Recommended etcd practices

This topic provides recommended performance and scalability practices for etcd in OKD.

Recommended etcd practices

Because etcd writes data to disk and persists proposals on disk, its performance depends on disk performance. Although etcd is not particularly I/O intensive, it requires a low latency block device for optimal performance and stability. Because etcd’s consensus protocol depends on persistently storing metadata to a log (WAL), etcd is sensitive to disk-write latency. Slow disks and disk activity from other processes can cause long fsync latencies.

Those latencies can cause etcd to miss heartbeats, not commit new proposals to the disk on time, and ultimately experience request timeouts and temporary leader loss. High write latencies also lead to an OpenShift API slowness, which affects cluster performance. Because of these reasons, avoid colocating other workloads on the control-plane nodes that are I/O sensitive or intensive and share the same underlying I/O infrastructure.

In terms of latency, run etcd on top of a block device that can write at least 50 IOPS of 8000 bytes long sequentially. That is, with a latency of 10ms, keep in mind that uses fdatasync to synchronize each write in the WAL. For heavy loaded clusters, sequential 500 IOPS of 8000 bytes (2 ms) are recommended. To measure those numbers, you can use a benchmarking tool, such as fio.

To achieve such performance, run etcd on machines that are backed by SSD or NVMe disks with low latency and high throughput. Consider single-level cell (SLC) solid-state drives (SSDs), which provide 1 bit per memory cell, are durable and reliable, and are ideal for write-intensive workloads.

The following hard disk features provide optimal etcd performance:

• Low latency to support fast read operation.

• High-bandwidth writes for faster compactions and defragmentation.

• High-bandwidth reads for faster recovery from failures.

• Solid state drives as a minimum selection, however NVMe drives are preferred.

• Server-grade hardware from various manufacturers for increased reliability.

• RAID 0 technology for increased performance.

• Dedicated etcd drives. Do not place log files or other heavy workloads on etcd drives.

Always benchmark by using utilities such as fio. You can use such utilities to continuously monitor the cluster performance as it increases.

Some key metrics to monitor on a deployed OKD cluster are p99 of etcd disk write ahead log duration and the number of etcd leader changes. Use Prometheus to track these metrics.

To validate the hardware for etcd before or after you create the OKD cluster, you can use fio.

Prerequisites

• Container runtimes such as Podman or Docker are installed on the machine that you’re testing.

• Data is written to the /var/lib/etcd path.

Procedure

• Run fio and analyze the results:

  • If you use Podman, run this command:

    $ sudo podman run --volume /var/lib/etcd:/var/lib/etcd:Z quay.io/cloud-bulldozer/etcd-perf

  • If you use Docker, run this command:

    $ sudo docker run --volume /var/lib/etcd:/var/lib/etcd:Z quay.io/cloud-bulldozer/etcd-perf

The output reports whether the disk is fast enough to host etcd by comparing the 99th percentile of the fsync metric captured from the run to see if it is less than 10 ms. A few of the most important etcd metrics that might affected by I/O performance are as follow:

• etcd_disk_wal_fsync_duration_seconds_bucket metric reports the etcd’s WAL fsync duration

• etcd_disk_backend_commit_duration_seconds_bucket metric reports the etcd backend commit latency duration

• etcd_server_leader_changes_seen_total metric reports the leader changes

Because etcd replicates the requests among all the members, its performance strongly depends on network input/output (I/O) latency. High network latencies result in etcd heartbeats taking longer than the election timeout, which results in leader elections that are disruptive to the cluster. A key metric to monitor on a deployed OKD cluster is the 99th percentile of etcd network peer latency on each etcd cluster member. Use Prometheus to track the metric.

The histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[2m])) metric reports the round trip time for etcd to finish replicating the client requests between the members. Ensure that it is less than 50 ms.

Additional resources

• How to use fio to check etcd disk performance in OKD

• etcd performance troubleshooting guide for OKD

Moving etcd to a different disk

You can move etcd from a shared disk to a separate disk to prevent or resolve performance issues.

The Machine Config Operator (MCO) is responsible for mounting a secondary disk for OKD 4 container storage.

Prerequisites

• You have installed the OpenShift CLI (oc).

• You have access to the cluster with cluster-admin privileges.

• The MachineConfigPool must match metadata.labels[machineconfiguration.openshift.io/role]. This applies to a controller, worker, or a custom pool.

Procedure

1. Attach the new disk to the cluster and verify that the disk is detected in the node by using the lsblk command in a debug shell:

   $ oc debug node/<node_name>

   # lsblk

   Note the device name of the new disk reported by the lsblk command.

2. Create a MachineConfig YAML file named etcd-mc.yml with contents such as the following, replacing instances of <new_disk_name> with the noted device name:

   apiVersion: machineconfiguration.openshift.io/v1
   kind: MachineConfig
   metadata:
     labels:
       machineconfiguration.openshift.io/role: master
     name: 98-var-lib-etcd
   spec:
     config:
       ignition:
         version: 3.2.0
       systemd:
         units:
         - contents: |
             [Unit]
             Description=Make File System on /dev/<new_disk_name>
             DefaultDependencies=no
             BindsTo=dev-<new_disk_name>.device
             After=dev-<new_disk_name>.device var.mount
             Before=systemd-fsck@dev-<new_disk_name>.service
             [Service]
             Type=oneshot
             RemainAfterExit=yes
             ExecStart=/usr/lib/systemd/systemd-makefs xfs /dev/<new_disk_name>
             TimeoutSec=0
             [Install]
             WantedBy=var-lib-containers.mount
           enabled: true
           name: systemd-mkfs@dev-<new_disk_name>.service
         - contents: |
             [Unit]
             Description=Mount /dev/<new_disk_name> to /var/lib/etcd
             Before=local-fs.target
             Requires=systemd-mkfs@dev-<new_disk_name>.service
             After=systemd-mkfs@dev-<new_disk_name>.service var.mount
             [Mount]
             What=/dev/<new_disk_name>
             Where=/var/lib/etcd
             Type=xfs
             Options=defaults,prjquota
             [Install]
             WantedBy=local-fs.target
           enabled: true
           name: var-lib-etcd.mount
         - contents: |
             [Unit]
             Description=Sync etcd data if new mount is empty
             DefaultDependencies=no
             After=var-lib-etcd.mount var.mount
             Before=crio.service
             [Service]
             Type=oneshot
             RemainAfterExit=yes
             ExecCondition=/usr/bin/test ! -d /var/lib/etcd/member
             ExecStart=/usr/sbin/setenforce 0
             ExecStart=/bin/rsync -ar /sysroot/ostree/deploy/rhcos/var/lib/etcd/ /var/lib/etcd/
             ExecStart=/usr/sbin/setenforce 1
             TimeoutSec=0
             [Install]
             WantedBy=multi-user.target graphical.target
           enabled: true
           name: sync-var-lib-etcd-to-etcd.service
         - contents: |
             [Unit]
             Description=Restore recursive SELinux security contexts
             DefaultDependencies=no
             After=var-lib-etcd.mount
             Before=crio.service
             [Service]
             Type=oneshot
             RemainAfterExit=yes
             ExecStart=/sbin/restorecon -R /var/lib/etcd/
             TimeoutSec=0
             [Install]
             WantedBy=multi-user.target graphical.target
           enabled: true
           name: restorecon-var-lib-etcd.service

3. Log in to the cluster as a user with cluster-admin privileges and create the machine configuration:

   $ oc login -u <username> -p <password>

   $ oc create -f etcd-mc.yml

   The nodes are updated and rebooted. After the reboot completes, the following events occur:

   • An XFS file system is created on the specified disk.

   • The disk mounts to /var/lib/etcd.

   • The content from /sysroot/ostree/deploy/rhcos/var/lib/etcd syncs to /var/lib/etcd.

   • A restore of SELinux labels is forced for /var/lib/etcd.

   • The old content is not removed.

4. After the nodes are on a separate disk, update the etcd-mc.yml file with contents such as the following, replacing instances of <new_disk_name> with the noted device name:

   apiVersion: machineconfiguration.openshift.io/v1
   kind: MachineConfig
   metadata:
     labels:
       machineconfiguration.openshift.io/role: master
     name: 98-var-lib-etcd
   spec:
     config:
       ignition:
         version: 3.2.0
       systemd:
         units:
         - contents: |
             [Unit]
             Description=Mount /dev/<new_disk_name> to /var/lib/etcd
             Before=local-fs.target
             After=var.mount
             [Mount]
             What=/dev/<new_disk_name>
             Where=/var/lib/etcd
             Type=xfs
             Options=defaults,prjquota
             [Install]
             WantedBy=local-fs.target
           enabled: true
           name: var-lib-etcd.mount

5. Apply the modified version that removes the logic for creating and syncing the device to prevent the nodes from rebooting:

   $ oc replace -f etcd-mc.yml

Verification steps

• Run the grep <new_disk_name> /proc/mounts command in a debug shell for the node to ensure that the disk mounted:

  $ oc debug node/<node_name>

  # grep <new_disk_name> /proc/mounts

  Example output

  /dev/nvme1n1 /var/lib/etcd xfs rw,seclabel,relatime,attr2,inode64,logbufs=8,logbsize=32k,prjquota 0 0

Additional resources

• Red Hat Enterprise Linux CoreOS (RHCOS)

Defragmenting etcd data

For large and dense clusters, etcd can suffer from poor performance if the keyspace grows too large and exceeds the space quota. Periodically maintain and defragment etcd to free up space in the data store. Monitor Prometheus for etcd metrics and defragment it when required; otherwise, etcd can raise a cluster-wide alarm that puts the cluster into a maintenance mode that accepts only key reads and deletes.

Monitor these key metrics:

• etcd_server_quota_backend_bytes, which is the current quota limit

• etcd_mvcc_db_total_size_in_use_in_bytes, which indicates the actual database usage after a history compaction

• etcd_mvcc_db_total_size_in_bytes, which shows the database size, including free space waiting for defragmentation

Defragment etcd data to reclaim disk space after events that cause disk fragmentation, such as etcd history compaction.

History compaction is performed automatically every five minutes and leaves gaps in the back-end database. This fragmented space is available for use by etcd, but is not available to the host file system. You must defragment etcd to make this space available to the host file system.

Defragmentation occurs automatically, but you can also trigger it manually.

Automatic defragmentation

The etcd Operator automatically defragments disks. No manual intervention is needed.

Verify that the defragmentation process is successful by viewing one of these logs:

• etcd logs

• cluster-etcd-operator pod

• operator status error log

Example log output for successful defragmentation

etcd member has been defragmented: <member_name>, memberID: <member_id>

Example log output for unsuccessful defragmentation

failed defrag on member: <member_name>, memberID: <member_id>: <error_message>

Manual defragmentation

A Prometheus alert indicates when you need to use manual defragmentation. The alert is displayed in two cases:

• When etcd uses more than 50% of its available space for more than 10 minutes

• When etcd is actively using less than 50% of its total database size for more than 10 minutes

You can also determine whether defragmentation is needed by checking the etcd database size in MB that will be freed by defragmentation with the PromQL expression: (etcd_mvcc_db_total_size_in_bytes - etcd_mvcc_db_total_size_in_use_in_bytes)/1024/1024

Follow this procedure to defragment etcd data on each etcd member.

Prerequisites

• You have access to the cluster as a user with the cluster-admin role.

Procedure

1. Determine which etcd member is the leader, because the leader should be defragmented last.

   1. Get the list of etcd pods:

      $ oc -n openshift-etcd get pods -l k8s-app=etcd -o wide

      Example output

      etcd-ip-10-0-159-225.example.redhat.com                3/3     Running     0          175m   10.0.159.225   ip-10-0-159-225.example.redhat.com   <none>           <none>
      etcd-ip-10-0-191-37.example.redhat.com                 3/3     Running     0          173m   10.0.191.37    ip-10-0-191-37.example.redhat.com    <none>           <none>
      etcd-ip-10-0-199-170.example.redhat.com                3/3     Running     0          176m   10.0.199.170   ip-10-0-199-170.example.redhat.com   <none>           <none>

   2. Choose a pod and run the following command to determine which etcd member is the leader:

      $ oc rsh -n openshift-etcd etcd-ip-10-0-159-225.example.redhat.com etcdctl endpoint status --cluster -w table

      Example output

      Defaulting container name to etcdctl.
      Use 'oc describe pod/etcd-ip-10-0-159-225.example.redhat.com -n openshift-etcd' to see all of the containers in this pod.
      +---------------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
      |         ENDPOINT          |        ID        | VERSION | DB SIZE | IS LEADER | IS LEARNER | RAFT TERM | RAFT INDEX | RAFT APPLIED INDEX | ERRORS |
      +---------------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
      |  https://10.0.191.37:2379 | 251cd44483d811c3 |   3.5.9 |  104 MB |     false |      false |         7 |      91624 |              91624 |        |
      | https://10.0.159.225:2379 | 264c7c58ecbdabee |   3.5.9 |  104 MB |     false |      false |         7 |      91624 |              91624 |        |
      | https://10.0.199.170:2379 | 9ac311f93915cc79 |   3.5.9 |  104 MB |      true |      false |         7 |      91624 |              91624 |        |
      +---------------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+

      Based on the IS LEADER column of this output, the https://10.0.199.170:2379 endpoint is the leader. Matching this endpoint with the output of the previous step, the pod name of the leader is etcd-ip-10-0-199-170.example.redhat.com.

2. Defragment an etcd member.

   1. Connect to the running etcd container, passing in the name of a pod that is not the leader:

      $ oc rsh -n openshift-etcd etcd-ip-10-0-159-225.example.redhat.com

   2. Unset the ETCDCTL_ENDPOINTS environment variable:

      sh-4.4# unset ETCDCTL_ENDPOINTS

   3. Defragment the etcd member:

      sh-4.4# etcdctl --command-timeout=30s --endpoints=https://localhost:2379 defrag

      Example output

      Finished defragmenting etcd member[https://localhost:2379]

      If a timeout error occurs, increase the value for --command-timeout until the command succeeds.

   4. Verify that the database size was reduced:

      sh-4.4# etcdctl endpoint status -w table --cluster

      Example output

      +---------------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
      |         ENDPOINT          |        ID        | VERSION | DB SIZE | IS LEADER | IS LEARNER | RAFT TERM | RAFT INDEX | RAFT APPLIED INDEX | ERRORS |
      +---------------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
      |  https://10.0.191.37:2379 | 251cd44483d811c3 |   3.5.9 |  104 MB |     false |      false |         7 |      91624 |              91624 |        |
      | https://10.0.159.225:2379 | 264c7c58ecbdabee |   3.5.9 |   41 MB |     false |      false |         7 |      91624 |              91624 |        | (1)
      | https://10.0.199.170:2379 | 9ac311f93915cc79 |   3.5.9 |  104 MB |      true |      false |         7 |      91624 |              91624 |        |
      +---------------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+

      This example shows that the database size for this etcd member is now 41 MB as opposed to the starting size of 104 MB.

   5. Repeat these steps to connect to each of the other etcd members and defragment them. Always defragment the leader last.

      Wait at least one minute between defragmentation actions to allow the etcd pod to recover. Until the etcd pod recovers, the etcd member will not respond.

3. If any NOSPACE alarms were triggered due to the space quota being exceeded, clear them.

   1. Check if there are any NOSPACE alarms:

      sh-4.4# etcdctl alarm list

      Example output

      memberID:12345678912345678912 alarm:NOSPACE

   2. Clear the alarms:

      sh-4.4# etcdctl alarm disarm

Setting tuning parameters for etcd

You can set the control plane hardware speed to "Standard", "Slower", or the default, which is "".

The default setting allows the system to decide which speed to use. This value enables upgrades from versions where this feature does not exist, as the system can select values from previous versions.

By selecting one of the other values, you are overriding the default. If you see many leader elections due to timeouts or missed heartbeats and your system is set to "" or "Standard", set the hardware speed to "Slower" to make the system more tolerant to the increased latency.

Changing hardware speed tolerance

To change the hardware speed tolerance for etcd, complete the following steps.

Procedure

1. Check to see what the current value is by entering the following command:

   $ oc describe etcd/cluster | grep "Control Plane Hardware Speed"

   Example output

   Control Plane Hardware Speed:  <VALUE>

   If the output is empty, the field has not been set and should be considered as the default (“”).

2. Change the value by entering the following command. Replace <value> with one of the valid values: "", "Standard", or "Slower":

   oc patch etcd/cluster --type=merge -p '{"spec": {"controlPlaneHardwareSpeed": "<value>"}}'

   The following table indicates the heartbeat interval and leader election timeout for each profile. These values are subject to change.

   Profile	ETCD_HEARTBEAT_INTERVAL	ETCD_LEADER_ELECTION_TIMEOUT
   “”	Varies depending on platform	Varies depending on platform
   Standard	100	1000
   Slower	500	2500

3. Review the output:

   Example output

   etcd.operator.openshift.io/cluster patched

   If you enter any value besides the valid values, error output is displayed. For example, if you entered "Faster" as the value, the output is as follows:

   Example output

   The Etcd "cluster" is invalid: spec.controlPlaneHardwareSpeed: Unsupported value: "Faster": supported values: "", "Standard", "Slower"

4. Verify that the value was changed by entering the following command:

   $ oc describe etcd/cluster | grep "Control Plane Hardware Speed"

   Example output

   Control Plane Hardware Speed:  ""

5. Wait for etcd pods to roll out:

   oc get pods -n openshift-etcd -w

   The following output shows the expected entries for master-0. Before you continue, wait until all masters show a status of 4/4 Running.

   Example output

   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     Pending             0          0s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     Pending             0          0s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     ContainerCreating   0          0s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     ContainerCreating   0          1s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           1/1     Running             0          2s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     Completed           0          34s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     Completed           0          36s
   installer-9-ci-ln-qkgs94t-72292-9clnd-master-0           0/1     Completed           0          36s
   etcd-guard-ci-ln-qkgs94t-72292-9clnd-master-0            0/1     Running             0          26m
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  4/4     Terminating         0          11m
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  4/4     Terminating         0          11m
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  0/4     Pending             0          0s
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  0/4     Init:1/3            0          1s
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  0/4     Init:2/3            0          2s
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  0/4     PodInitializing     0          3s
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  3/4     Running             0          4s
   etcd-guard-ci-ln-qkgs94t-72292-9clnd-master-0            1/1     Running             0          26m
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  3/4     Running             0          20s
   etcd-ci-ln-qkgs94t-72292-9clnd-master-0                  4/4     Running             0          20s

6. Enter the following command to review to the values:

   $ oc describe -n openshift-etcd pod/<ETCD_PODNAME> | grep -e HEARTBEAT_INTERVAL -e ELECTION_TIMEOUT

   These values might not have changed from the default.