geo-rep: Status Enhancements

Discussion in gluster-devel
http://www.gluster.org/pipermail/gluster-devel/2015-April/044301.html

MASTER NODE - Master Volume Node
MASTER VOL - Master Volume name
MASTER BRICK - Master Volume Brick
SLAVE USER - Slave User to which Geo-rep session is established
SLAVE - <SLAVE_NODE>::<SLAVE_VOL> used in Geo-rep Create command
SLAVE NODE - Slave Node to which Master worker is connected
STATUS - Worker Status(Created, Initializing, Active, Passive, Faulty,
         Paused, Stopped)
CRAWL STATUS - Crawl type(Hybrid Crawl, History Crawl, Changelog Crawl)
LAST_SYNCED - Last Synced Time(Local Time in CLI output and UTC in XML output)
ENTRY - Number of entry Operations pending.(Resets on worker restart)
DATA - Number of Data operations pending(Resets on worker restart)
META - Number of Meta operations pending(Resets on worker restart)
FAILURES - Number of Failures
CHECKPOINT TIME - Checkpoint set Time(Local Time in CLI output and UTC
                  in XML output)
CHECKPOINT COMPLETED - Yes/No or N/A
CHECKPOINT COMPLETION TIME - Checkpoint Completed Time(Local Time in CLI
                             output and UTC in XML output)

XML output:
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
cliOutput>
  geoRep>
      volume>
        name>
        sessions>
          session>
             session_slave>
             pair>
                master_node>
                master_brick>
                slave_user>
                slave/>
                slave_node>
                status>
                crawl_status>
                entry>
                data>
                meta>
                failures>
                checkpoint_completed>
                master_node_uuid>
                last_synced>
                checkpoint_time>
                checkpoint_completion_time>

BUG: 1212410
Change-Id: I944a6c3c67f1e6d6baf9670b474233bec8f61ea3
Signed-off-by: Aravinda VK <avishwan@redhat.com>
Reviewed-on: http://review.gluster.org/10121
Tested-by: NetBSD Build System
Reviewed-by: Kotresh HR <khiremat@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>

1 files changed, 15 insertions, 10 deletions

diff --git a/geo-replication/syncdaemon/gsyncd.py b/geo-replication/syncdaemon/gsyncd.py
index b9ee5aec8c7..32e4eb7828d 100644
--- a/geo-replication/syncdaemon/gsyncd.py
+++ b/geo-replication/syncdaemon/gsyncd.py
@@ -27,12 +27,13 @@ from ipaddr import IPAddress, IPNetwork
 
 from gconf import gconf
 from syncdutils import FreeObject, norm, grabpidfile, finalize
-from syncdutils import log_raise_exception, privileged, update_file
+from syncdutils import log_raise_exception, privileged
 from syncdutils import GsyncdError, select, set_term_handler
 from configinterface import GConffile, upgrade_config_file
 import resource
 from monitor import monitor
 from changelogagent import agent, Changelog
+from gsyncdstatus import set_monitor_status, GeorepStatus
 
 
 class GLogger(Logger):
@@ -267,7 +268,7 @@ def main_i():
     op.add_option('--socketdir', metavar='DIR')
     op.add_option('--state-socket-unencoded', metavar='SOCKF',
                   type=str, action='callback', callback=store_abs)
-    op.add_option('--checkpoint', metavar='LABEL', default='')
+    op.add_option('--checkpoint', metavar='LABEL', default='0')
 
     # tunables for failover/failback mechanism:
     # None   - gsyncd behaves as normal
@@ -315,6 +316,8 @@ def main_i():
                   action='callback', callback=store_local)
     op.add_option('--delete', dest='delete', action='callback',
                   callback=store_local_curry(True))
+    op.add_option('--status-get', dest='status_get', action='callback',
+                  callback=store_local_curry(True))
     op.add_option('--debug', dest="go_daemon", action='callback',
                   callback=lambda *a: (store_local_curry('dont')(*a),
                                        setattr(
@@ -583,15 +586,8 @@ def main_i():
             GLogger._gsyncd_loginit(log_file=gconf.log_file, label='conf')
             if confdata.op == 'set':
                 logging.info('checkpoint %s set' % confdata.val)
-                gcnf.delete('checkpoint_completed')
-                gcnf.delete('checkpoint_target')
             elif confdata.op == 'del':
                 logging.info('checkpoint info was reset')
-                # if it is removing 'checkpoint' then we need
-                # to remove 'checkpoint_completed' and 'checkpoint_target' too
-                gcnf.delete('checkpoint_completed')
-                gcnf.delete('checkpoint_target')
-
         except IOError:
             if sys.exc_info()[1].errno == ENOENT:
                 # directory of log path is not present,
@@ -607,7 +603,7 @@ def main_i():
     create = rconf.get('create')
     if create:
         if getattr(gconf, 'state_file', None):
-            update_file(gconf.state_file, lambda f: f.write(create + '\n'))
+            set_monitor_status(gconf.state_file, create)
         return
 
     go_daemon = rconf['go_daemon']
@@ -615,6 +611,15 @@ def main_i():
     be_agent = rconf.get('agent')
 
     rscs, local, remote = makersc(args)
+
+    status_get = rconf.get('status_get')
+    if status_get:
+        for brick in gconf.path:
+            brick_status = GeorepStatus(gconf.state_file, brick)
+            checkpoint_time = int(getattr(gconf, "checkpoint", "0"))
+            brick_status.print_status(checkpoint_time=checkpoint_time)
+        return
+
     if not be_monitor and isinstance(remote, resource.SSH) and \
        go_daemon == 'should':
         go_daemon = 'postconn'