log check tool initial

This commit is contained in:
Jason Ertel
2023-09-26 18:12:20 -04:00
parent 641b8ef0b6
commit 48801da44e

View File

@@ -0,0 +1,174 @@
#!/bin/bash
#
# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
# https://securityonion.net/license; you may not use this file except in compliance with the
# Elastic License 2.0.
. /usr/sbin/so-common
RECENT_LOG_LINES=200
EXCLUDE_STARTUP_ERRORS=N
EXCLUDE_FALSE_POSITIVE_ERRORS=N
EXCLUDE_KNOWN_ERRORS=N
while [[ $# -gt 0 ]]; do
case $1 in
--exclude-connection-errors)
EXCLUDE_STARTUP_ERRORS=Y
;;
--exclude-false-positives)
EXCLUDE_FALSE_POSITIVE_ERRORS=Y
;;
--exclude-known-errors)
EXCLUDE_KNOWN_ERRORS=Y
;;
--unknown)
EXCLUDE_STARTUP_ERRORS=Y
EXCLUDE_FALSE_POSITIVE_ERRORS=Y
EXCLUDE_KNOWN_ERRORS=Y
;;
--recent-log-lines)
shift
RECENT_LOG_LINES=$1
;;
*)
echo "Usage: $0 [options]"
echo ""
echo "where options are:"
echo " --recent-log-lines N looks at the most recent N log lines per file or container; defaults to 200"
echo " --exclude-connection-errors exclude errors caused by a recent server or container restart"
echo " --exclude-false-positives exclude logs that are not actual errors but contain the error string"
echo " --exclude-known-errors exclude errors that are known and non-critical issues"
echo " --unknown exclude everthing mentioned above; only show unknown errors"
echo ""
echo "A non-zero return value indicates errors were found"
exit 1
;;
esac
shift
done
echo "Security Onion Log Check - $(date)"
echo "-------------------------------------------"
echo ""
echo "- RECENT_LOG_LINES: $RECENT_LOG_LINES"
echo "- EXCLUDE_STARTUP_ERRORS: $EXCLUDE_STARTUP_ERRORS"
echo "- EXCLUDE_FALSE_POSITIVE_ERRORS: $EXCLUDE_FALSE_POSITIVE_ERRORS"
echo "- EXCLUDE_KNOWN_ERRORS: $EXCLUDE_KNOWN_ERRORS"
echo ""
function status() {
header "$1"
}
function exclude_container() {
name=$1
exclude_id=$(docker ps | grep "$name" | awk '{print $1}')
if [[ -n "$exclude_id" ]]; then
CONTAINER_IDS=$(echo $CONTAINER_IDS | sed -e "s/$exclude_id//g")
return $?
fi
return $?
}
function exclude_log() {
name=$1
LOG_FILES=$(echo "$LOG_FILES" | sed -e "s/$name//g")
}
function check_for_errors() {
if cat /tmp/log_check | grep -i error | grep -vEi "$EXCLUDED_ERRORS"; then
RESULT=1
fi
}
EXCLUDED_ERRORS="__LOG_CHECK_PLACEHOLDER_EXCLUSION__"
if [[ $EXCLUDE_STARTUP_ERRORS == 'Y' ]]; then
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|database is locked" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|econnreset" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|unreachable" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|no route to host" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|not running" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|unavailable" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|request.py" # server not yet ready (python stack output)
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|httperror" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|servfail" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|connection refused" # server not yet ready
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|missing shards" # server not yet ready
fi
if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|elastalert_status_error" # false positive
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|elastalert_error.json" # false positive
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|error: '0'" # false positive
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|errors_index" # false positive
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|noerror" # false positive
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|emerging-all.rules" # false positive (error in rulename)
fi
if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|eof"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|_ml" # Elastic ML errors
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|iteration"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|communication packets"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|use of closed"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|bookkeeper"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|noindices"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|failed to start transient scope"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|status 200" # request successful, contained error string in content
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|so-user.lock exists"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|systemd-run"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|retcode: 1"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|telemetry-task"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|redisqueue"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|fleet_detail_query"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|num errors=0"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|provisioning/alerting"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|provisioning/notifiers"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|provisoning/plugins"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|active-responses.log"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|scanentropy"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|integration policy"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|blob unknown"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|token required"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|zeekcaptureloss"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|unable to create detection"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|error installing new prebuilt rules"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|parent.error"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|req.LocalMeta.host.ip" # known issue
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|sendmail" # zeek
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|example" # example test data
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|so_long_term" # setup in progress, influxdb not yet setup
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|stats.log"
EXCLUDED_ERRORS="$EXCLUDED_ERRORS|context deadline exceeded"
fi
RESULT=0
# Check Security Onion container stdout/stderr logs
CONTAINER_IDS=$(docker ps -q)
exclude_container so-kibana
exclude_container so-idstools
for container_id in $CONTAINER_IDS; do
status "Checking container $container_id"
docker logs -n $RECENT_LOG_LINES $container_id > /tmp/log_check 2>&1
check_for_errors
done
# Check Security Onion related log files
LOG_FILES=$(find /opt/so/log/ /nsm -name \*.log)
exclude_log "\s?.*kibana.log"
LOG_FILES="$LOG_FILES /var/log/cron"
for log_file in $LOG_FILES; do
status "Checking log file $log_file"
tail -n $RECENT_LOG_LINES $log_file > /tmp/log_check
check_for_errors
done
exit $RESULT