System Health provides insight into the health of the Apache Kafka® cluster from both a broker and topic-centric perspective.
Note
This view is deprecated and not available by default in Confluent Platform 5.3 and later versions.
You can re-enable it by setting
confluent.controlcenter.deprecated.views.enable=true
in the appropriate
control-center.properties
file. RBAC cannot be enabled in
Control Center if you want to reinstate the legacy views, which cannot be
enforced with RBAC. The information presented in this view is also available
in various locations of the current redesigned GUI with RBAC enforced. For
updated monitoring and system health information, see View consumption details for a consumer group
and Brokers.
Navigation
After enabling the deprecated feature in the Control Center properties file, the System health
option appears in the cluster navigation submenu.
To explore system health in this view:
Click the Brokers and Topics tabs to navigate between broker and topic views.
Click on the usage metrics on the lefthand navigation to see more detailed information.
Click on the ellipsis (...
) and select View details from each row of the topics table.
From the Brokers view tab, you can select a percentile from the request latency percentile dropdown.
Tip
Request latency percentiles are only available in the Brokers tab.
Produce and Fetch Charts
When clients write data to Kafka, they send produce requests to leader brokers
which handle the produce requests and send responses back to the client.
When clients read data from Kafka, they send fetch requests to leader brokers
which handle the fetch requests and send responses back to the client. It is
important to monitor the throughput and latency of these produce
and fetch requests to ensure your cluster is performing optimally.
On each of the broker and topic tabs of the System Health view, you can
see a summary of the produce and fetch requests.
The left side shows the produced metrics, and the right side shows the fetched metrics.
In either the Brokers and Topics tab, you can hover the mouse cursor over an individual row of
the broker or topic table to overlay the request statistics for that individual broker or topic in the chart.
Hover over the top chart to see the request throughput for any given interval:
- Bytes produced/fetched per sec
- Total number of bytes per second of data produced to or fetched from this cluster.
- Successful requests
- Total number of successful requests produced to or fetched from the cluster in a one minute interval.
- Failed requests
- Total number of failed requests produced to or fetched from the cluster in a one minute interval.