ast_coredumper

#!/usr/bin/env bash
# Turn on extended globbing
shopt -s extglob
# Bail on any error
set -e

prog=$(basename $0)

print_help() {
cat <<EOF
NAME
	$prog - Dump and/or format asterisk coredump files

SYNOPSIS
	$prog [ --help ] [ --running | --RUNNING ] [ --latest ]
		[ --tarball-coredumps ] [ --delete-coredumps-after ]
		[ --tarball-results ] [ --delete-results-after ]
		[ --tarball-config ] [ --tarball-uniqueid="<uniqueid>" ]
		[ --no-default-search ] [ --append-coredumps ]
		[ --asterisk-bin="path" ]
		[ <coredump> | <pattern> ... ]

DESCRIPTION

	Extracts backtraces and lock tables from Asterisk coredump files.
	For each coredump found, 4 new result files are created:
	- <coredump>.brief.txt: The output of "thread apply all bt".

	- <coredump>.thread1.txt: The output of "thread apply 1 bt full".

	- <coredump>.full.txt: The output of "thread apply all bt full".

	- <coredump>.locks.txt: If asterisk was compiled with
		"DEBUG_THREADS", this file will contain a dump of the locks
		table similar to doing a "core show locks" from the asterisk
		CLI.

	Optional features:
	- The running asterisk process can be suspended and dumped.
	- The coredumps can be merged into a tarball.
	- The coredumps can be deleted after processing.
	- The results files can be merged into a tarball.
	- The results files can be deleted after processing.

	Options:

	--help
		Print this help.

	--running
		Create a coredump from the running asterisk instance and
		process it along with any other coredumps found (if any).
		WARNING: This WILL interrupt call processing.  You will be
		asked to confirm.  The coredump will be written to /tmp if
		$OUTPUTDIR is not defined.

	--RUNNING
		Same as --running but without the confirmation prompt.
		DANGEROUS!!

	--latest
		Process only the latest coredump from those specified (based
		on last-modified time).  If a dump of the running process was
		requested, it is always included in addition to the latest
		from the existing coredumps.

	--tarball-coredumps
		Creates a gzipped tarball of coredumps processed, their
		results txt files and copies of /etc/os-release,
		/usr/sbin/asterisk, /usr/lib(64)/libasterisk* and
		/usr/lib(64)/asterisk as those files are needed to properly
		examine the coredump.  The file will be named
		$OUTPUTDIR/asterisk.<timestamp>.coredumps.tar.gz or
		$OUTPUTDIR/asterisk-<uniqueid>.coredumps.tar.gz if
		--tarball-uniqueid was specified.
		WARNING:  This file could 1gb in size!
		Mutually exclusive with --tartball-results

	--delete-coredumps-after
		Deletes all processed coredumps regardless of whether
		a tarball was created.

	--tarball-results
		Creates a gzipped tarball of all result files produced.
		The tarball name will be:
		$OUTPUTDIR/asterisk.<timestamp>.results.tar.gz
		Mutually exclusive with --tartball-coredumps

	--delete-results-after
		Deletes all processed results regardless of whether
		a tarball was created.  It probably doesn't make sense
		to use this option unless you have also specified
		--tarball-results.

	--tarball-config
		Adds the contents of /etc/asterisk to the tarball created
		with --tarball-coredumps or --tarball-results.

	--tarball-uniqueid="<uniqueid>"
		Normally DATEFORMAT is used to make the tarballs unique
		but you can use your own unique id in the tarball names
		such as the Jira issue id.

	--no-default-search
		Ignore COREDUMPS from the config files and process only
		coredumps listed on the command line (if any) and/or
		the running asterisk instance (if requested).

	--append-coredumps
		Append any coredumps specified on the command line to the
		config file specified ones instead of overriding them.

	--asterisk-binary
		Path to the asterisk binary. Default: look for asterisk
		in the PATH.

	<coredump> | <pattern>
		A list of coredumps or coredump search patterns.  Unless
		--append-coredumps was specified, these entries will override
		those specified in the config files.

		Any resulting file that isn't actually a coredump is silently
		ignored.  If your patterns contains spaces be sure to only
		quote the portion of the pattern that DOESN'T contain wildcard
		expressions.  If you quote the whole pattern, it won't be
		expanded.

		If --no-default-search is specified and no files are specified
		on the command line, then the only the running asterisk process
		will be dumped (if requested).  Otherwise if no files are
		specified on the command line the value of COREDUMPS from
		ast_debug_tools.conf will be used.  Failing that, the following
		patterns will be used:
		/tmp/core[-._]asterisk!(*.txt)
		/tmp/core[-._]\$(hostname)!(*.txt)

NOTES
	You must be root to use $prog.

	$OUTPUTDIR can be read from the current environment or from the
	ast_debug_tools.conf file described below.  If not specified,
	work products are placed in the same directory as the core file.

	The script relies on not only bash, but also recent GNU date and
	gdb with python support.  *BSD operating systems may require
	installation of the 'coreutils' and 'devel/gdb' packagess and minor
	tweaking of the ast_debug_tools.conf file.

	Any files output will have ':' characters changed to '-'.  This is
	to facilitate uploading those files to Jira which doesn't like the
	colons.

FILES
	/etc/asterisk/ast_debug_tools.conf
	~/ast_debug_tools.conf
	./ast_debug_tools.conf

	#
	# This file is used by the Asterisk debug tools.
	# Unlike other Asterisk config files, this one is
	# "sourced" by bash and must adhere to bash semantics.
	#

	# A list of coredumps and/or coredump search patterns.
	# Bash extended globs are enabled and any resulting files
	# that aren't actually coredumps are silently ignored
	# so you can be liberal with the globs.
	#
	# If your patterns contains spaces be sure to only quote
	# the portion of the pattern that DOESN'T contain wildcard
	# expressions.  If you quote the whole pattern, it won't
	# be expanded and the glob characters will be treated as
	# literals.
	#
	# The exclusion of files ending ".txt" is just for
	# demonstration purposes as non-coredumps will be ignored
	# anyway.
	COREDUMPS=(/tmp/core[-._]asterisk!(*.txt) /tmp/core[-._]\$(hostname)!(*.txt))

	# The directory to contain output files and work directories.
	# For output from existing core files, the default is the
	# directory that the core file is found in.  For core files
	# produced from a running process, the default is /tmp.
	OUTPUTDIR=/some/directory

	# Date command for the "running" coredump and tarballs.
	# DATEFORMAT will be executed to get the timestamp.
	# Don't put quotes around the format string or they'll be
	# treated as literal characters.  Also be aware of colons
	# in the output as you can't upload files with colons in
	# the name to Jira.
	#
	# Unix timestamp
	#DATEFORMAT='date +%s.%N'
	#
	# *BSD/MacOS doesn't support %N but after installing GNU
	# coreutils...
	#DATEFORMAT='gdate +%s.%N'
	#
	# Readable GMT
	#DATEFORMAT='date -u +%FT%H-%M-%S%z'
	#
	# Readable Local time
	DATEFORMAT='date +%FT%H-%M-%S%z'

EOF
	exit 1
}

if [ $EUID -ne 0 ] ; then
	echo "You must be root to use $prog."
	exit 1
fi

running=false
RUNNING=false
latest=false
tarball_coredumps=false
tarball_config=false
delete_coredumps_after=false
tarball_results=false
delete_results_after=false
append_coredumps=false

declare -a COREDUMPS
declare -a ARGS_COREDUMPS

# readconf reads a bash-sourceable file and sets variables
# that havn't already been set.  This allows variables set
# on the command line or that are already in the environment
# to take precedence over those read from the file.
#
# Setting the values can't be done in a subshell so you can't
# just pipe the output of sed into the while.

readconf() {
	while read line ; do
		v=${line%%=*}
		[ -z "${!v}" ] && eval $line || :
	done <<EOF
$( sed -r -e "/\s*#/d" -e "/^\s*$/d" $1 )
EOF
}

# Read config files from most important to least important.
# Variable set on the command line or environment always take precedence.
[ -f ./ast_debug_tools.conf ] && readconf ./ast_debug_tools.conf
[ -f ~/ast_debug_tools.conf ] && readconf ~/ast_debug_tools.conf
[ -f /etc/asterisk/ast_debug_tools.conf ] && readconf /etc/asterisk/ast_debug_tools.conf

# For *BSD, the preferred gdb may be in /usr/local/bin so we
# need to search for one that supports python.
for g in $(which -a gdb) ; do
	result=$($g --batch --ex "python print('hello')" 2>/dev/null || : )
	if [[ "$result" =~ ^hello$ ]] ; then
		GDB=$g
		break
	fi
done

if [ -z "$GDB" ] ; then
	echo "No suitable gdb was found in $PATH"
	exit 1
fi

if [ -n "$OUTPUTDIR" ] ; then
	if [ ! -d "$OUTPUTDIR" ] ; then
		echo "OUTPUTDIR $OUTPUTDIR doesn't exists or is not a directory"
		exit 1
	fi
fi

if [ ${#COREDUMPS[@]} -eq 0 ] ; then
	COREDUMPS+=(/tmp/core[-._]asterisk!(*.txt) /tmp/core[-._]$(hostname)!(*.txt))
fi

DATEFORMAT=${DATEFORMAT:-'date +%FT%H-%M-%S%z'}

# Use "$@" (with the quotes) so spaces in patterns or
# file names are preserved.
# Later on when we have to iterate over COREDUMPS, we always
# use the indexes rather than trying to expand the values of COREDUMPS
# just in case.

for a in "$@" ; do
	case "$a" in
	--running)
		running=true
		;;
	--RUNNING)
		RUNNING=true
		;;
	--no-default-search)
		# Clean out COREDUMPS from config files
		COREDUMPS=()
		;;
	--latest)
		latest=true
		;;
	--tarball-coredumps)
		tarball_coredumps=true
		;;
	--tarball-config)
		tarball_config=true
		;;
	--delete-coredumps-after)
		delete_coredumps_after=true
		;;
	--tarball-results)
		tarball_results=true
		;;
	--delete-results-after)
		delete_results_after=true
		;;
	--append-coredumps)
		append_coredumps=true
		;;
	--tarball-uniqueid=*)
		tarball_uniqueid=${a#*=}
		;;
	--asterisk-bin=*)
		asterisk_bin=${a#*=}
		;;
	--help|-*)
		print_help
		;;
	*)
		ARGS_COREDUMPS+=("$a")
		# If any files are specified on the command line, ignore those
		# specified in the config files unless append-coredumps was specified.
		if ! $append_coredumps ; then
			COREDUMPS=()
		fi
	esac
done

# append coredumps/patterns specified as command line arguments to COREDUMPS.
for i in ${!ARGS_COREDUMPS[@]} ; do
	COREDUMPS+=("${ARGS_COREDUMPS[$i]}")
done

# At this point, all glob entries that match files should be expanded.
# Any entries that don't exist are probably globs that didn't match anything
# and need to be pruned.  Any non coredumps are also pruned.

for i in ${!COREDUMPS[@]} ; do
	if [ ! -f "${COREDUMPS[$i]}" ] ; then
		unset COREDUMPS[$i]
		continue
	fi
	# Some versions of 'file' don't allow only the first n bytes of the
	# file to be processed so we use dd to grab just the first 32 bytes.
	mimetype=$(dd if="${COREDUMPS[$i]}" bs=32 count=1 2>/dev/null | file -bi -)
	if [[ ! "$mimetype" =~ coredump ]] ; then
		unset COREDUMPS[$i]
		continue
	fi
done

# Sort and weed out any dups
IFS=$'\x0a'
readarray -t COREDUMPS < <(echo -n "${COREDUMPS[*]}" | sort -u )
unset IFS

# If --latest, get the last modified timestamp of each file,
# sort them, then return the latest.
if [ ${#COREDUMPS[@]} -gt 0 ] && $latest ; then
	lf=$(find "${COREDUMPS[@]}" -printf '%T@ %p\n' | sort -n | tail -1)
	COREDUMPS=("${lf#* }")
fi

# Timestamp to use for output files
df=${tarball_uniqueid:-$(${DATEFORMAT})}

if [ x"$asterisk_bin" = x ]; then
	asterisk_bin=$(which asterisk)
fi

if $running || $RUNNING ; then
	# We need to go through some gyrations to find the pid of the running
	# MAIN asterisk process and not someone or something running asterisk -r.

	unset pid

	# Simplest case first...
	pids=$(pgrep -f "$asterisk_bin")
	pidcount=$(echo $pids | wc -w)

	if [ $pidcount -eq 0 ] ; then
		>&2 echo "Asterisk is not running"
		exit 1
	fi

	# Single process, great.
	if [ $pidcount -eq 1 ] ; then
		pid=$pids
		echo "Found a single asterisk instance running as process $pid"
	fi

	# More than 1 asterisk process running
	if [ x"$pid" = x ] ; then
		# More than 1 process running, let's try asking asterisk for it's
		# pidfile
		pidfile=$("$asterisk_bin" -rx "core show settings" 2>/dev/null | sed -n -r -e "s/^\s*pid file:\s+(.*)/\1/gpi")
		# We found it
		if [ x"$pidfile" != x -a -f "$pidfile" ] ; then
			pid=$(cat "$pidfile")
			echo "Found pidfile $pidfile with process $pid"
		fi
	fi

	# It's possible that asterisk was started with the -C option which means the
	# control socket and pidfile might not be where we expect.  We're going to
	# have to parse the process arguments to see if -C was specified.
	# The first process that has a -C argument determines which config
	# file to use to find the pidfile of the main process.
	# NOTE: The ps command doesn't quote command line arguments that it
	# displays so we need to look in /proc/<pid>/cmdline.

	if [ x"$pid" = x ] ; then
		# BSDs might not mount /proc by default :(
		mounted_proc=0
		if uname -o | grep -qi "bsd" ; then
			if ! mount | grep -qi "/proc" ; then
				echo "Temporarily mounting /proc"
				mounted_proc=1
				mount -t procfs proc /proc
			fi
		fi

		for p in $pids ; do
			# Fields in cmdline are delimited by NULLs
			astetcconf=$(sed -n -r -e "s/.*\x00-C\x00([^\x00]+).*/\1/gp" /proc/$p/cmdline)
			if [ x"$astetcconf" != x ] ; then
				pidfile=$("$asterisk_bin" -C "$astetcconf" -rx "core show settings" 2>/dev/null | sed -n -r -e "s/^\s*pid file:\s+(.*)/\1/gpi")
				if [ x"$pidfile" != x -a -f "$pidfile" ] ; then
					pid=$(cat "$pidfile")
					echo "Found pidfile $pidfile the hard way with process $pid"
					break
				fi
			fi
		done
		if [ $mounted_proc -eq 1 ] ; then
			echo "Unmounting /proc"
			umount /proc
		fi
	fi

	if [ x"$pid" = x ] ; then
		>&2 echo "Can't determine pid of the running asterisk instance"
		exit 1
	fi

	if $RUNNING ; then
		answer=Y
	else
		read -p "WARNING:  Taking a core dump of the running asterisk instance will suspend call processing while the dump is saved.  Do you wish to continue? (y/N) " answer
	fi
	if [[ "$answer" =~ ^[Yy] ]] ; then
		cf="${OUTPUTDIR:-/tmp}/core-asterisk-running-$df"
		echo "Dumping running asterisk process to $cf"
		${GDB} ${asterisk_bin} -p $pid -q --batch --ex "gcore $cf" >/dev/null 2>&1
		COREDUMPS+=("$cf")
	else
		echo "Skipping dump of running process"
	fi
fi

if [ "${#COREDUMPS[@]}" -eq 0 ] ; then
	echo "No coredumps found"
	print_help
fi

# Extract the gdb scripts from the end of this script
# and save them to /tmp/.gdbinit

gdbinit=${OUTPUTDIR:-/tmp}/.ast_coredumper.gdbinit

trap "rm $gdbinit" EXIT

ss=`egrep -n "^#@@@SCRIPTSTART@@@" $0 |cut -f1 -d:`
tail -n +${ss} $0 >$gdbinit

# Now iterate over the coredumps and dump the debugging info
for i in ${!COREDUMPS[@]} ; do
	cf=${COREDUMPS[$i]}
	echo "Processing $cf"

	cfdir=`dirname ${cf}`
	cfname=`basename ${cf}`
	outputdir=${OUTPUTDIR:-${cfdir}}

	${GDB} -n --batch -q --ex "source $gdbinit" "$asterisk_bin" "$cf" 2>/dev/null | (
		of=/dev/null
		while IFS= read line ; do
			if [[ "$line" =~ !@!@!@!\ ([^\ ]+)\ !@!@!@! ]] ; then
				of=${outputdir}/${cfname}-${BASH_REMATCH[1]}
				of=${of//:/-}
				rm -f "$of"
				echo "Creating $of"
			fi
			echo -e $"$line" >> "$of"
		done
	)

	if $tarball_coredumps ; then
		cfname=${cfname//:/-}
		tf=${outputdir}/${cfname}.tar.gz
		echo "Creating ${tf}"

		dest=${outputdir}/${cfname}.output
		rm -rf ${dest} 2>/dev/null || :

		libdir=usr/lib
		[ -d /usr/lib64 ] && libdir+=64
		mkdir -p ${dest}/tmp ${dest}/${libdir}/asterisk ${dest}/etc ${dest}/usr/sbin

		ln -s ${cf} ${dest}/tmp/${cfname}
		cp ${outputdir}/${cfname}*.txt ${dest}/tmp/
		[ -f /etc/os-release ] && cp /etc/os-release ${dest}/etc/
		if $tarball_config ; then
			cp -a /etc/asterisk ${dest}/etc/
		fi
		cp -a /${libdir}/libasterisk* ${dest}/${libdir}/
		cp -a /${libdir}/asterisk/* ${dest}/${libdir}/asterisk/
		cp -a /usr/sbin/asterisk ${dest}/usr/sbin
		rm -rf ${tf}
		tar -chzf ${tf} --transform="s/^[.]/${cfname}/" -C ${dest} .
		sleep 3
		rm -rf ${dest}
		echo "Created $tf"
	elif $tarball_results ; then
		cfname=${cfname//:/-}
		tf=${outputdir}/${cfname}.tar.gz
		echo "Creating ${tf}"

		dest=${outputdir}/${cfname}.output
		rm -rf ${dest} 2>/dev/null || :
		mkdir -p ${dest}
		cp ${outputdir}/${cfname}*.txt ${dest}/
		if $tarball_config ; then
			mkdir -p ${dest}/etc
			cp -a /etc/asterisk ${dest}/etc/
		fi
		tar -chzf ${tf} --transform="s/^[.]/${cfname}/" -C ${dest} .
		rm -rf ${dest}
		echo "Created $tf"
	fi

if $delete_coredumps_after ; then
		rm -rf "${cf}"
	fi

	if $delete_results_after ; then
		rm -rf "${cf//:/-}"-{brief,full,thread1,locks}.txt
	fi
done

exit

# Be careful editng the inline scripts.
# They're space-indented.

# We need the python bit because lock_infos isn't
# a valid symbol in asterisk unless DEBUG_THREADS was
# used during the compile.  Also, interrupt and continue
# are only valid for a running program.

#@@@SCRIPTSTART@@@
python
class DumpAsteriskCommand(gdb.Command):

    def __init__(self):
        super(DumpAsteriskCommand, self).__init__ ("dump-asterisk",
            gdb.COMMAND_OBSCURE, gdb.COMPLETE_COMMAND)

    def invoke(self, arg, from_tty):
        try:
            gdb.execute("interrupt", from_tty)
        except:
            pass
        print("!@!@!@! thread1.txt !@!@!@!\n")
        try:
            gdb.execute("p $_siginfo", from_tty)
            gdb.execute("info signal $_siginfo.si_signo")
        except:
            pass
        try:
            gdb.execute("thread apply 1 bt full", from_tty)
        except:
            pass
        print("!@!@!@! brief.txt !@!@!@!\n")
        try:
            gdb.execute("p $_siginfo", from_tty)
            gdb.execute("info signal $_siginfo.si_signo")
        except:
            pass
        try:
            gdb.execute("thread apply all bt", from_tty)
        except:
            pass
        print("!@!@!@! full.txt !@!@!@!\n")
        try:
            gdb.execute("p $_siginfo", from_tty)
            gdb.execute("info signal $_siginfo.si_signo")
        except:
            pass
        try:
            gdb.execute("thread apply all bt full", from_tty)
        except:
            pass
        print("!@!@!@! locks.txt !@!@!@!\n")
        try:
            gdb.execute("p $_siginfo", from_tty)
            gdb.execute("info signal $_siginfo.si_signo")
        except:
            pass
        try:
            gdb.execute("show_locks", from_tty)
        except:
            pass
        try:
            gdb.execute("continue", from_tty)
        except:
            pass

DumpAsteriskCommand ()
end

define show_locks
   set $n = lock_infos.first

   if $argc == 0
      printf "                                                                                                                    where_held count-|\n"
      printf "                                                                                                                         suspended-| |\n"
      printf "                                                                                                        type- |     times locked-| | |\n"
      printf "thread         status   file                   line function                             lock name            | lock addr        | | |\n"
   else
      printf "thread,status,file,line,function,lock_name,lock_type,lock_addr,times_locked,suspended,where_held_count,where_held_file,where_held_line,where_held_function,there_held_thread\n"
   end

   while $n
      if $n->num_locks > 0
      set $i = 0
      while $i < $n->num_locks
         if $n->locks[$i]->suspended == 0
            if ((ast_mutex_t *)$n->locks[$i]->lock_addr)->tracking
               if $n->locks[$i]->type > 0
                  set $track = ((ast_rwlock_t *)$n->locks[$i]->lock_addr)->track
               else
                  set $track = ((ast_mutex_t *)$n->locks[$i]->lock_addr)->track
               end
            end
            set $reentrancy = $track->reentrancy
            set $pending = $n->locks[$i]->pending
            if $argc > 0
               printf "%p,%d,%s,%d,%s,%s,%d,%p,%d,%d,%d",\
                  $n->thread_id, $n->locks[$i]->pending, $n->locks[$i]->file, $n->locks[$i]->line_num, $n->locks[$i]->func,\
                  $n->locks[$i]->lock_name, $n->locks[$i]->type, $n->locks[$i]->lock_addr, $n->locks[$i]->times_locked,\
                  $n->locks[$i]->suspended, $track->reentrancy
               if $reentrancy
                  if $pending
                     printf ",%s,%d,%s,%p", $track->file[0], $track->lineno[0], $track->func[0], $track->thread[0]
                  end
               end
            else
               if $n->locks[$i]->pending < 0
                  printf "%p failed   %-20s %6d %-36s %-20s %d %14p %3d %d %d",\
                     $n->thread_id,\
                     $n->locks[$i]->file, $n->locks[$i]->line_num, $n->locks[$i]->func,\
                     $n->locks[$i]->lock_name, $n->locks[$i]->type, $n->locks[$i]->lock_addr, $n->locks[$i]->times_locked,\
                     $n->locks[$i]->suspended, $track->reentrancy
               end
               if $n->locks[$i]->pending == 0
                  printf "%p holding  %-20s %6d %-36s %-20s %d %14p %3d %d %d",\
                     $n->thread_id,\
                     $n->locks[$i]->file, $n->locks[$i]->line_num, $n->locks[$i]->func,\
                     $n->locks[$i]->lock_name, $n->locks[$i]->type, $n->locks[$i]->lock_addr, $n->locks[$i]->times_locked,\
                     $n->locks[$i]->suspended, $track->reentrancy
               end
               if $n->locks[$i]->pending > 0
                  printf "%p waiting  %-20s %6d %-36s %-20s %d %14p %3d %d %d",\
                     $n->thread_id,\
                     $n->locks[$i]->file, $n->locks[$i]->line_num, $n->locks[$i]->func,\
                     $n->locks[$i]->lock_name, $n->locks[$i]->type, $n->locks[$i]->lock_addr, $n->locks[$i]->times_locked,\
                     $n->locks[$i]->suspended, $track->reentrancy
               end
               if $reentrancy
                  if $pending
                     printf "\n               held at: %-20s %6d %-36s by 0x%08lx", $track->file[0], $track->lineno[0], $track->func[0], $track->thread_id[0]
                  end
               end
            end
            printf "\n"
         end
         set $i = $i + 1
      end
    end
    set $n = $n->entry->next
  end
end

dump-asterisk