Monitoring overview

The aim of this part of the documentation is to explain the Ceph monitoring stack and the meaning of the main Ceph metrics.

With a good understand of the Ceph monitoring stack and metrics users can create customized monitoring tools, like Prometheus queries, Grafana dashboards, or scripts.

Ceph Monitoring stack

Ceph provides a default monitoring stack wich is installed by cephadm and explained in the Monitoring Services section of the cephadm documentation.

Ceph metrics

The main source for Ceph metrics are the performance counters exposed by each Ceph daemon. The Perf counters are native Ceph monitoring data

Performance counters are transformed into standard Prometheus metrics by the Ceph exporter daemon. This daemon runs on every Ceph cluster host and exposes a metrics end point where all the performance counters exposed by all the Ceph daemons running in the host are published in the form of Prometheus metrics.

In addition to the Ceph exporter, there is another agent to expose Ceph metrics. It is the Prometheus manager module, wich exposes metrics related to the whole cluster, basically metrics that are not produced by individual Ceph daemons.

The main source for obtaining Ceph metrics is the metrics endpoint exposed by the Cluster Prometheus server. Ceph can provide you with the Prometheus endpoint where you can obtain the complete list of metrics (coming from Ceph exporter daemons and Prometheus manager module) and exeute queries.

Use the following command to obtain the Prometheus server endpoint in your cluster:

Example:

# ceph orch ps --service_name prometheus
NAME                         HOST                          PORTS   STATUS          REFRESHED  AGE  MEM USE  MEM LIM  VERSION  IMAGE ID      CONTAINER ID
prometheus.cephtest-node-00  cephtest-node-00.cephlab.com  *:9095  running (103m)    50s ago   5w     142M        -  2.33.4   514e6a882f6e  efe3cbc2e521

With this information you can connect to http://cephtest-node-00.cephlab.com:9095 to access the Prometheus server interface.

And the complete list of metrics (with help) for your cluster will be available in:

http://cephtest-node-00.cephlab.com:9095/api/v1/targets/metadata

It is good to outline that the main tool allowing users to observe and monitor a Ceph cluster is the Ceph dashboard. It provides graphics where the most important cluster and service metrics are represented. Most of the examples in this document are extracted from the dashboard graphics or extrapolated from the metrics exposed by the Ceph dashboard.

Performance metrics

Main metrics used to measure Cluster Ceph performance:

All metrics have the following labels: ceph_daemon: identifier of the OSD daemon generating the metric instance: the IP address of the ceph exporter instance exposing the metric. job: prometheus scrape job

Example:

ceph_osd_op_r{ceph_daemon="osd.0", instance="192.168.122.7:9283", job="ceph"} = 73981

Cluster I/O (throughput): Use ceph_osd_op_r_out_bytes and ceph_osd_op_w_in_bytes to obtain the cluster throughput generated by clients

Example:

Writes (B/s):
sum(irate(ceph_osd_op_w_in_bytes[1m]))

Reads (B/s):
sum(irate(ceph_osd_op_r_out_bytes[1m]))

Cluster I/O (operations): Use ceph_osd_op_r, ceph_osd_op_w to obtain the number of operations generated by clients

Example:

Writes (ops/s):
sum(irate(ceph_osd_op_w[1m]))

Reads (ops/s):
sum(irate(ceph_osd_op_r[1m]))

Latency: Use ceph_osd_op_latency_sum wich represents the delay before a OSD transfer of data begins following a client instruction for its transfer

Example:

sum(irate(ceph_osd_op_latency_sum[1m]))

OSD performance

The previous explained cluster performance metrics are based in OSD metrics, selecting the right label we can obtain for a single OSD the same performance information explained for the cluster:

Example:

OSD 0 read latency
irate(ceph_osd_op_r_latency_sum{ceph_daemon=~"osd.0"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m])

OSD 0 write IOPS
irate(ceph_osd_op_w{ceph_daemon=~"osd.0"}[1m])

OSD 0 write thughtput (bytes)
irate(ceph_osd_op_w_in_bytes{ceph_daemon=~"osd.0"}[1m])

OSD.0 total raw capacity available
ceph_osd_stat_bytes{ceph_daemon="osd.0", instance="cephtest-node-00.cephlab.com:9283", job="ceph"} = 536451481

Physical disk performance:

Combining Prometheus node_exporter metrics with Ceph metrics we can have information about the performance provided by physical disks used by OSDs.

Example:

Read latency of device used by OSD 0:
label_replace(irate(node_disk_read_time_seconds_total[1m]) / irate(node_disk_reads_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

Write latency of device used by OSD 0
label_replace(irate(node_disk_write_time_seconds_total[1m]) / irate(node_disk_writes_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

IOPS (device used by OSD.0)
reads:
label_replace(irate(node_disk_reads_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

writes:
label_replace(irate(node_disk_writes_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

Throughput (device used by OSD.0)
reads:
label_replace(irate(node_disk_read_bytes_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

writes:
label_replace(irate(node_disk_written_bytes_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

Physical Device Utilization (%) for OSD.0 in the last 5 minutes
label_replace(irate(node_disk_io_time_seconds_total[5m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"osd.0"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")

Pool metrics

These metrics have the following labels: instance: the ip address of the Ceph exporter daemon producing the metric. pool_id: identifier of the pool job: prometheus scrape job

  • ceph_pool_metadata: Information about the pool It can be used together with other metrics to provide more contextual information in queries and graphs. Apart of the three common labels this metric provide the following extra labels:

    • compression_mode: compression used in the pool (lz4, snappy, zlib, zstd, none). Example: compression_mode=”none”

    • description: brief description of the pool type (replica:number of replicas or Erasure code: ec profile). Example: description=”replica:3”

    • name: name of the pool. Example: name=”.mgr”

    • type: type of pool (replicated/erasure code). Example: type=”replicated”

  • ceph_pool_bytes_used: Total raw capacity consumed by user data and associated overheads by pool (metadata + redundancy):

  • ceph_pool_stored: Total of CLIENT data stored in the pool

  • ceph_pool_compress_under_bytes: Data eligible to be compressed in the pool

  • ceph_pool_compress_bytes_used: Data compressed in the pool

  • ceph_pool_rd: CLIENT read operations per pool (reads per second)

  • ceph_pool_rd_bytes: CLIENT read operations in bytes per pool

  • ceph_pool_wr: CLIENT write operations per pool (writes per second)

  • ceph_pool_wr_bytes: CLIENT write operation in bytes per pool

Useful queries:

Total raw capacity available in the cluster:
sum(ceph_osd_stat_bytes)

Total raw capacity consumed in the cluster (including metadata + redundancy):
sum(ceph_pool_bytes_used)

Total of CLIENT data stored in the cluster:
sum(ceph_pool_stored)

Compression savings:
sum(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used)

CLIENT IOPS for a pool (testrbdpool)
reads: irate(ceph_pool_rd[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"testrbdpool"}
writes: irate(ceph_pool_wr[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"testrbdpool"}

CLIENT Throughput for a pool
reads: irate(ceph_pool_rd_bytes[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"testrbdpool"}
writes: irate(ceph_pool_wr_bytes[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"testrbdpool"}

Object metrics

These metrics have the following labels: instance: the ip address of the ceph exporter daemon providing the metric instance_id: identifier of the rgw daemon job: prometheus scrape job

Example:

ceph_rgw_req{instance="192.168.122.7:9283", instance_id="154247", job="ceph"} = 12345

Generic metrics

  • ceph_rgw_metadata: Provides generic information about the RGW daemon. It can be used together with other metrics to provide more contextual information in queries and graphs. Apart from the three common labels, this metric provides the following extra labels:

    • ceph_daemon: Name of the Ceph daemon. Example: ceph_daemon=”rgw.rgwtest.cephtest-node-00.sxizyq”,

    • ceph_version: Version of Ceph daemon. Example: ceph_version=”ceph version 17.2.6 (d7ff0d10654d2280e08f1ab989c7cdf3064446a5) quincy (stable)”,

    • hostname: Name of the host where the daemon runs. Example: hostname:”cephtest-node-00.cephlab.com”,

  • ceph_rgw_req: Number total of requests for the daemon (GET+PUT+DELETE)

    Useful to detect bottlenecks and optimize load distribution.

  • ceph_rgw_qlen: RGW operations queue length for the daemon.

    Useful to detect bottlenecks and optimize load distribution.

  • ceph_rgw_failed_req: Aborted requests.

    Useful to detect daemon errors

Useful queries

The average of get latencies:
rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata

The average of put latencies:
rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata

Total requests per second:
rate(ceph_rgw_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata

Total number of "other" operations (LIST, DELETE)
rate(ceph_rgw_req[30s]) -  (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))

GET latencies
rate(ceph_rgw_get_initial_lat_sum[30s]) /  rate(ceph_rgw_get_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata

PUT latencies
rate(ceph_rgw_put_initial_lat_sum[30s]) /  rate(ceph_rgw_put_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata

Bandwidth consumed by GET operations
sum(rate(ceph_rgw_get_b[30s]))

Bandwidth consumed by PUT operations
sum(rate(ceph_rgw_put_b[30s]))

Bandwidth consumed by RGW instance (PUTs + GETs)
sum by (instance_id) (rate(ceph_rgw_get_b[30s]) + rate(ceph_rgw_put_b[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata

Http errors:
rate(ceph_rgw_failed_req[30s])

Filesystem Metrics

These metrics have the following labels: ceph_daemon: The name of the MDS daemon instance: the ip address (and port) of of the Ceph exporter daemon exposing the metric job: prometheus scrape job

Example:

ceph_mds_request{ceph_daemon="mds.test.cephtest-node-00.hmhsoh", instance="192.168.122.7:9283", job="ceph"} = 1452

Main metrics

  • ceph_mds_metadata: Provides general information about the MDS daemon. It can be used together with other metrics to provide more contextual information in queries and graphs. It provides the following extra labels:

    • ceph_version: MDS daemon Ceph version

    • fs_id: filesystem cluster id

    • hostname: Host name where the MDS daemon runs

    • public_addr: Public address where the MDS daemon runs

    • rank: Rank of the MDS daemon

Example:

ceph_mds_metadata{ceph_daemon="mds.test.cephtest-node-00.hmhsoh", ceph_version="ceph version 17.2.6 (d7ff0d10654d2280e08f1ab989c7cdf3064446a5) quincy (stable)", fs_id="-1", hostname="cephtest-node-00.cephlab.com", instance="cephtest-node-00.cephlab.com:9283", job="ceph", public_addr="192.168.122.145:6801/118896446", rank="-1"}
  • ceph_mds_request: Total number of requests for the MDs daemon

  • ceph_mds_reply_latency_sum: Reply latency total

  • ceph_mds_reply_latency_count: Reply latency count

  • ceph_mds_server_handle_client_request: Number of client requests

  • ceph_mds_sessions_session_count: Session count

  • ceph_mds_sessions_total_load: Total load

  • ceph_mds_sessions_sessions_open: Sessions currently open

  • ceph_mds_sessions_sessions_stale: Sessions currently stale

  • ceph_objecter_op_r: Number of read operations

  • ceph_objecter_op_w: Number of write operations

  • ceph_mds_root_rbytes: Total number of bytes managed by the daemon

  • ceph_mds_root_rfiles: Total number of files managed by the daemon

Useful queries:

Total MDS daemons read workload:
sum(rate(ceph_objecter_op_r[1m]))

Total MDS daemons write workload:
sum(rate(ceph_objecter_op_w[1m]))

MDS daemon read workload: (daemon name is "mdstest")
sum(rate(ceph_objecter_op_r{ceph_daemon=~"mdstest"}[1m]))

MDS daemon write workload: (daemon name is "mdstest")
sum(rate(ceph_objecter_op_r{ceph_daemon=~"mdstest"}[1m]))

The average of reply latencies:
rate(ceph_mds_reply_latency_sum[30s]) / rate(ceph_mds_reply_latency_count[30s])

Total requests per second:
rate(ceph_mds_request[30s]) * on (instance) group_right (ceph_daemon) ceph_mds_metadata

Block metrics

By default RBD metrics for images are not available in order to provide the best performance in the prometheus manager module.

To produce metrics for RBD images it is needed to configure properly the manager option mgr/prometheus/rbd_stats_pools. For more information please see Ceph Health Checks

These metrics have the following labels: image: Name of the image which produces the metric value. instance: Node where the rbd metric is produced. (It points to the Ceph exporter daemon) job: Name of the Prometheus scrape job. pool: Image pool name.

Example:

ceph_rbd_read_bytes{image="test2", instance="cephtest-node-00.cephlab.com:9283", job="ceph", pool="testrbdpool"}

Main metrics

  • ceph_rbd_read_bytes: RBD image bytes read

  • ceph_rbd_read_latency_count: RBD image reads latency count

  • ceph_rbd_read_latency_sum: RBD image reads latency total

  • ceph_rbd_read_ops: RBD image reads count

  • ceph_rbd_write_bytes: RBD image bytes written

  • ceph_rbd_write_latency_count: RBD image writes latency count

  • ceph_rbd_write_latency_sum: RBD image writes latency total

  • ceph_rbd_write_ops: RBD image writes count

Useful queries

The average of read latencies:
rate(ceph_rbd_read_latency_sum[30s]) / rate(ceph_rbd_read_latency_count[30s]) * on (instance) group_left (ceph_daemon) ceph_rgw_metadata