TaskTracker Metrics

In addition to these base metrics, many aggregate metrics are available. If an entity type has parents defined, you can formulate all possible aggregate metrics using the formula base_metric_across_parents.

In addition, metrics for aggregate totals can be formed by adding the prefix total_ to the front of the metric name.

Use the type-ahead feature in the Cloudera Manager chart browser to find the exact aggregate metric name, in case the plural form does not end in "s".

For example, the following metric names may be valid for TaskTracker:

  • alerts_rate_across_clusters
  • total_alerts_rate_across_clusters

Some metrics, such as alerts_rate, apply to nearly every metric context. Others only apply to a certain service or role.

For more information about metrics, see Cloudera Manager Metrics and Metric Aggregation.

Metric Name Description Unit Parents CDH Version
alerts_rate The number of alerts. events per second cluster, mapreduce, rack CDH 5
cgroup_cpu_system_rate CPU usage of the role's cgroup seconds per second cluster, mapreduce, rack CDH 5
cgroup_cpu_user_rate User Space CPU usage of the role's cgroup seconds per second cluster, mapreduce, rack CDH 5
cgroup_mem_page_cache Page cache usage of the role's cgroup bytes cluster, mapreduce, rack CDH 5
cgroup_mem_rss Resident memory of the role's cgroup bytes cluster, mapreduce, rack CDH 5
cgroup_mem_swap Swap usage of the role's cgroup bytes cluster, mapreduce, rack CDH 5
cgroup_read_bytes_rate Bytes read from all disks by the role's cgroup bytes per second cluster, mapreduce, rack CDH 5
cgroup_read_ios_rate Number of read I/O operations from all disks by the role's cgroup ios per second cluster, mapreduce, rack CDH 5
cgroup_write_bytes_rate Bytes written to all disks by the role's cgroup bytes per second cluster, mapreduce, rack CDH 5
cgroup_write_ios_rate Number of write I/O operations to all disks by the role's cgroup ios per second cluster, mapreduce, rack CDH 5
cpu_system_rate Total System CPU seconds per second cluster, mapreduce, rack CDH 5
cpu_system_with_descendants_rate The total system CPU time for this process and all its descendant processes seconds per second cluster, mapreduce, rack CDH 5
cpu_user_rate Total CPU user time seconds per second cluster, mapreduce, rack CDH 5
cpu_user_with_descendants_rate The total user CPU time for this process and all its descendant processes seconds per second cluster, mapreduce, rack CDH 5
events_critical_rate The number of critical events. events per second cluster, mapreduce, rack CDH 5
events_important_rate The number of important events. events per second cluster, mapreduce, rack CDH 5
events_informational_rate The number of informational events. events per second cluster, mapreduce, rack CDH 5
failed_dirs Failed Directories directories cluster, mapreduce, rack CDH 5
fd_max Maximum number of file descriptors file descriptors cluster, mapreduce, rack CDH 5
fd_open Open file descriptors. file descriptors cluster, mapreduce, rack CDH 5
health_bad_rate Percentage of Time with Bad Health seconds per second cluster, mapreduce, rack CDH 5
health_concerning_rate Percentage of Time with Concerning Health seconds per second cluster, mapreduce, rack CDH 5
health_disabled_rate Percentage of Time with Disabled Health seconds per second cluster, mapreduce, rack CDH 5
health_good_rate Percentage of Time with Good Health seconds per second cluster, mapreduce, rack CDH 5
health_unknown_rate Percentage of Time with Unknown Health seconds per second cluster, mapreduce, rack CDH 5
jvm_blocked_threads Blocked threads threads cluster, mapreduce, rack CDH 5
jvm_gc_rate Number of garbage collections garbage collections per second cluster, mapreduce, rack CDH 5
jvm_gc_time_ms_rate Total time spent garbage collecting. ms per second cluster, mapreduce, rack CDH 5
jvm_heap_committed_mb Total amount of committed heap memory. MB cluster, mapreduce, rack CDH 5
jvm_heap_used_mb Total amount of used heap memory. MB cluster, mapreduce, rack CDH 5
jvm_max_memory_mb Maximum allowed memory. MB cluster, mapreduce, rack CDH 5
jvm_new_threads New threads threads cluster, mapreduce, rack CDH 5
jvm_non_heap_committed_mb Total amount of committed non-heap memory. MB cluster, mapreduce, rack CDH 5
jvm_non_heap_used_mb Total amount of used non-heap memory. MB cluster, mapreduce, rack CDH 5
jvm_runnable_threads Runnable threads threads cluster, mapreduce, rack CDH 5
jvm_terminated_threads Terminated threads threads cluster, mapreduce, rack CDH 5
jvm_timed_waiting_threads Timed waiting threads threads cluster, mapreduce, rack CDH 5
jvm_total_threads Total threads threads cluster, mapreduce, rack CDH 5
jvm_waiting_threads Waiting threads threads cluster, mapreduce, rack CDH 5
log_error_rate Logged Errors messages per second cluster, mapreduce, rack CDH 5
log_fatal_rate Logged Fatals messages per second cluster, mapreduce, rack CDH 5
log_info_rate Logged Infos messages per second cluster, mapreduce, rack CDH 5
log_warn_rate Logged Warnings messages per second cluster, mapreduce, rack CDH 5
map_task_slots Map Task Slots slots cluster, mapreduce, rack CDH 5
maps_running Maps Running tasks cluster, mapreduce, rack CDH 5
mem_rss Resident memory used bytes cluster, mapreduce, rack CDH 5
mem_rss_with_descendants The total resident memory for this process and all its descendant processes bytes cluster, mapreduce, rack CDH 5
mem_swap Amount of swap memory used by this role's process. bytes cluster, mapreduce, rack CDH 5
mem_virtual Virtual memory used bytes cluster, mapreduce, rack CDH 5
mem_virtual_with_descendants The total virtual memory for this process and all its descendant processes bytes cluster, mapreduce, rack CDH 5
oom_exits_rate The number of times the role's backing process was killed due to an OutOfMemory error. This counter is only incremented if the Cloudera Manager "Kill When Out of Memory" option is enabled. exits per second cluster, mapreduce, rack CDH 5
read_bytes_rate The number of bytes read from the device bytes per second cluster, mapreduce, rack CDH 5
reduce_task_slots Reduce Task Slots slots cluster, mapreduce, rack CDH 5
reduces_running Reduces Running tasks cluster, mapreduce, rack CDH 5
shuffle_exceptions_caught_rate Shuffle Handler Exceptions Caught exceptions per second cluster, mapreduce, rack CDH 5
shuffle_failed_outputs_rate Shuffle Handler Failed Requests requests per second cluster, mapreduce, rack CDH 5
shuffle_handler_busy_percent Shuffle Handler Busy Percentage percent cluster, mapreduce, rack CDH 5
shuffle_output_bytes_rate Shuffle Output bytes per second cluster, mapreduce, rack CDH 5
shuffle_success_outputs_rate Shuffle Handler Successful Requests requests per second cluster, mapreduce, rack CDH 5
tasks_completed_rate Tasks Completed tasks per second cluster, mapreduce, rack CDH 5
tasks_failed_ping_rate Tasks Failed: Ping tasks per second cluster, mapreduce, rack CDH 5
tasks_failed_timeout_rate Tasks Failed: Timeout tasks per second cluster, mapreduce, rack CDH 5
unexpected_exits_rate The number of times the role's backing process exited unexpectedly. exits per second cluster, mapreduce, rack CDH 5
uptime For a host, the amount of time since the host was booted. For a role, the uptime of the backing process. seconds cluster, mapreduce, rack CDH 5
web_metrics_collection_duration Web Server Responsiveness ms cluster, mapreduce, rack CDH 5
write_bytes_rate The number of bytes written to the device bytes per second cluster, mapreduce, rack CDH 5