-rep: Remove unused working directory check in gsyncd

2018-01-30T18:36:10+00:00

To append the default config file path, gsyncd calls gluster
command to get the workdir path and constructs config file path.
This is not required now since the Config management in Geo-replication
is changed with patch 18257(Issue #73)

BUG: 1539701
Change-Id: Ia7eb39e36ed59ece4de65ea7ec71a0f615e338bb
Signed-off-by: Aravinda VK 
(cherry picked from commit 596143a286079338c30c8abc4b862f8d6ddddb3a)

geo-rep: Detailed JSON output for config

2018-01-29T13:51:01+00:00

JSON output of `config-get` command now returns in the following
format

    {
        "name": CONFIG_NAME,
        "value": CONFIG_VALUE,
        "default_value": DEFAULT_VALUE,  # Only if modified == true
        "configurable": true|false,
        "modified": true|false
    }

Change-Id: I6193de48cd33655df7ecef5a0d83d7cb147089cf
Fixes: #361
Signed-off-by: Aravinda VK 
(cherry picked from commit 5d3c90d14839fc134580a4ff944d68f3ff3c605a)

geo-rep: Support for using Volinfo from Conf file

2018-01-23T03:03:01+00:00

Once Geo-replication is started, it runs Gluster commands to get Volume
info from Master and Slave. With this patch, Georep can get Volume info
from Conf file if `--use-gconf-volinfo` argument is specified to monitor

Create a config(Or add to the config if exists) with following fields

    [vars]
    master-bricks=NODEID:HOSTNAME:PATH,..
    slave-bricks=NODEID:HOSTNAME,..
    master-volume-id=
    slave-volume-id=
    master-replica-count=
    master-disperse_count=

Note: Exising Geo-replication is not affected since this is activated
only when `--use-gconf-volinfo` is passed while spawning `gsyncd
monitor`

Tiering support is not yet added since Tiering + Glusterd2 is still
under discussion.

Fixes: #396
Change-Id: I281baccbad03686c00f6488a8511dd6db0edc57a
Signed-off-by: Aravinda VK

geo-rep: Improve geo-rep pre-validation logs

2018-01-22T06:33:48+00:00

Geo-rep runs gverify.sh which does pre-validation.
As part of it, master and slave volume is mounted
to verify the size. If for some reason, the mount
fails, the error message does not point out the
mount log file location. Also both master and
slave mount logs are same.

Patch does following improvements.

1. Master and slave mount logs are separated and
   error message points the log file to be looked for.
2. The log location is changed to /var/log/glusterfs/geo-replication
   instead of /var/log/glusterfs/geo-replication-slaves
3. The log file name is changed to "gverify-mastermnt.log" and
   "gverify-slavemnt.log" for master and slave mount respectively

Fixes: #395
Change-Id: Ia644ec0afebbdaae92e01adf03c635e5f8866a02
Signed-off-by: Kotresh HR

geo-rep: Validate availability of gluster binary on slave

2018-01-19T03:53:24+00:00

1. Adds validation to check if gluster binary is available on slave
2. Add a simple geo-rep setup test case to verify whether setup is fine.
   It's named in such a way that it runs first.

BUG: 1532591
Change-Id: Ie777e55ae13db8fa97d4e32464ad82269ee5fd07
Signed-off-by: Kotresh HR

tests: Enable geo-rep test cases

2018-01-05T07:08:10+00:00

This patch re-enables the geo-rep test cases.
Along with it does following optimizations.

1. Use EXPECT_WITHIN instead of sleep
2. Clean up geo-rep ssh key after test
3. Changes to gverify.sh and S56glusterd-geo-rep-create-post.sh
   to use the given ssh identity file for geo-rep create
4. Make gluster-command-dir configurable and introduce
   slave-gluster-command-dir which points the parent directory
   of gluster binaries in master and slave respectively.

Change-Id: Ia7696278d9dd3ba04224dcd7c3564088ca970b04
BUG: 1480491
Signed-off-by: Kotresh HR

geo-rep: Log message improvements

2017-12-28T14:49:49+00:00

BUG: 1529480
Change-Id: If4775ed9886990c0e1bcf4e44c7dfef95cc4f0c3
Signed-off-by: Aravinda VK

fips/geo-rep: Replace MD5 with SHA256

2017-12-22T15:32:06+00:00

MD5 is not fips compliant. Hence replacing
with SHA256.

NOTE:
The hash is used to form the ctl_path for the ssh connection.
The length of ctl_path for ssh connection should not be > 108.
ssh fails with ctl_path too long if it is so. But when rsync
is piped to ssh, it is not taking > 90. rsync is failing with
error number 12. Hence using first 32 bytes of hash. Hash
collision doesn't matter as only one sock file is created
per directory.

Change-Id: I58aeb32a80b5422f6ac0188cf33fbecccbf08ae7
Updates: #230
Signed-off-by: Kotresh HR

geo-rep: Cleanup stale unprocessed xsync changelogs

2017-12-11T06:48:53+00:00

Fixes: #376

Change-Id: Ib92920c716c7d27e1eeb4bc4ebaf3efb48e0694d
Signed-off-by: Kotresh HR

geo-rep: Fix access-mount geo-rep config

2017-11-30T06:32:37+00:00

Fix access-mount and slave-access-mount
configs.

Change-Id: Ib586677755e76a51b9f20093e441b72789b4fecc
Signed-off-by: Kotresh HR 
BUG: 1517633