zulip/tools/ci/production-verify

#!/usr/bin/env bash
# This tests a Zulip production environment (installed via
# production-install) with some Nagios checks and other tools to
# verify that everything is working properly.
set -e
set -x

cat >>/etc/zulip/settings.py <<EOF
# CircleCI override settings above
AUTHENTICATION_BACKENDS = ( 'zproject.backends.EmailAuthBackend', )
NOREPLY_EMAIL_ADDRESS = 'noreply@circleci.example.com'
ALLOWED_HOSTS = []
EOF

if [ -f /etc/os-release ]; then
    os_info="$(
        . /etc/os-release
        printf '%s\n' "$VERSION_CODENAME"
    )"
    { read -r os_version_codename || true; } <<<"$os_info"
fi

check_header() {
    sed -i -e 's|Length: [0-9]\+\( [(][0-9]\+[.][0-9]K[)]\)\?|Length: <Length>|' -e "s|{nginx_version_string}|$nginx_version|g" "$success_header_file"
    if ! diff -ur /tmp/http-headers-processed "$success_header_file"; then
        set +x
        echo
        echo "FAILURE: The HTTP headers returned from loading the homepage on the server do not match the contents of tools/ci/success-http-headers.template.txt.  Typically, this means that the server threw a 500 when trying to load the homepage."
        echo "Displaying the contents of the server's error log:"
        echo
        cat /var/log/zulip/errors.log
        echo
        echo "Displaying the contents of the main server log:"
        echo
        cat /var/log/zulip/server.log
        exit 1
    fi
}

echo
echo "Now testing that the supervisord jobs are running properly"
echo
sleep 15 # Guaranteed to have a working supervisord process get an extra digit
if supervisorctl status | grep -vq RUNNING || supervisorctl status | sed 's/^.*uptime //' | grep -q 0:00:0; then
    set +x
    echo
    echo "FAILURE: Supervisor output shows daemons are crashing:"
    echo
    supervisorctl status
    echo
    echo "DEBUG: printing Zulip server's error log:"
    cat /var/log/zulip/errors.log
    echo
    echo "DEBUG: printing Zulip server's workers log:"
    cat /var/log/zulip/workers.log
    echo
    echo "DEBUG: printing Zulip server's tornado log:"
    cat /var/log/zulip/tornado.log
    exit 1
fi

# TODO: Ideally this would test actually logging in, but this is a start.
echo
echo "Now testing that the newly installed server's homepage loads"
echo

wget https://localhost -O /tmp/index.html --no-check-certificate -S 2>/tmp/wget-output || true # || true so we see errors.log if this 500s
grep -vi '\(Vary\|Content-Language\|expires\|issued by\|modified\|saved\|[.][.][.]\|Date\|[-][-]\)' /tmp/wget-output >/tmp/http-headers-processed

nginx_version="$(nginx -v 2>&1 | awk '{print $3, $4}' | xargs)"

# Simplify the diff by getting replacing 4-5 digit length numbers with <Length>.
sed -i 's|Length: [0-9]\+\( [(][0-9]\+[.][0-9]K[)]\)\?|Length: <Length>|' /tmp/http-headers-processed
if [ "$os_version_codename" = "buster" ] || [ "$os_version_codename" = "bullseye" ]; then
    success_header_file="/tmp/success-http-headers.template.debian.txt"
    check_header
else
    success_header_file="/tmp/success-http-headers.template.txt"
    check_header
fi

# Start the RabbitMQ queue worker related section
echo
echo "Now confirming all the RabbitMQ queue processors are correctly registered!"
echo
# These hacky shell scripts just extract the sorted list of queue processors, running and expected
supervisorctl status | cut -f1 -dR | cut -f2- -d: | grep events | cut -f1 -d" " | cut -f3- -d_ | cut -f1 -d- | sort -u >/tmp/running_queue_processors.txt
su zulip -c /home/zulip/deployments/current/scripts/lib/queue_workers.py | sort -u >/tmp/expected_queue_processors.txt
if ! diff /tmp/expected_queue_processors.txt /tmp/running_queue_processors.txt >/dev/null; then
    set +x
    echo "FAILURE: Runnable queue processors declared in zerver/worker/queue_processors.py "
    echo "do not match those in puppet/zulip/manifests/profile/base.pp"
    echo "See https://zulip.readthedocs.io/en/latest/subsystems/queuing.html for details."
    echo
    diff -ur /tmp/expected_queue_processors.txt /tmp/running_queue_processors.txt
    exit 1
fi

echo
echo "Now running RabbitMQ consumer Nagios tests"
echo
# First run the check that usually runs in cron and populates the state files
/home/zulip/deployments/current/scripts/nagios/check-rabbitmq-consumers

# Then, compute the list of all Django queue workers to run Nagios checks against
consumer_list=$(/home/zulip/deployments/current/scripts/lib/queue_workers.py --queue-type=consumer)
for consumer in $consumer_list; do
    if ! /usr/lib/nagios/plugins/zulip_app_frontend/check_rabbitmq_consumers "$consumer"; then
        set +x
        echo
        echo "FAILURE: Missing Nagios consumer for $consumer; displaying full consumer output:"
        set -x
        rabbitmqctl list_consumers
        supervisorctl status
        tail -n +1 /var/log/zulip/events*.log
        exit 1
    fi
done

# Some of the Nagios tests have been temporarily disabled to work
# around a Travis CI infrastructure issue.
echo
echo "Now running additional Nagios tests"
echo
if ! /usr/lib/nagios/plugins/zulip_app_frontend/check_queue_worker_errors \
    || ! su zulip -c "/usr/local/bin/process_fts_updates --nagios-check"; then # || \
    #   ! su zulip -c "/usr/lib/nagios/plugins/zulip_app_frontend/check_send_receive_time --site=https://127.0.0.1/api --nagios --insecure"; then
    set +x
    echo
    echo "FAILURE: Nagios checks don't pass:"
    echo
    echo "DEBUG: printing Zulip server's error log:"
    cat /var/log/zulip/errors.log
    exit 1
fi
echo "Production installation test successful!"
exit 0