/usr/sbin/crm_report is in pacemaker-cli-utils 1.1.10+git20130802-1ubuntu2.4.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 | #!/bin/sh
# Copyright (C) 2010 Andrew Beekhof <andrew@beekhof.net>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This software is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
# Note the quotes around `$TEMP': they are essential!
TEMP=`getopt \
-o hv?xl:f:t:n:T:Lp:c:dSACHu:D:MVs \
--long help,cts:,cts-log:,dest:,node:,nodes:,from:,to:logfile:,as-directory,single-node,cluster:,user:,max-depth:,version,features \
-n 'crm_report' -- "$@"`
eval set -- "$TEMP"
times=""
tests=""
nodes=""
compress=1
cluster="any"
ssh_user="root"
search_logs=1
report_data=`dirname $0`
extra_logs=""
sanitize_patterns=""
log_patterns="CRIT: ERROR:"
usage() {
cat<<EOF
crm_report - Create a tarball containing everything needed when reporting cluster problems
Usage: `basename $0` -f "YYYY-M-D H:M:S" [-t "YYYY-M-D H:M:S"] [additional options] [dest]
Options:
-V increase verbosity
-v,--version software version
--features software features
-f, --from time time to start from: "YYYY-M-D H:M:S" (do not forget the quotes)
-t, --to time time to finish at (default: now)
-T, --cts test CTS test or set of tests to extract
--cts-log CTS master logfile
-n, --nodes nodes node names for this cluster
only needed if the cluster is not active on the current machine
accepts both -n "a b" and -n a -n b
-l, --logfile file log file to collect, normally this will be determined automatically
-p patt additional regular expression to match variables to be removed
(default: "passw.*")
-L patt additional regular expression to match in log files for analysis
(default: $log_patterns)
-M collect only the logs specified by -l
-S, --single-node single node operation; don't try to start report collectors on other nodes
-c, --cluster type force the cluster type (corosync,openais,heartbeat,logmaster)
-A, --openais force the cluster type to be OpenAIS
-C, --corosync force the cluster type to be CoroSync
-H, --heartbeat force the cluster type to be Heartbeat
-u, --user user ssh username for cluster nodes (default: root)
-D, --depth search depth to use when attempting to locate files
--dest a custom destination directory/file
dest a custom destination directory/file
Examples:
crm_report -f "2011-12-14 13:05:00" unexplained-apache-failure
crm_report -f 2011-12-14 -t 2011-12-15 something-that-took-multiple-days
crm_report -f 13:05:00 -t 13:12:00 brief-outage
EOF
}
case "$1" in
-v|--version) echo "1.1.10 - 42f2063"; exit 0;;
--features) echo "1.1.10 - 42f2063: generated-manpages agent-manpages ncurses libqb-logging libqb-ipc lha-fencing upstart nagios heartbeat corosync-native snmp libesmtp"; exit 0;;
--|-h|--help) usage; exit 0;;
esac
# Prefer helpers in the same directory if they exist, to simplify development
if [ ! -f $report_data/report.common ]; then
report_data=/usr/share/pacemaker
else
echo "Using local helpers"
fi
. $report_data/report.common
while true; do
case "$1" in
-x) set -x; shift;;
-V) verbose=`expr $verbose + 1`; shift;;
-T|--cts-test) tests="$tests $2"; shift; shift;;
--cts-log) ctslog="$2"; shift; shift;;
-f|--from) start_time=`get_time "$2"`; shift; shift;;
-t|--to) end_time=`get_time "$2"`; shift; shift;;
-n|--node|--nodes) nodes="$nodes $2"; shift; shift;;
-S|--single-node) nodes="$host"; shift;;
-E|-l|--logfile) extra_logs="$extra_logs $2"; shift; shift;;
-p) sanitize_patterns="$sanitize_patterns $2"; shift; shift;;
-L) log_patterns="$log_patterns `echo $2 | sed 's/ /\\\W/g'`"; shift; shift;;
-d|--as-directory) compress=0; shift;;
-A|--openais) cluster="openais"; shift;;
-C|--corosync) cluster="corosync"; shift;;
-H|--heartbeat) cluster="heartbeat"; shift;;
-c|--cluster) cluster="$2"; shift; shift;;
-u|--user) ssh_user="$2"; shift; shift;;
-D|--max-depth) maxdepth="$2"; shift; shift;;
-M) search_logs=0; shift;;
--dest) DESTDIR=$2; shift; shift;;
--) if [ ! -z $2 ]; then DESTDIR=$2; fi; break;;
-h|--help) usage; exit 0;;
# Options for compatability with hb_report
-s) shift;;
*) echo "Unknown argument: $1"; usage; exit 1;;
esac
done
collect_data() {
label="$1"
start=`expr $2 - 10`
end=`expr $3 + 10`
masterlog=$4
if [ "x$DESTDIR" != x ]; then
echo $DESTDIR | grep -e "^/" -qs
if [ $? = 0 ]; then
l_base=$DESTDIR
else
l_base="`pwd`/$DESTDIR"
fi
debug "Using custom scratch dir: $l_base"
r_base=`basename $l_base`
else
l_base=$HOME/$label
r_base=$label
fi
if [ -e $l_base ]; then
fatal "Output directory $l_base already exists, specify an alternate name with --dest"
fi
mkdir -p $l_base
if [ "x$masterlog" != "x" ]; then
dumplogset "$masterlog" $start $end > "$l_base/$HALOG_F"
fi
for node in $nodes; do
cat<<EOF>$l_base/.env
LABEL="$label"
REPORT_HOME="$r_base"
REPORT_MASTER="$host"
REPORT_TARGET="$node"
LOG_START=$start
LOG_END=$end
REMOVE=1
SANITIZE="$sanitize_patterns"
CLUSTER=$cluster
LOG_PATTERNS="$log_patterns"
EXTRA_LOGS="$extra_logs"
SEARCH_LOGS=$search_logs
verbose=$verbose
maxdepth=$maxdepth
EOF
if [ $host = $node ]; then
cat<<EOF>>$l_base/.env
REPORT_HOME="$l_base"
EOF
cat $l_base/.env $report_data/report.common $report_data/report.collector > $l_base/collector
bash $l_base/collector
else
cat $l_base/.env $report_data/report.common $report_data/report.collector \
| ssh -l $ssh_user -T $node -- "mkdir -p $r_base; cat > $r_base/collector; bash $r_base/collector" | (cd $l_base && tar mxf -)
fi
done
analyze $l_base > $l_base/$ANALYSIS_F
if [ -f $l_base/$HALOG_F ]; then
node_events $l_base/$HALOG_F > $l_base/$EVENTS_F
fi
for node in $nodes; do
cat $l_base/$node/$ANALYSIS_F >> $l_base/$ANALYSIS_F
if [ -s $l_base/$node/$EVENTS_F ]; then
cat $l_base/$node/$EVENTS_F >> $l_base/$EVENTS_F
elif [ -s $l_base/$HALOG_F ]; then
awk "\$4==\"$nodes\"" $l_base/$EVENTS_F >> $l_base/$n/$EVENTS_F
fi
done
log " "
if [ $compress = 1 ]; then
fname=`shrink $l_base`
rm -rf $l_base
log "Collected results are available in $fname"
log " "
log "Please create a bug entry at"
log " http://developerbugs.linux-foundation.org/enter_bug.cgi?product=Pacemaker"
log "Include a description of your problem and attach this tarball"
log " "
log "Thank you for taking time to create this report."
else
log "Collected results are available in $l_base"
fi
log " "
}
#
# check if files have same content in the cluster
#
cibdiff() {
d1=`dirname $1`
d2=`dirname $2`
if [ -f $d1/RUNNING -a -f $d2/RUNNING ] ||
[ -f $d1/STOPPED -a -f $d2/STOPPED ]; then
if which crm_diff > /dev/null 2>&1; then
crm_diff -c -n $1 -o $2
else
info "crm_diff(8) not found, cannot diff CIBs"
fi
else
echo "can't compare cibs from running and stopped systems"
fi
}
diffcheck() {
[ -f "$1" ] || {
echo "$1 does not exist"
return 1
}
[ -f "$2" ] || {
echo "$2 does not exist"
return 1
}
case `basename $1` in
$CIB_F) cibdiff $1 $2;;
$B_CONF) diff -u $1 $2;; # confdiff?
*) diff -u $1 $2;;
esac
}
#
# remove duplicates if files are same, make links instead
#
consolidate() {
for n in $NODES; do
if [ -f $1/$2 ]; then
rm $1/$n/$2
else
mv $1/$n/$2 $1
fi
ln -s ../$2 $1/$n
done
}
analyze_one() {
rc=0
node0=""
for n in $NODES; do
if [ "$node0" ]; then
diffcheck $1/$node0/$2 $1/$n/$2
rc=$(($rc+$?))
else
node0=$n
fi
done
return $rc
}
analyze() {
flist="$HOSTCACHE $MEMBERSHIP_F $CIB_F $CRM_MON_F $B_CONF logd.cf $SYSINFO_F"
for f in $flist; do
printf "Diff $f... "
ls $1/*/$f >/dev/null 2>&1 || {
echo "no $1/*/$f :/"
continue
}
if analyze_one $1 $f; then
echo "OK"
[ "$f" != $CIB_F ] && consolidate $1 $f
else
echo ""
fi
done
}
do_cts() {
test_sets=`echo $tests | tr ',' ' '`
for test_set in $test_sets; do
start_time=0
start_test=`echo $test_set | tr '-' ' ' | awk '{print $1}'`
end_time=0
end_test=`echo $test_set | tr '-' ' ' | awk '{print $2}'`
if [ x$end_test = x ]; then
msg="Extracting test $start_test"
label="CTS-$start_test-`date +"%b-%d-%Y"`"
end_test=`expr $start_test + 1`
else
msg="Extracting tests $start_test to $end_test"
label="CTS-$start_test-$end_test-`date +"%b-%d-%Y"`"
end_test=`expr $end_test + 1`
fi
if [ $start_test = 0 ]; then
start_pat="BEGINNING [0-9].* TESTS"
else
start_pat="Running test.*\[ *$start_test\]"
fi
if [ x$ctslog = x ]; then
ctslog=`findmsg 1 "$start_pat"`
if [ x$ctslog = x ]; then
fatal "No CTS control file detected"
else
log "Using CTS control file: $ctslog"
fi
fi
line=`grep -n "$start_pat" $ctslog | tail -1 | sed 's/:.*//'`
if [ ! -z "$line" ]; then
start_time=`linetime $ctslog $line`
fi
line=`grep -n "Running test.*\[ *$end_test\]" $ctslog | tail -1 | sed 's/:.*//'`
if [ ! -z "$line" ]; then
end_time=`linetime $ctslog $line`
fi
if [ -z "$nodes" ]; then
nodes=`grep CTS: $ctslog | grep -v debug: | grep " \* " | sed s:.*\\\*::g | sort -u | tr '\\n' ' '`
log "Calculated node list: $nodes"
fi
if [ $end_time -lt $start_time ]; then
debug "Test didn't complete, grabbing everything up to now"
end_time=`date +%s`
fi
if [ $start_time != 0 ];then
log "$msg (`time2str $start_time` to `time2str $end_time`)"
collect_data $label $start_time $end_time $ctslog
else
fatal "$msg failed: not found"
fi
done
}
getnodes() {
if [ -z $1 ]; then
cluster=`get_cluster_type`
elif [ $1 = any ]; then
cluster=`get_cluster_type`
else
cluster=$1
fi
if [ -z $HA_STATE_DIR ]; then
HA_STATE_DIR=/var/lib/heartbeat
fi
cluster_cf=`find_cluster_cf $cluster`
# 1. Live
if
ps -ef | egrep -qs "[c]ib"
then
debug "Querying CIB for nodes"
cibadmin -Ql -o nodes | awk '
/uname/ {
for( i=1; i<=NF; i++ )
if( $i~/^uname=/ ) {
sub("uname=.","",$i);
sub("\".*","",$i);
print $i;
next;
}
}
' | tr '\n' ' '
# 2. Saved
elif [ -f /var/lib/pacemaker/cib/cib.xml ]; then
debug "Querying on-disk CIB for nodes"
grep "node " /var/lib/pacemaker/cib/cib.xml | awk '
/uname/ {
for( i=1; i<=NF; i++ )
if( $i~/^uname=/ ) {
sub("uname=.","",$i);
sub("\".*","",$i);
print $i;
next;
}
}
' | tr '\n' ' '
# 3. hostcache
elif [ -f $HA_STATE_DIR/hostcache ]; then
debug "Reading nodes from $HA_STATE_DIR/hostcache"
awk '{print $1}' $HA_STATE_DIR/hostcache
# 4. ha.cf
elif [ "x$cluster" = "xheartbeat" ]; then
debug "Reading nodes from $cluster_cf"
getcfvar $cluster node $cluster_cf
# 5. logs
else
# Look in the logs...
logfile=`findmsg 1 "crm_update_peer"`
debug "Reading nodes from $logfile"
if [ ! -z "$logfile" ]; then
grep crm_update_peer: $logfile | sed s/.*crm_update_peer// | sed s/://g | awk '{print $2}' | grep -v "(null)" | sort -u | tr '\n' ' '
fi
fi
}
if [ "x$tests" != "x" ]; then
do_cts
elif [ "x$start_time" != "x" ]; then
masterlog=""
if [ -z "$sanitize_patterns" ]; then
log "WARNING: The tarball produced by this program may contain"
log " sensitive information such as passwords."
log ""
log "We will attempt to remove such information if you use the"
log "-p option. For example: -p \"pass.*\" -p \"user.*\""
log ""
log "However, doing this may reduce the ability for the recipients"
log "to diagnose issues and generally provide assistance."
log ""
log "IT IS YOUR RESPONSIBILITY TO PROTECT SENSITIVE DATA FROM EXPOSURE"
log ""
fi
if [ -z "$nodes" ]; then
nodes=`getnodes $cluster`
log "Calculated node list: $nodes"
fi
if [ -z "$nodes" ]; then
fatal "Cannot determine node list, please specify manually with --nodes"
fi
if
echo $nodes | grep -qs $host
then
debug "We are a cluster node"
else
debug "We are a log master"
masterlog=`findmsg 1 "crmd\\|CTS"`
fi
if [ -z $end_time ]; then
end_time=`perl -e 'print time()'`
fi
label="pcmk-`date +"%a-%d-%b-%Y"`"
log "Collecting data from $nodes (`time2str $start_time` to `time2str $end_time`)"
collect_data $label $start_time $end_time $masterlog
else
fatal "Not sure what to do, no tests or time ranges to extract"
fi
|