Add documentation for configuring alerts using Alertmanager #603

Workflow file for this run

	name: Tests
	on:
	- push
	- pull_request

	jobs:
	build-microceph:
	name: Build microceph snap
	runs-on: ubuntu-22.04
	env:
	SNAPCRAFT_BUILD_ENVIRONMENT: "lxd"
	steps:
	- name: Checkout code
	uses: actions/checkout@v3

	- name: Clear FORWARD firewall rules
	run: \|
	# Docker can inject rules causing firewall conflicts
	sudo iptables -P FORWARD ACCEPT \|\| true
	sudo ip6tables -P FORWARD ACCEPT \|\| true
	sudo iptables -F FORWARD \|\| true
	sudo ip6tables -F FORWARD \|\| true

	- name: Install dependencies
	run: \|
	sudo snap refresh
	sudo snap set lxd daemon.group=adm
	sudo lxd init --auto
	sudo snap install snapcraft --classic
	snap list

	- name: Build snaps
	run: snapcraft

	- name: Upload snap artifact
	if: always()
	uses: actions/upload-artifact@v3
	with:
	name: snaps
	path: "*.snap"
	retention-days: 5

	single-system-tests:
	name: Single node testing
	runs-on: ubuntu-22.04
	needs: build-microceph
	steps:
	- name: Download snap
	uses: actions/download-artifact@v3
	with:
	name: snaps
	- name: Install and setup
	run: \|
	set -eux
	sudo snap install --dangerous microceph_*.snap
	sudo snap connect microceph:block-devices
	sudo snap connect microceph:hardware-observe
	# defer dm-crypt enablement for later.

	# Daemon needs restart for the added dm-crypt connection
	sudo snap restart microceph.daemon

	sudo microceph cluster bootstrap
	sudo microceph.ceph version
	sudo microceph.ceph status

	# Verify metadata.yaml
	meta=/var/snap/microceph/current/conf/metadata.yaml
	cat $meta
	grep -q ceph-version $meta

	# Allow ceph to notice no OSD are present
	sleep 30
	sudo microceph.ceph status
	sudo microceph.ceph health
	sudo microceph.ceph health \| grep -q "OSD count 0 < osd_pool_default_size 3"

	# Verify auto crush rule
	sudo microceph.ceph osd crush rule ls \| grep -F microceph_auto_osd

	- name: Add OSD with failure
	run: \|
	set -eux
	loop_file="$(sudo mktemp -p /mnt XXXX.img)"
	sudo truncate -s 1G "${loop_file}"
	loop_dev="$(sudo losetup --show -f "${loop_file}")"

	minor="${loop_dev##/dev/loop}"
	sudo mknod -m 0660 "/dev/sdi21" b 7 "${minor}"

	set +e
	sudo microceph disk add --wipe "/dev/sdi21" --encrypt \|\| rc="$?"
	if [[ $rc -eq 0 ]] ; then echo "FDE should fail without dmcrypt: $rc"; exit 1; fi

	- name: Add OSDs
	run: \|
	set -eux
	# Enable dm-crypt connection and restart microceph daemon
	sudo snap connect microceph:dm-crypt
	sudo snap restart microceph.daemon
	# Add OSDs backed by loop devices on /mnt (ephemeral "large" disk attached to GitHub action runners)
	i=0
	for l in a b c; do
	loop_file="$(sudo mktemp -p /mnt XXXX.img)"
	sudo truncate -s 1G "${loop_file}"
	loop_dev="$(sudo losetup --show -f "${loop_file}")"

	# XXX: the block-devices plug doesn't allow accessing /dev/loopX
	# devices so we make those same devices available under alternate
	# names (/dev/sdiY) that are not used inside GitHub Action runners
	minor="${loop_dev##/dev/loop}"
	sudo mknod -m 0660 "/dev/sdi${l}" b 7 "${minor}"
	sudo microceph disk add --wipe "/dev/sdi${l}" --encrypt
	done

	# Wait for OSDs to become up
	sleep 30

	- name: Enable RGW
	run: \|
	set -ux

	sudo microceph enable rgw
	# Wait for RGW to settle
	for i in $(seq 1 8); do
	res=$( ( sudo microceph.ceph status \| grep -cF "rgw: 1 daemon" ) \|\| true )
	if [[ $res -gt 0 ]] ; then
	echo "Found rgw daemon"
	break
	else
	echo -n '.'
	sleep 5
	fi
	done

	- name: Run system tests
	run: \|
	set -eux
	# Show ceph's status
	sudo microceph.ceph status

	# Confirm ceph is healthy and services started
	sudo microceph.ceph status \| grep -F "mon: 1 daemons"
	sudo microceph.ceph status \| grep -E "mgr: .*active, "
	sudo microceph.ceph status \| grep -F "osd: 3 osds"
	sudo microceph.ceph status \| grep -F "rgw: 1 daemon"

	# Check health after restart
	sudo snap stop microceph
	sudo snap start microceph
	sleep 2m

	sudo microceph.ceph status
	sudo microceph.ceph status \| grep -F "mon: 1 daemons"
	sudo microceph.ceph status \| grep -E "mgr: .*active, "
	sudo microceph.ceph status \| grep -F "osd: 3 osds"
	sudo microceph.ceph status \| grep -F "rgw: 1 daemon"
	pgrep ceph-osd \|\| { echo "No ceph-osd process found" ; exit 1; }

	- name: Exercise RGW
	run: \|
	set -eux
	sudo microceph.ceph status
	sudo systemctl status snap.microceph.rgw
	sudo microceph.radosgw-admin user create --uid=test --display-name=test
	sudo microceph.radosgw-admin key create --uid=test --key-type=s3 --access-key fooAccessKey --secret-key fooSecretKey
	sudo apt-get -qq install s3cmd
	echo hello-radosgw > ~/test.txt
	s3cmd --host localhost --host-bucket="localhost/%(bucket)" --access_key=fooAccessKey --secret_key=fooSecretKey --no-ssl mb s3://testbucket
	s3cmd --host localhost --host-bucket="localhost/%(bucket)" --access_key=fooAccessKey --secret_key=fooSecretKey --no-ssl put -P ~/test.txt s3://testbucket
	curl -s http://localhost/testbucket/test.txt \| grep -F hello-radosgw

	- name: Test Cluster Config
	run: \|
	set -eux
	cip=$(ip -4 -j route \| jq -r '.[] \| select(.dst \| contains("default")) \| .prefsrc' \| tr -d '[:space:]')

	# pre config set timestamp for service age
	ts=$(sudo systemctl show --property ActiveEnterTimestampMonotonic snap.microceph.osd.service \| cut -d= -f2)

	# set config
	sudo microceph cluster config set cluster_network $cip/8 --wait

	# post config set timestamp for service age
	ts2=$(sudo systemctl show --property ActiveEnterTimestampMonotonic snap.microceph.osd.service \| cut -d= -f2)

	# Check config output
	output=$(sudo microceph cluster config get cluster_network \| grep -cim1 'cluster_network')
	if [[ $output -lt 1 ]] ; then echo "config check failed: $output"; exit 1; fi

	# Check service restarted
	if [ $ts2 -lt $ts ]; then echo "config check failed: TS1: $ts2 TS2: $ts3"; exit 1; fi

	# reset config
	sudo microceph cluster config reset cluster_network --wait

	# post config reset timestamp for service age
	ts3=$(sudo systemctl show --property ActiveEnterTimestampMonotonic snap.microceph.osd.service \| cut -d= -f2)

	# Check service restarted
	if [ $ts3 -lt $ts2 ]; then echo "config check failed: TS2: $ts2 TS3: $ts3"; exit 1; fi

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add documentation for configuring alerts using Alertmanager #603

Workflow file

Add documentation for configuring alerts using Alertmanager #603

Jobs

Run details

Workflow file for this run