Breaking changes: the binary is now named prometheus-alertmanager
New systemd service prometheus-alertmanager Added man pages Service now run under prometheus user New config file in /etc/default
This commit is contained in:
Robert-André Mauchin
parent
790f300588
commit
64a3dcbb20
|
|
@ -0,0 +1,4 @@
|
|||
Place here custom template definitions for the Alert Manager.
|
||||
|
||||
The default templates are defined in
|
||||
/usr/share/prometheus/alertmanager/default.tmpl
|
||||
|
|
@ -0,0 +1,88 @@
|
|||
Description: Change default paths to match Debian packaging
|
||||
Forwarded: not-needed
|
||||
Author: Martina Ferrari <tina@debian.org>
|
||||
Last-Update: 2019-10-29
|
||||
|
||||
---
|
||||
README.md | 2 +-
|
||||
cli/root.go | 8 ++++----
|
||||
cli/silence_add.go | 5 ++++-
|
||||
cmd/alertmanager/main.go | 4 ++--
|
||||
4 files changed, 11 insertions(+), 8 deletions(-)
|
||||
|
||||
--- a/cmd/alertmanager/main.go
|
||||
+++ b/cmd/alertmanager/main.go
|
||||
@@ -186,8 +186,8 @@ func run() int {
|
||||
}
|
||||
|
||||
var (
|
||||
- configFile = kingpin.Flag("config.file", "Alertmanager configuration file name.").Default("alertmanager.yml").String()
|
||||
- dataDir = kingpin.Flag("storage.path", "Base path for data storage.").Default("data/").String()
|
||||
+ configFile = kingpin.Flag("config.file", "Alertmanager configuration file name.").Default("/etc/prometheus/alertmanager.yml").String()
|
||||
+ dataDir = kingpin.Flag("storage.path", "Base path for data storage.").Default("/var/lib/prometheus/alertmanager/").String()
|
||||
retention = kingpin.Flag("data.retention", "How long to keep data for.").Default("120h").Duration()
|
||||
alertGCInterval = kingpin.Flag("alerts.gc-interval", "Interval between alert GC.").Default("30m").Duration()
|
||||
|
||||
--- a/cli/root.go
|
||||
+++ b/cli/root.go
|
||||
@@ -42,7 +42,7 @@ var (
|
||||
tlsInsecureSkipVerify bool
|
||||
versionCheck bool
|
||||
|
||||
- configFiles = []string{os.ExpandEnv("$HOME/.config/amtool/config.yml"), "/etc/amtool/config.yml"}
|
||||
+ configFiles = []string{os.ExpandEnv("$HOME/.config/prometheus/amtool.yml"), "/etc/prometheus/amtool.yml"}
|
||||
legacyFlags = map[string]string{"comment_required": "require-comment"}
|
||||
)
|
||||
|
||||
@@ -124,7 +124,7 @@ func Execute() {
|
||||
format.InitFormatFlags(app)
|
||||
|
||||
app.Flag("verbose", "Verbose running information").Short('v').BoolVar(&verbose)
|
||||
- app.Flag("alertmanager.url", "Alertmanager to talk to").URLVar(&alertmanagerURL)
|
||||
+ app.Flag("alertmanager.url", "Alertmanager to talk to").Default("http://localhost:9093/").URLVar(&alertmanagerURL)
|
||||
app.Flag("output", "Output formatter (simple, extended, json)").Short('o').Default("simple").EnumVar(&output, "simple", "extended", "json")
|
||||
app.Flag("timeout", "Timeout for the executed command").Default("30s").DurationVar(&timeout)
|
||||
app.Flag("tls.insecure.skip.verify", "Skip TLS certificate verification").BoolVar(&tlsInsecureSkipVerify)
|
||||
@@ -162,8 +162,8 @@ const (
|
||||
|
||||
Config File:
|
||||
The alertmanager tool will read a config file in YAML format from one of two
|
||||
-default config locations: $HOME/.config/amtool/config.yml or
|
||||
-/etc/amtool/config.yml
|
||||
+default config locations: $HOME/.config/prometheus/amtool.yml or
|
||||
+/etc/prometheus/amtool.yml
|
||||
|
||||
All flags can be given in the config file, but the following are the suited for
|
||||
static configuration:
|
||||
--- a/README.md
|
||||
+++ b/README.md
|
||||
@@ -307,7 +307,7 @@ amtool template render --template.glob='
|
||||
|
||||
### Configuration
|
||||
|
||||
-`amtool` allows a configuration file to specify some options for convenience. The default configuration file paths are `$HOME/.config/amtool/config.yml` or `/etc/amtool/config.yml`
|
||||
+`amtool` allows a configuration file to specify some options for convenience. The default configuration file paths are `$HOME/.config/prometheus/amtool/config.yml` or `/etc/prometheus/amtool/config.yml`
|
||||
|
||||
An example configuration file might look like the following:
|
||||
|
||||
--- a/cli/silence_add.go
|
||||
+++ b/cli/silence_add.go
|
||||
@@ -75,7 +75,7 @@ func configureSilenceAddCmd(cc *kingpin.
|
||||
c = &silenceAddCmd{}
|
||||
addCmd = cc.Command("add", silenceAddHelp)
|
||||
)
|
||||
- addCmd.Flag("author", "Username for CreatedBy field").Short('a').Default(username()).StringVar(&c.author)
|
||||
+ addCmd.Flag("author", "Username for CreatedBy field").Short('a').StringVar(&c.author)
|
||||
addCmd.Flag("require-comment", "Require comment to be set").Hidden().Default("true").BoolVar(&c.requireComment)
|
||||
addCmd.Flag("duration", "Duration of silence").Short('d').Default("1h").StringVar(&c.duration)
|
||||
addCmd.Flag("start", "Set when the silence should start. RFC3339 format 2006-01-02T15:04:05-07:00").StringVar(&c.start)
|
||||
@@ -108,6 +108,9 @@ func (c *silenceAddCmd) add(ctx context.
|
||||
return fmt.Errorf("no matchers specified")
|
||||
}
|
||||
|
||||
+ if c.author == "" {
|
||||
+ c.author = username()
|
||||
+ }
|
||||
var endsAt time.Time
|
||||
if c.end != "" {
|
||||
endsAt, err = time.Parse(time.RFC3339, c.end)
|
||||
|
|
@ -1,5 +1,6 @@
|
|||
# Generated by go2rpm 1.5.0
|
||||
%bcond_without check
|
||||
%global shortname prometheus-alertmanager
|
||||
|
||||
# https://github.com/prometheus/alertmanager
|
||||
%global goipath github.com/prometheus/alertmanager
|
||||
|
|
@ -24,9 +25,17 @@ Summary: Prometheus Alertmanager
|
|||
License: ASL 2.0
|
||||
URL: %{gourl}
|
||||
Source0: %{gosource}
|
||||
Source1: %{shortname}.service
|
||||
Source2: %{shortname}.sysusers
|
||||
Source3: %{shortname}.conf
|
||||
Source4: %{shortname}.yml
|
||||
Source5: README.templates
|
||||
# Replace defaults paths for config files
|
||||
Patch0: defaults-paths.patch
|
||||
|
||||
ExcludeArch: s390x
|
||||
|
||||
BuildRequires: systemd-rpm-macros
|
||||
BuildRequires: golang(github.com/alecthomas/units)
|
||||
BuildRequires: golang(github.com/cenkalti/backoff/v4)
|
||||
BuildRequires: golang(github.com/cespare/xxhash)
|
||||
|
|
@ -85,8 +94,14 @@ BuildRequires: golang(github.com/kylelemons/godebug/pretty)
|
|||
|
||||
%prep
|
||||
%goprep
|
||||
%patch0 -p1
|
||||
|
||||
%build
|
||||
LDFLAGS="-X github.com/prometheus/common/version.Version=%{version} \
|
||||
-X github.com/prometheus/common/version.Revision=%{release} \
|
||||
-X github.com/prometheus/common/version.Branch=tarball \
|
||||
-X github.com/prometheus/common/version.BuildDate=$(date -u -d@$SOURCE_DATE_EPOCH +%%Y%%m%%d)"
|
||||
|
||||
for cmd in cmd/* ; do
|
||||
%gobuild -o %{gobuilddir}/bin/$(basename $cmd) %{goipath}/$cmd
|
||||
done
|
||||
|
|
@ -95,6 +110,44 @@ done
|
|||
%gopkginstall
|
||||
install -m 0755 -vd %{buildroot}%{_bindir}
|
||||
install -m 0755 -vp %{gobuilddir}/bin/* %{buildroot}%{_bindir}/
|
||||
mv %{buildroot}%{_bindir}/alertmanager %{buildroot}%{_bindir}/%{shortname}
|
||||
pushd %{buildroot}%{_bindir}
|
||||
ln -s %{shortname} alertmanager
|
||||
popd
|
||||
|
||||
install -Dpm0644 %{S:4} %{buildroot}%{_sysconfdir}/prometheus/alertmanager.yml
|
||||
install -Dpm0644 %{S:5} %{buildroot}%{_sysconfdir}/prometheus/alertmanager_templates/README.templates
|
||||
install -dm750 %{buildroot}%{_sharedstatedir}/prometheus/alertmanager
|
||||
|
||||
install -Dm0644 %{S:1} %{buildroot}%{_unitdir}/%{shortname}.service
|
||||
install -Dm0644 %{S:2} %{buildroot}%{_sysusersdir}/%{shortname}.conf
|
||||
install -Dm0644 %{S:3} %{buildroot}%{_sysconfdir}/default/%{shortname}
|
||||
install -Dpm0644 template/default.tmpl %{buildroot}/%{_datadir}/prometheus/alertmanager/template/default.tmpl
|
||||
|
||||
# Build man pages.
|
||||
mkdir -vp %{buildroot}/%{_mandir}/man1/
|
||||
%{buildroot}%{_bindir}/%{shortname} --help-man > \
|
||||
%{buildroot}/%{_mandir}/man1/%{shortname}.1
|
||||
%{buildroot}%{_bindir}/amtool --help-man > \
|
||||
%{buildroot}/%{_mandir}/man1/amtool.1
|
||||
sed -i '/^ /d; /^.SH "NAME"/,+1c.SH "NAME"\nprometheus-alertmanager \\- The Prometheus alert manager' \
|
||||
%{buildroot}/%{_mandir}/man1/%{shortname}.1
|
||||
sed -i '/^ /d; /^.SH "NAME"/,+1c.SH "NAME"\namtool \\- Tooling for the Prometheus alert manager' \
|
||||
%{buildroot}/%{_mandir}/man1/amtool.1
|
||||
# Fix executable path in amtool examples
|
||||
sed -i 's/\.\/amtool/amtool/' %{buildroot}/%{_mandir}/man1/amtool.1
|
||||
|
||||
%pre
|
||||
%sysusers_create_compat %{SOURCE2}
|
||||
|
||||
%post
|
||||
%systemd_post %{shortname}.service
|
||||
|
||||
%preun
|
||||
%systemd_preun %{shortname}.service
|
||||
|
||||
%postun
|
||||
%systemd_postun_with_restart %{shortname}.service
|
||||
|
||||
%if %{with check}
|
||||
%check
|
||||
|
|
@ -105,6 +158,16 @@ install -m 0755 -vp %{gobuilddir}/bin/* %{buildroot}%{_bindir}/
|
|||
%license COPYRIGHT.txt LICENSE NOTICE
|
||||
%doc doc examples MAINTAINERS.md README.md CHANGELOG.md SECURITY.md
|
||||
%{_bindir}/*
|
||||
%{_datadir}/prometheus
|
||||
%{_mandir}/man1/%{shortname}.1*
|
||||
%{_mandir}/man1/amtool.1*
|
||||
%dir %{_sysconfdir}/prometheus
|
||||
%config(noreplace) %{_sysconfdir}/prometheus/alertmanager.yml
|
||||
%{_sysconfdir}/prometheus/alertmanager_templates
|
||||
%config(noreplace) %{_sysconfdir}/default/%{shortname}
|
||||
%attr(0750,prometheus,prometheus) %{_sharedstatedir}/prometheus
|
||||
%{_sysusersdir}/%{shortname}.conf
|
||||
%{_unitdir}/%{shortname}.service
|
||||
|
||||
%gopkgfiles
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,77 @@
|
|||
# Set the command-line arguments to pass to the server.
|
||||
# Due to shell scaping, to pass backslashes for regexes, you need to double
|
||||
# them (\\d for \d). If running under systemd, you need to double them again
|
||||
# (\\\\d to mean \d), and escape newlines too.
|
||||
ARGS=''
|
||||
|
||||
# prometheus-alertmanager supports the following options:
|
||||
#
|
||||
# --alerts.gc-interval=30m
|
||||
# Interval between alert GC.
|
||||
# --cluster.advertise-address=CLUSTER.ADVERTISE-ADDRESS
|
||||
# Explicit address to advertise in cluster.
|
||||
# --cluster.gossip-interval=200ms
|
||||
# Interval between sending gossip messages. By lowering this value (more
|
||||
# frequent) gossip messages are propagated across the cluster more quickly
|
||||
# at the expense of increased bandwidth.
|
||||
# --cluster.listen-address="0.0.0.0:9094"
|
||||
# Listen address for cluster. Set to empty string to disable HA mode.
|
||||
# --cluster.peer-timeout=15s
|
||||
# Time to wait between peers to send notifications.
|
||||
# --cluster.peer=CLUSTER.PEER...
|
||||
# Initial peers (may be repeated).
|
||||
# --cluster.probe-interval=1s
|
||||
# Interval between random node probes. Setting this lower (more frequent)
|
||||
# will cause the cluster to detect failed nodes more quickly at the expense
|
||||
# of increased bandwidth usage.
|
||||
# --cluster.probe-timeout=500ms
|
||||
# Timeout to wait for an ack from a probed node before assuming it is
|
||||
# unhealthy. This should be set to 99-percentile of RTT (round-trip time) on
|
||||
# your network.
|
||||
# --cluster.pushpull-interval=1m0s
|
||||
# Interval for gossip state syncs. Setting this interval lower (more
|
||||
# frequent) will increase convergence speeds across larger clusters at the
|
||||
# expense of increased bandwidth usage.
|
||||
# --cluster.reconnect-interval=10s
|
||||
# Interval between attempting to reconnect to lost peers.
|
||||
# --cluster.reconnect-timeout=6h0m0s
|
||||
# Length of time to attempt to reconnect to a lost peer.
|
||||
# --cluster.settle-timeout=1m0s
|
||||
# Maximum time to wait for cluster connections to settle before evaluating
|
||||
# notifications.
|
||||
# --cluster.tcp-timeout=10s
|
||||
# Timeout for establishing a stream connection with a remote node for a full
|
||||
# state sync, and for stream read and write operations.
|
||||
# --config.file="/etc/prometheus/alertmanager.yml"
|
||||
# Alertmanager configuration file name.
|
||||
# --data.retention=120h
|
||||
# How long to keep data for.
|
||||
# --log.format=logfmt
|
||||
# Output format of log messages. One of: [logfmt, json].
|
||||
# --log.level=info
|
||||
# Only log messages with the given severity or above. One of: [debug, info,
|
||||
# warn, error].
|
||||
# --storage.path="/var/lib/prometheus/alertmanager/"
|
||||
# Base path for data storage.
|
||||
# --template.default="/usr/share/prometheus/alertmanager/default.tmpl"
|
||||
# Path to default notification template.
|
||||
# --web.config.file=""
|
||||
# [EXPERIMENTAL] Path to configuration file that can enable TLS or
|
||||
# authentication.
|
||||
# --web.external-url=WEB.EXTERNAL-URL
|
||||
# The URL under which Alertmanager is externally reachable (for example, if
|
||||
# Alertmanager is served via a reverse proxy). Used for generating relative
|
||||
# and absolute links back to Alertmanager itself. If the URL has a path
|
||||
# portion, it will be used to prefix all HTTP endpoints served by
|
||||
# Alertmanager. If omitted, relevant URL components will be derived
|
||||
# automatically.
|
||||
# --web.get-concurrency=0
|
||||
# Maximum number of GET requests processed concurrently. If negative or
|
||||
# zero, the limit is GOMAXPROC or 8, whichever is larger.
|
||||
# --web.listen-address=":9093"
|
||||
# Address to listen on for the web interface and API.
|
||||
# --web.route-prefix=WEB.ROUTE-PREFIX
|
||||
# Prefix for the internal routes of web endpoints. Defaults to path of
|
||||
# --web.external-url.
|
||||
# --web.timeout=0
|
||||
# Timeout for HTTP requests. If negative or zero, no timeout is set.
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
[Unit]
|
||||
Description=Alertmanager for Prometheus
|
||||
Documentation=https://prometheus.io/docs/alerting/alertmanager/
|
||||
Requires=network-online.target
|
||||
After=network-online.target
|
||||
|
||||
[Service]
|
||||
Restart=on-failure
|
||||
User=prometheus
|
||||
EnvironmentFile=/etc/default/prometheus-alertmanager
|
||||
ExecStart=/usr/bin/prometheus-alertmanager $ARGS
|
||||
ExecReload=/bin/kill -HUP $MAINPID
|
||||
TimeoutStopSec=20s
|
||||
SendSIGKILL=no
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
#Type Name ID GECOS Home directory Shell
|
||||
u prometheus - "Prometheus user account" /var/lib/prometheus /sbin/nologin
|
||||
|
|
@ -0,0 +1,116 @@
|
|||
# Sample configuration.
|
||||
# See https://prometheus.io/docs/alerting/configuration/ for documentation.
|
||||
|
||||
global:
|
||||
# The smarthost and SMTP sender used for mail notifications.
|
||||
smtp_smarthost: 'localhost:25'
|
||||
smtp_from: 'alertmanager@example.org'
|
||||
smtp_auth_username: 'alertmanager'
|
||||
smtp_auth_password: 'password'
|
||||
|
||||
# The directory from which notification templates are read.
|
||||
templates:
|
||||
- '/etc/prometheus/alertmanager_templates/*.tmpl'
|
||||
|
||||
# The root route on which each incoming alert enters.
|
||||
route:
|
||||
# The labels by which incoming alerts are grouped together. For example,
|
||||
# multiple alerts coming in for cluster=A and alertname=LatencyHigh would
|
||||
# be batched into a single group.
|
||||
group_by: ['alertname', 'cluster', 'service']
|
||||
|
||||
# When a new group of alerts is created by an incoming alert, wait at
|
||||
# least 'group_wait' to send the initial notification.
|
||||
# This way ensures that you get multiple alerts for the same group that start
|
||||
# firing shortly after another are batched together on the first
|
||||
# notification.
|
||||
group_wait: 30s
|
||||
|
||||
# When the first notification was sent, wait 'group_interval' to send a batch
|
||||
# of new alerts that started firing for that group.
|
||||
group_interval: 5m
|
||||
|
||||
# If an alert has successfully been sent, wait 'repeat_interval' to
|
||||
# resend them.
|
||||
repeat_interval: 3h
|
||||
|
||||
# A default receiver
|
||||
receiver: team-X-mails
|
||||
|
||||
# All the above attributes are inherited by all child routes and can
|
||||
# overwritten on each.
|
||||
|
||||
# The child route trees.
|
||||
routes:
|
||||
# This routes performs a regular expression match on alert labels to
|
||||
# catch alerts that are related to a list of services.
|
||||
- match_re:
|
||||
service: ^(foo1|foo2|baz)$
|
||||
receiver: team-X-mails
|
||||
# The service has a sub-route for critical alerts, any alerts
|
||||
# that do not match, i.e. severity != critical, fall-back to the
|
||||
# parent node and are sent to 'team-X-mails'
|
||||
routes:
|
||||
- match:
|
||||
severity: critical
|
||||
receiver: team-X-pager
|
||||
- match:
|
||||
service: files
|
||||
receiver: team-Y-mails
|
||||
|
||||
routes:
|
||||
- match:
|
||||
severity: critical
|
||||
receiver: team-Y-pager
|
||||
|
||||
# This route handles all alerts coming from a database service. If there's
|
||||
# no team to handle it, it defaults to the DB team.
|
||||
- match:
|
||||
service: database
|
||||
receiver: team-DB-pager
|
||||
# Also group alerts by affected database.
|
||||
group_by: [alertname, cluster, database]
|
||||
routes:
|
||||
- match:
|
||||
owner: team-X
|
||||
receiver: team-X-pager
|
||||
- match:
|
||||
owner: team-Y
|
||||
receiver: team-Y-pager
|
||||
|
||||
|
||||
# Inhibition rules allow to mute a set of alerts given that another alert is
|
||||
# firing.
|
||||
# We use this to mute any warning-level notifications if the same alert is
|
||||
# already critical.
|
||||
inhibit_rules:
|
||||
- source_match:
|
||||
severity: 'critical'
|
||||
target_match:
|
||||
severity: 'warning'
|
||||
# Apply inhibition if the alertname is the same.
|
||||
equal: ['alertname', 'cluster', 'service']
|
||||
|
||||
|
||||
receivers:
|
||||
- name: 'team-X-mails'
|
||||
email_configs:
|
||||
- to: 'team-X+alerts@example.org'
|
||||
|
||||
- name: 'team-X-pager'
|
||||
email_configs:
|
||||
- to: 'team-X+alerts-critical@example.org'
|
||||
pagerduty_configs:
|
||||
- service_key: <team-X-key>
|
||||
|
||||
- name: 'team-Y-mails'
|
||||
email_configs:
|
||||
- to: 'team-Y+alerts@example.org'
|
||||
|
||||
- name: 'team-Y-pager'
|
||||
pagerduty_configs:
|
||||
- service_key: <team-Y-key>
|
||||
|
||||
- name: 'team-DB-pager'
|
||||
pagerduty_configs:
|
||||
- service_key: <team-DB-key>
|
||||
Loading…
Reference in New Issue