HBASE-25663 Make graceful_stop localhostname compare match even if fqdn (#3048)

bin/graceful_stop.sh

@@ -19,7 +19,6 @@
 # */
 
 # Move regions off a server then stop it. Optionally restart and reload.
-# Turn off the balancer before running this script.
 function usage {
   echo "Usage: graceful_stop.sh [--config <conf-dir>] [-e] [--restart [--reload]] [--thrift] \
 [--rest] [-n |--noack] [--maxthreads <number of threads>] [--movetimeout <timeout in seconds>] \
@@ -33,7 +32,7 @@ moving regions"
   echo " maxthreads xx  Limit the number of threads used by the region mover. Default value is 1."
   echo " movetimeout xx Timeout for moving regions. If regions are not moved by the timeout value,\
 exit with error. Default value is INT_MAX."
-  echo " hostname       Hostname of server we are to stop"
+  echo " hostname       Hostname to stop; match what HBase uses; pass 'localhost' if local to avoid ssh"
   echo " e|failfast     Set -e so exit immediately if any command exits with non-zero status"
   echo " nob|nobalancer Do not manage balancer states. This is only used as optimization in \
 rolling_restart.sh to avoid multiple calls to hbase shell"
@@ -102,13 +101,6 @@ fi
 hostname=$1
 filename="/tmp/$hostname"
 
-local=
-localhostname=`/bin/hostname`
-
-if [ "$localhostname" == "$hostname" ]; then
-  local=true
-fi
-
 if [ "$nob" == "true"  ]; then
   log "[ $0 ] skipping disabling balancer -nob argument is used"
   HBASE_BALANCER_STATE=false
@@ -139,50 +131,26 @@ hosts="/tmp/$(basename $0).$$.tmp"
 echo $hostname >> $hosts
 if [ "$thrift" != "" ]; then
   log "Stopping thrift server on $hostname"
-  if [ "$local" == true ]; then
-    "$bin"/hbase-daemon.sh --config ${HBASE_CONF_DIR} stop thrift
-  else
   "$bin"/hbase-daemons.sh --config ${HBASE_CONF_DIR} --hosts ${hosts} stop thrift
 fi
-fi
 if [ "$rest" != "" ]; then
   log "Stopping rest server on $hostname"
-  if [ "$local" == true ]; then
-    "$bin"/hbase-daemon.sh --config ${HBASE_CONF_DIR} stop rest
-  else
   "$bin"/hbase-daemons.sh --config ${HBASE_CONF_DIR} --hosts ${hosts} stop rest
 fi
-fi
 log "Stopping regionserver on $hostname"
-if [ "$local" == true ]; then
-  "$bin"/hbase-daemon.sh --config ${HBASE_CONF_DIR} stop regionserver
-else
 "$bin"/hbase-daemons.sh --config ${HBASE_CONF_DIR} --hosts ${hosts} stop regionserver
-fi
 if [ "$restart" != "" ]; then
   log "Restarting regionserver on $hostname"
-  if [ "$local" == true ]; then
-    "$bin"/hbase-daemon.sh --config ${HBASE_CONF_DIR} start regionserver
-  else
   "$bin"/hbase-daemons.sh --config ${HBASE_CONF_DIR} --hosts ${hosts} start regionserver
-  fi
   if [ "$thrift" != "" ]; then
     log "Restarting thrift server on $hostname"
     # -b 0.0.0.0 says listen on all interfaces rather than just default.
-    if [ "$local" == true ]; then
-      "$bin"/hbase-daemon.sh --config ${HBASE_CONF_DIR} start thrift -b 0.0.0.0
-    else
     "$bin"/hbase-daemons.sh --config ${HBASE_CONF_DIR} --hosts ${hosts} start thrift -b 0.0.0.0
   fi
-  fi
   if [ "$rest" != "" ]; then
     log "Restarting rest server on $hostname"
-    if [ "$local" == true ]; then
-      "$bin"/hbase-daemon.sh --config ${HBASE_CONF_DIR} start rest
-    else
     "$bin"/hbase-daemons.sh --config ${HBASE_CONF_DIR} --hosts ${hosts} start rest
   fi
-  fi
   if [ "$reload" != "" ]; then
     log "Reloading $hostname region(s)"
     HBASE_NOEXEC=true "$bin"/hbase --config ${HBASE_CONF_DIR} \
@@ -201,4 +169,4 @@ else
 fi
 
 # Cleanup tmp files.
-trap "rm -f  "/tmp/$(basename $0).*.tmp" &> /dev/null" EXIT
+trap "rm -f  /tmp/$(basename $0).*.tmp &> /dev/null" EXIT

src/main/asciidoc/_chapters/ops_mgt.adoc

@@ -1364,10 +1364,9 @@ Copy the script if you need to make use of it in a version of hbase previous to
 
 A downside to the above stop of a RegionServer is that regions could be offline for a good period of time.
 Regions are closed in order.
-If many regions on the server, the first region to close may not be back online until all regions close and after the master notices the RegionServer's znode gone.
+If many regions on the server, the first region to close may not be back online until all regions close and
-In Apache HBase 0.90.2, we added facility for having a node gradually shed its load and then shutdown itself down.
+after the master notices the RegionServer's znode gone.  A node can be asked to gradually shed its load and
-Apache HBase 0.90.2 added the _graceful_stop.sh_ script.
+then shutdown itself using the  _graceful_stop.sh_ script. Here is its usage:
-Here is its usage:
 
 ----
 $ ./bin/graceful_stop.sh
@@ -1393,16 +1392,17 @@ To decommission a loaded RegionServer, run the following: +$
 [NOTE]
 ====
 The `HOSTNAME` passed to _graceful_stop.sh_ must match the hostname that hbase is using to identify RegionServers.
-Check the list of RegionServers in the master UI for how HBase is referring to servers.
+HBase uses fully-qualified domain names usually. Check the list of RegionServers in the master UI for how HBase
-It's usually hostname but can also be FQDN.
+is referring to servers. Whatever HBase is using, this is what you should pass the _graceful_stop.sh_ decommission script.
-Whatever HBase is using, this is what you should pass the _graceful_stop.sh_ decommission script.
+If you pass IPs, the script is not yet smart enough to make a hostname (or FQDN) of it and so it will fail when it checks
-If you pass IPs, the script is not yet smart enough to make a hostname (or FQDN) of it and so it will fail when it checks if server is currently running; the graceful unloading of regions will not run.
+if server is currently running; the graceful unloading of regions will not run.
 ====
 
 The _graceful_stop.sh_ script will move the regions off the decommissioned RegionServer one at a time to minimize region churn.
-It will verify the region deployed in the new location before it will moves the next region and so on until the decommissioned server is carrying zero regions.
+It will verify the region deployed in the new location before it will moves the next region and so on until the decommissioned
-At this point, the _graceful_stop.sh_ tells the RegionServer `stop`.
+server is carrying zero regions. At this point, the _graceful_stop.sh_ tells the RegionServer `stop`.
-The master will at this point notice the RegionServer gone but all regions will have already been redeployed and because the RegionServer went down cleanly, there will be no WAL logs to split.
+The master will at this point notice the RegionServer gone but all regions will have already been redeployed and because the
+RegionServer went down cleanly, there will be no WAL logs to split.
 
 [[lb]]
 .Load Balancer