Skip to content

feat: add raft member lag #365

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
liebman wants to merge 2 commits into
base: master
Choose a base branch
from
Open

feat: add raft member lag #365

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5355604
feat: add raft member lag
liebman Jun 3, 2025
20e8054
readme
liebman Jun 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ make
| consul_serf_lan_member_status | Status of member in the cluster. 1=Alive, 2=Leaving, 3=Left, 4=Failed. | member |
| consul_serf_wan_member_info | Information of member in the wan cluster. | member, dc, role, version |
| consul_serf_wan_member_status | Status of member in the wan cluster. 1=Alive, 2=Leaving, 3=Left, 4=Failed. | member, dc |
| consul_raft_lag | How far behind the leader a member is. | member, member_id |
| consul_catalog_services | How many services are in the cluster | |
| consul_service_tag | Tags of a service. | service_id, node, tag |
| consul_catalog_service_node_healthy | Is this service healthy on this node | service_id, node, service_name |
Expand Down
31 changes: 31 additions & 0 deletions pkg/exporter/consul_exporter.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,11 @@ var (
"Does Raft cluster have a leader (according to this node).",
nil, nil,
)
clusterLag = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "", "raft_lag"),
"How far behind the leader a node is.",
[]string{"member", "member_id"}, nil,
)
nodeCount = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "", "serf_lan_members"),
"How many members are in the cluster.",
Expand Down Expand Up @@ -210,6 +215,7 @@ func (e *Exporter) Describe(ch chan<- *prometheus.Desc) {
ch <- up
ch <- clusterServers
ch <- clusterLeader
ch <- clusterLag
ch <- nodeCount
ch <- memberInfo
ch <- memberStatus
Expand All @@ -232,6 +238,7 @@ func (e *Exporter) Collect(ch chan<- prometheus.Metric) {
if !e.agentOnly {
ok = e.collectPeersMetric(ch) && ok
ok = e.collectLeaderMetric(ch) && ok
ok = e.collectLagMetric(ch) && ok
ok = e.collectNodesMetric(ch) && ok
ok = e.collectMembersInfoMetric(ch) && ok
ok = e.collectMembersMetric(ch) && ok
Expand Down Expand Up @@ -282,6 +289,30 @@ func (e *Exporter) collectLeaderMetric(ch chan<- prometheus.Metric) bool {
return true
}

func (e *Exporter) collectLagMetric(ch chan<- prometheus.Metric) bool {
raft_config, err := e.client.Operator().RaftGetConfiguration(&e.queryOptions)
if err != nil {
e.logger.Error("Can't query consul", "err", err)
return false
}

leaderLastCommitIndex := uint64(0)

for _, raftServer := range raft_config.Servers {
if raftServer.Leader {
leaderLastCommitIndex = raftServer.LastIndex
}
}

for _, s := range raft_config.Servers {
lag := leaderLastCommitIndex - s.LastIndex
ch <- prometheus.MustNewConstMetric(
clusterLag, prometheus.GaugeValue, float64(lag), s.Node, s.ID,
)
}
return true
}

func (e *Exporter) collectNodesMetric(ch chan<- prometheus.Metric) bool {
nodes, _, err := e.client.Catalog().Nodes(&e.queryOptions)
if err != nil {
Expand Down