Object metrics

The following section lists all the object metrics:

Important:
  • CES Swift Object protocol feature is not supported from IBM Storage Scale 5.2.0 onwards.
  • IBM Storage Scale 5.1.8 is the last release that has CES Swift Object protocol.
  • IBM Storage Scale 5.2.0 will tolerate the update of a CES node from IBM Storage Scale 5.1.8.
    • Tolerate means:
      • The CES node will be updated to 5.2.0.
      • Swift Object support will not be updated as part of the 5.2.0 update.
      • You may continue to use the version of Swift Object protocol that was provided in IBM Storage Scale 5.1.8 on the CES 5.2.0 node.
      • IBM will provide usage and known defect support for the version of Swift Object that was provided in IBM Storage Scale 5.1.8 until you migrate to a supported object solution that IBM Storage Scale provides.
  • Please contact IBM for further details and migration planning.

SwiftAccount

  • account_auditor_time: Timing the data for individual account database audits.
  • account_DEL_err_time: Timing the data for each DELETE request, which results in an error like bad request, not mounted, or missing timestamp.
  • account_DEL_time: Timing the data for each DELETE request, which does not result in an error.
  • account_GET_err_time: Timing the data for each GET request, which results in an error like bad request, not mounted, bad delimiter, account listing limit too high, or bad accept header.
  • account_GET_time: Timing the data for each GET request, which does not result in an error.
  • account_HEAD_err_time: Timing the data for each HEAD request, which results in an error like bad request or not mounted.
  • account_HEAD_time: Timing the data for each HEAD request, which does not result in an error.
  • account_POST_err_time: Timing the data for each POST request, which results in an error like bad request, bad or missing timestamp, or not mounted.
  • account_POST_time: Timing the data for each POST request, which does not result in an error.
  • account_PUT_err_time: Timing the data for each PUT request, which results in an error like bad request, not mounted, conflict, or recently deleted.
  • account_PUT_time: Timing the data for each PUT request, which does not result in an error.
  • account_reaper_time: Timing the data for each reap_account() call.
  • account_REPLICATE_err_time: Timing the data for each REPLICATE request, which results in an error like bad request or not mounted.
  • account_REPLICATE_time: Timing the data for each REPLICATE request, which does not result in an error.
  • account_replicator_time: Timing the data for each database replication attempt, which does not result in a failure.

SwiftContainer

  • container_auditor_time: Timing the data for each container audit.
  • container_DEL_err_time: Timing the data for DELETE request errors like bad request, not mounted, missing timestamp, or conflict.
  • container_DEL_time: Timing the data for each DELETE request, which does not result in an error.
  • container_GET_err_time: Timing the data for GET request errors like bad request, not mounted, parameters not utf8, or bad accept header.
  • container_GET_time: Timing data for each GET request, which does not result in an error.
  • container_HEAD_err_time: Timing the data for HEAD request errors like bad request or not mounted.
  • container_HEAD_time: Timing the data for each HEAD request, which does not result in an error.
  • container_POST_err_time: Timing the data for POST request errors like bad request, bad x-container-sync-to, or not mounted.
  • container_POST_time: Timing the data for each POST request, which does not result in an error.
  • container_PUT_err_time: Timing the data for PUT request errors like bad request, missing timestamp, not mounted, or conflict.
  • container_PUT_time: Timing the data for each PUT request, which does not result in an error.
  • container_REPLICATE_err_time: Timing the data for REPLICATE request errors like bad request or not mounted.
  • container_REPLICATE_time: Timing the data for each REPLICATE request, which does not result in an error.
  • container_replicator_time: Timing the data for each database replication attempt, which does not result in a failure.
  • container_sync_deletes_time: Timing the data for each container database row synchronization through deletion.
  • container_sync_puts_time: Timing the data for each container database row synchronization by using the PUT process.
  • container_updater_time: Timing the data for processing a container that includes only timing for containers, which is needed to update their accounts.

SwiftObject

  • object_auditor_time: Timing the data for each object audit (does not include any rate-limiting sleep time for max_files_per_second, but does include rate-limiting sleep time for max_bytes_per_second).
  • object_DEL_err_time: Timing the data for DELETE request errors like bad request, missing timestamp, not mounted, or precondition that failed. Includes requests, which did not find or match the object.
  • object_DEL_time: Timing the data for each DELETE request, which does not result in an error.
  • object_expirer_time: Timing the data for each object expiration attempt that includes ones, which result in an error.
  • object_GET_err_time: Timing the data for GET request errors like bad request, not mounted, header timestamps before the epoch, or precondition failed. File errors, which result in a quarantine, are not counted here.
  • object_GET_time: Timing the data for each GET request, which did not result in an error. Includes requests, which did not find the object, such as disk errors that result in file quarantine.
  • object_HEAD_err_time: Timing the data for HEAD request errors like bad request or not mounted.
  • object_HEAD_time: Timing the data for each HEAD request, which did not result in an error. Includes requests, which did not find the object, such as disk errors that result in file quarantine.
  • object_POST_err_time: Timing the data for POST request errors like bad request, missing timestamp, delete-at in past, or not mounted.
  • object_POST_time: Timing the data for each POST request, which did not result in an error.
  • object_PUT_err_time: Timing the data for PUT request errors like bad request, not mounted, missing timestamp, object creation constraint violation, or delete-at in past.
  • object_PUT_time: Timing the data for each PUT request, which did not result in an error.
  • object_REPLICATE_err_time: Timing the data for REPLICATE request errors like bad request or not mounted.
  • object_REPLICATE_time: Timing the data for each REPLICATE request, which did not result in an error.
  • object_replicator_partition_delete_time: Timing the data for partitions that are replicated to another node because they do not belong to this node. This metric is not tracked per device.
  • object_replicator_partition_update_time: Timing the data for partitions replicated that also belong on this node. This metric is not tracked per device.
  • object_updater_time: Timing the data for object sweeps to flush async_pending container updates. It does not include object sweeps that did not find an existing async_pending storage directory.

SwiftProxy

  • proxy_account_GET_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests 200, which is a standard response for successful HTTP requests.
  • proxy_account_GET_time: Timing the data for GET request, start to finish, 200, which is a standard response for successful HTTP requests.
  • proxy_account_HEAD_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 204, wherein request is processed but no content is returned.
  • proxy_account_HEAD_time: Timing the data for HEAD request, start to finish, 204, wherein request is processed but no content is returned.
  • proxy_account_latency: Timing the data up to completion of sending the response headers, 200, which is a standard response for successful HTTP requests.
  • proxy_container_DEL_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 204, wherein request is processed but no content is returned.
  • proxy_container_DEL_time: Timing the data for DELETE request, start to finish, 204, wherein request is processed but no content is returned.
  • proxy_container_GET_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 200, which is a standard response for successful HTTP requests.
  • proxy_container_GET_time: Timing the data for GET request, start to finish, 200, which is a standard response for successful HTTP requests.
  • proxy_container_HEAD_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 204, wherein request is processed but no content is returned.
  • proxy_container_HEAD_time: Timing the data for HEAD request, start to finish, 204, wherein request is processed but no content is returned.
  • proxy_container_latency: Timing the data up to completion of sending the response headers, 200, which is a standard response for successful HTTP requests.
  • proxy_container_PUT_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 201, wherein request is processed and a new resource is created.
  • proxy_container_PUT_time: Timing the data for each PUT request not resulting in an error, 201, wherein request is processed and a new resource is created.
  • proxy_object_DEL_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 204, wherein request is processed but no content is returned.
  • proxy_object_DEL_time: Timing the data for DELETE request, start to finish, 204, wherein request is processed but no content is returned.
  • proxy_object_GET_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 200, which is a standard response for successful HTTP requests.
  • proxy_object_GET_time: Timing the data for GET request, start to finish, 200, which is a standard response for successful HTTP requests.
  • proxy_object_HEAD_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 204, wherein request is processed but no content is returned.
  • proxy_object_HEAD_time: Timing the data for HEAD request, start to finish, 204, wherein request is processed but no content is returned.
  • proxy_object_latency: Timing the data up to completion of sending the response headers, 200, which is a standard response for successful HTTP requests.
  • proxy_object_PUT_bytes: The sum of bytes that are transferred in (from clients) and out (to clients) for requests, 201, wherein request is processed and a new resource is created.
  • proxy_object_PUT_time: Timing the data for each PUT request not resulting in an error, 201, wherein request is processed and a new resource is created.
Note: For information about computed metrics for object, see Performance monitoring for object metrics.