rsync - Aug 2001 - problems with rsync version 2.4.6 protocol version 24 on solaris 2.8

Greetings,

         I'm using rsync to keep multiple nfs filesystems on two emc nfs 
serves in sync.  Here are the six file systems and their info:

Filesystem           kbytes       used      avail capacity  Mounted 
on             Number of files
burd1p0:/nettmp      258120      37144     220976    15% 
/nfs/burd1p0/nettmp      2102
burd1p0:/user      29443776   16160480   13283296    55% 
/nfs/burd1p0/user       68171
burd2p0:/netutl    14721376    4515128   10206248    31% 
/nfs/burd2p0/netutl     13611
burd3p0:/netconfig 
14721376    1010336   13711040     7%    /nfs/burd3p0/netconfig  33198
burd2p0:/aqptmp      258120      10664     247456     5% 
/nfs/burd2p0/aqptmp       546
burd3p0:/reports   14721376    3868000   10853376    27% 
/nfs/burd3p0/reports   290481

         What I'm seeing is that Rsync will freeze in the middle of the 
sync.  I've attached the script that I use along with the config file for
it.

         I know that there is a patch for this version, but I am unable the 
compile in this environment and do not have access to a compiler in the our 
other environments.

         I have done a truss -p pid on the three running processes and here 
are their outputs:

root@lancelot:/opt/Rsync% ps -ef | grep rsync
     root 29191 29182  0 14:43:37 pts/2    2:51 /opt/Rsync/bin/rsync.7 
--recursive --progress --stats --delete --one-file-syste
     root  1516 25536  0 15:16:35 pts/5    0:00 grep rsync
     root 29192 29191  0 14:43:37 pts/2    1:10 /opt/Rsync/bin/rsync.7 
--recursive --progress --stats --delete --one-file-syste
root@lancelot:/opt/Rsync% truss -p 29191
poll(0xFFBEF888, 0, 20)                         = 0
waitid(P_PID, 29192, 0xFFBEF898, WEXITED|WTRAPPED|WNOHANG) = 0
poll(0xFFBEF888, 0, 20)                         = 0
waitid(P_PID, 29192, 0xFFBEF898, WEXITED|WTRAPPED|WNOHANG) = 0
^Croot@lancelot:/opt/Rsync% truss -p 29192
poll(0xFFBEDC58, 1, 60000)      (sleeping...)
^Croot@lancelot:/opt/Rsync%

-------------- next part --------------
#
#
#  A list of file systems and where they are located
#
# filesystem		FROM				TO
netconfig	/nfs/burd3p1/netconfig		/nfs/wald2p1/netconfig 
netutl		/nfs/burd2p1/netutl		/nfs/wald2p1/netutl 
reports		/nfs/burd3p1/reports		/nfs/wald3p1/reports 
user		/nfs/burd1p1/user		/nfs/wald1p1/user 	
aqptmp		/nfs/burd2p1/aqptmp		/nfs/wald2p1/aqptmp
nettmp		/nfs/burd1p1/nettmp		/nfs/wald2p1/nettmp		
-------------- next part --------------
#!/bin/ksh

#
#  set -x
#

#
#  sync_nfs_filesystems
#
#  This script was written to help keep the nfs file systems in sync between
file systems.
#    It takes one argument - which file system to sync.  It uses this argument
to read from
#    a config file a FROM location and a TO location.  It also set up the
logging information
#    and determines which exclude file to use from this.
#
#  EXIT STATUS:
#	0	normal suggessful exit
#	-2	Usage has been displayed
#	-3	A Sync for this filesystem is already running
#
#  V1.0		12/15/2000	PEL	Initial Version
#
#
#echo "$0 - Version 1.0 - last revised on 12/15/2000 by PEL"

#
#  check number of args - must be exactly one or else give usage
#
if [ $# -eq 0 -o "$1" = "-h" ]
then
  cat <<EOF
    USAGE:
	$0  filesystem

	Where filesystem is the file system that you want to sync
EOF
  exit -2
fi

FILESYSTEM=$1							# which file system to sync
WORKPATH=/opt/Rsync						# path to all needed files
CONF_FILE=$WORKPATH/sync_nfs_filesystem.conf			# config file of sync data
FROMDIR=`grep ^$FILESYSTEM $CONF_FILE | awk '{print $2}'`/	# get's
source data path
TODIR=`grep ^$FILESYSTEM $CONF_FILE | awk '{print $3}'`/	# get's
destination data path
#NOTIFY_LIST="sysopsprod@lightbridge.com"			# who to notify when done
NOTIFY_LIST="plamadeleine@lightbridge.com,pel_pager@lightbridge.com"
TIMELOG=$WORKPATH/times.log					# log file of start and stop times
OUTLOG=$WORKPATH/$FILESYSTEM.log				# log file of work done
ARCHIVELOG=$WORKPATH/logs/${FILESYSTEM}_`date +"%H%M_%m%d%Y"`.log	#
where/how to archive log files
EXCLUDE=$WORKPATH/sync_${FILESYSTEM}.exclude			# file of directories to exclude
from sync
STARTTIME=`date +"%H:%M:%S %m/%d/%Y"`				# start time of sync
LOCKFILE=/tmp/${FILESYSTEM}_sync.lock				# used for program locking

#
#  check to see if another sync job for this file system is already running
#
if [ -f $LOCKFILE ]
then
  MESSAGE='tried to start syncing when there already was on running'
  printf "%6s %6s %10s %55s \n" $STARTTIME $FILESYSTEM
"$MESSAGE" >> $TIMELOG
  exit -3
else
  MESSAGE='started sync'
  printf "%6s %6s %10s %35s \n" $STARTTIME $FILESYSTEM
"$MESSAGE" >> $TIMELOG	# records start time
  touch $LOCKFILE
fi

#
#  This line does the actually syncing of the two file systems
#
#$WORKPATH/bin/rsync.5   --recursive             \
$WORKPATH/bin/rsync.7	--recursive 		\
			--progress 		\
			--stats 		\
			--delete 		\
			--one-file-system 	\
			--times 		\
			--group  		\
			--owner 		\
			--perms 		\
			--archive  		\
			--verbose 		\
			--timeout=300		\
			--exclude-from=$EXCLUDE	\
			$FROMDIR $TODIR >> $OUTLOG 2>&1

ENDTIME=`date +"%H:%M:%S %m/%d/%Y"`						# gets ending time
MESSAGE='done with sync'
printf "%6s %6s %10s %35s \n" $ENDTIME $FILESYSTEM
"$MESSAGE" >> $TIMELOG	# records ending time

#
#  archive log file
#
mv $OUTLOG $ARCHIVELOG								# creates archive log file

#
#  remove lock file
#
rm $LOCKFILE

#
#  send out notification mail
#
#mailx -s "Done syncing $FILESYSTEM - $ENDTIME" $NOTIFY_LIST <
/dev/null		# mails notification list of job completion

exit 0										# exits nicely