Dell Powerflex

Supported OS Linux Windows Mac OS

Integration version1.0.0

Dell PowerFlex dashboard

Overview

This check monitors Dell PowerFlex software-defined storage environments through the Datadog Agent. It collects metrics and events from the PowerFlex Gateway REST API across the following resource types:

Systems: MDM cluster state, capacity, and I/O statistics
Protection Domains: capacity, rebuild, rebalance, and I/O metrics
Storage Pools: capacity utilization, usage ratios, and throughput
Volumes: per-volume I/O and SDC mappings
SDS (Storage Data Servers): device counts, capacity, cache, and I/O
SDC (Storage Data Clients): mapped volumes and user data I/O
Devices: read/write latency, capacity, and I/O bandwidth

Setup

Installation

The Dell PowerFlex check is included in the Datadog Agent package. No additional installation is needed on your server.

Configuration

Edit the dell_powerflex.d/conf.yaml file in the conf.d/ folder at the root of your Agent’s configuration directory to start collecting your Dell PowerFlex metrics. See the sample dell_powerflex.d/conf.yaml for all available configuration options.
```
instances:
  - powerflex_gateway_url: https://<GATEWAY_HOST>:443
    powerflex_username: <USERNAME>
    powerflex_password: <PASSWORD>
```

Use resource_filters to control which resources are collected and whether per-resource statistics API calls are made. This is useful for large environments where you want to limit the number of API calls. Exclude filters take precedence over include filters. By default, all resources are collected with statistics enabled, except for devices which have statistics disabled by default.

instances:
- powerflex_gateway_url: https://<GATEWAY_HOST>:443
  powerflex_username: <USERNAME>
  powerflex_password: <PASSWORD>
  resource_filters:
   - resource: storage_pool
     property: name
     patterns:
       - "^prod-"
   - resource: sds
     property: name
     type: exclude
     patterns:
       - "^standby-"
   - resource: device
     property: name
     collect_statistics: false

Restart the Agent.

Data Collected

Metrics


dell_powerflex.actual_net_capacity.in_use_in_kb (gauge)	Actual net capacity in use. Shown as kibibyte
dell_powerflex.api.can_connect (gauge)	Whether or not the PowerFlex Gateway API is reachable.
dell_powerflex.avg_read_latency_in_microsec (gauge)	Average read latency in microseconds. Shown as microsecond
dell_powerflex.avg_read_size_in_bytes (gauge)	Average read size in bytes. Shown as byte
dell_powerflex.avg_write_latency_in_microsec (gauge)	Average write latency in microseconds. Shown as microsecond
dell_powerflex.avg_write_size_in_bytes (gauge)	Average write size in bytes. Shown as byte
dell_powerflex.bck_rebuild_read_bwc.num_occured (gauge)	Number of backward rebuild read I/O operations.
dell_powerflex.bck_rebuild_read_bwc.num_seconds (gauge)	Duration of the backward rebuild read sampling window. Shown as second
dell_powerflex.bck_rebuild_read_bwc.total_weight_in_kb (gauge)	Total backward rebuild read bandwidth. Shown as kibibyte
dell_powerflex.bck_rebuild_write_bwc.num_occured (gauge)	Number of backward rebuild write I/O operations.
dell_powerflex.bck_rebuild_write_bwc.num_seconds (gauge)	Duration of the backward rebuild write sampling window. Shown as second
dell_powerflex.bck_rebuild_write_bwc.total_weight_in_kb (gauge)	Total backward rebuild write bandwidth. Shown as kibibyte
dell_powerflex.capacity.in_use_in_kb (gauge)	Total capacity in use. Shown as kibibyte
dell_powerflex.capacity_available_for_volume_allocation.in_kb (gauge)	Capacity available for volume allocation. Shown as kibibyte
dell_powerflex.capacity_limit.in_kb (gauge)	Capacity limit. Shown as kibibyte
dell_powerflex.compression_ratio (gauge)	Compression ratio.
dell_powerflex.device.count (gauge)	Timeseries with value 1 for each device. Use ‘sum by {X}’ queries to count all devices with the tag X.
dell_powerflex.exposed_capacity.in_kb (gauge)	Exposed capacity. Shown as kibibyte
dell_powerflex.failed_capacity.in_kb (gauge)	Failed capacity. Shown as kibibyte
dell_powerflex.failed_vac.in_kb (gauge)	Failed volume allocation capacity. Shown as kibibyte
dell_powerflex.fixed_read_error_count (gauge)	Number of fixed read errors found during background scan.
dell_powerflex.fwd_rebuild_read_bwc.num_occured (gauge)	Number of forward rebuild read I/O operations.
dell_powerflex.fwd_rebuild_read_bwc.num_seconds (gauge)	Duration of the forward rebuild read sampling window. Shown as second
dell_powerflex.fwd_rebuild_read_bwc.total_weight_in_kb (gauge)	Total forward rebuild read bandwidth. Shown as kibibyte
dell_powerflex.fwd_rebuild_write_bwc.num_occured (gauge)	Number of forward rebuild write I/O operations.
dell_powerflex.fwd_rebuild_write_bwc.num_seconds (gauge)	Duration of the forward rebuild write sampling window. Shown as second
dell_powerflex.fwd_rebuild_write_bwc.total_weight_in_kb (gauge)	Total forward rebuild write bandwidth. Shown as kibibyte
dell_powerflex.in_use_vac.in_kb (gauge)	Volume allocation capacity in use. Shown as kibibyte
dell_powerflex.inaccessible_capacity.in_kb (gauge)	Inaccessible capacity. Shown as kibibyte
dell_powerflex.journaler_read_latency.num_occured (gauge)	Number of journaler read I/O operations in the sampling window.
dell_powerflex.journaler_read_latency.num_seconds (gauge)	Duration of the journaler read latency sampling window. Shown as second
dell_powerflex.journaler_read_latency.total_weight_in_kb (gauge)	Total weight of journaler read latency samples in the sampling window. Shown as kibibyte
dell_powerflex.journaler_write_latency.num_occured (gauge)	Number of journaler write I/O operations in the sampling window.
dell_powerflex.journaler_write_latency.num_seconds (gauge)	Duration of the journaler write latency sampling window. Shown as second
dell_powerflex.journaler_write_latency.total_weight_in_kb (gauge)	Total weight of journaler write latency samples in the sampling window. Shown as kibibyte
dell_powerflex.max_capacity.in_kb (gauge)	Maximum usable capacity. Shown as kibibyte
dell_powerflex.mdm_cluster.cluster_state (gauge)	State of the MDM cluster. Emitted as 1 with a cluster_state tag.
dell_powerflex.mdm_cluster.good_nodes (gauge)	Number of MDM nodes in good health.
dell_powerflex.mdm_cluster.good_replicas (gauge)	Number of MDM replicas in good health.
dell_powerflex.mdm_mode (gauge)	MDM cluster mode. Emitted as 1 with an mdm_mode tag.
dell_powerflex.net_capacity.in_use_in_kb (gauge)	Net capacity in use. Shown as kibibyte
dell_powerflex.net_user_data_capacity.in_kb (gauge)	Net user data capacity. Shown as kibibyte
dell_powerflex.norm_rebuild_read_bwc.num_occured (gauge)	Number of normal rebuild read I/O operations.
dell_powerflex.norm_rebuild_read_bwc.num_seconds (gauge)	Duration of the normal rebuild read sampling window. Shown as second
dell_powerflex.norm_rebuild_read_bwc.total_weight_in_kb (gauge)	Total normal rebuild read bandwidth. Shown as kibibyte
dell_powerflex.norm_rebuild_write_bwc.num_occured (gauge)	Number of normal rebuild write I/O operations.
dell_powerflex.norm_rebuild_write_bwc.num_seconds (gauge)	Duration of the normal rebuild write sampling window. Shown as second
dell_powerflex.norm_rebuild_write_bwc.total_weight_in_kb (gauge)	Total normal rebuild write bandwidth. Shown as kibibyte
dell_powerflex.num_dev_errors (gauge)	Number of device errors.
dell_powerflex.num_of_child_volumes (gauge)	Number of child volumes (snapshots) of this volume.
dell_powerflex.num_of_devices (gauge)	Number of devices.
dell_powerflex.num_of_fault_sets (gauge)	Number of fault sets.
dell_powerflex.num_of_mapped_sdcs (gauge)	Number of SDCs mapped to this volume.
dell_powerflex.num_of_mapped_to_all_volumes (gauge)	Number of volumes mapped to all SDCs.
dell_powerflex.num_of_mapped_volumes (gauge)	Number of volumes mapped to this SDC.
dell_powerflex.num_of_sds (gauge)	Number of SDS nodes.
dell_powerflex.num_of_snapshots (gauge)	Number of snapshots.
dell_powerflex.num_of_storage_pools (gauge)	Number of storage pools.
dell_powerflex.num_of_thick_base_volumes (gauge)	Number of thick base volumes.
dell_powerflex.num_of_thin_base_volumes (gauge)	Number of thin base volumes.
dell_powerflex.num_of_unmapped_volumes (gauge)	Number of unmapped volumes.
dell_powerflex.num_of_volumes (gauge)	Number of volumes.
dell_powerflex.num_sdr_sdc_disconnections (gauge)	Number of SDR-SDC disconnections.
dell_powerflex.num_sds_reconnections (gauge)	Number of SDS reconnections.
dell_powerflex.num_sds_sdr_disconnections (gauge)	Number of SDS-SDR disconnections.
dell_powerflex.overall_usage_ratio (gauge)	Overall capacity usage ratio. Shown as fraction
dell_powerflex.primary_read_bwc.num_occured (gauge)	Number of primary read I/O operations.
dell_powerflex.primary_read_bwc.num_seconds (gauge)	Duration of the primary read sampling window. Shown as second
dell_powerflex.primary_read_bwc.total_weight_in_kb (gauge)	Total primary read bandwidth. Shown as kibibyte
dell_powerflex.primary_write_bwc.num_occured (gauge)	Number of primary write I/O operations.
dell_powerflex.primary_write_bwc.num_seconds (gauge)	Duration of the primary write sampling window. Shown as second
dell_powerflex.primary_write_bwc.total_weight_in_kb (gauge)	Total primary write bandwidth. Shown as kibibyte
dell_powerflex.protected_capacity.in_kb (gauge)	Protected capacity. Shown as kibibyte
dell_powerflex.protection_domain.count (gauge)	Timeseries with value 1 for each protection domain. Use ‘sum by {X}’ queries to count all protection domains with the tag X.
dell_powerflex.rebalance_read_bwc.num_occured (gauge)	Number of rebalance read I/O operations.
dell_powerflex.rebalance_read_bwc.num_seconds (gauge)	Duration of the rebalance read sampling window. Shown as second
dell_powerflex.rebalance_read_bwc.total_weight_in_kb (gauge)	Total rebalance read bandwidth. Shown as kibibyte
dell_powerflex.rebalance_wait_send_q_length (gauge)	Rebalance wait send queue length.
dell_powerflex.rebalance_write_bwc.num_occured (gauge)	Number of rebalance write I/O operations.
dell_powerflex.rebalance_write_bwc.num_seconds (gauge)	Duration of the rebalance write sampling window. Shown as second
dell_powerflex.rebalance_write_bwc.total_weight_in_kb (gauge)	Total rebalance write bandwidth. Shown as kibibyte
dell_powerflex.rebuild_wait_send_q_length (gauge)	Rebuild wait send queue length.
dell_powerflex.rfcache.io_errors (gauge)	Number of RF cache I/O errors.
dell_powerflex.rfcache.read_hit (gauge)	Number of RF cache read hits.
dell_powerflex.rfcache.read_miss (gauge)	Number of RF cache read misses.
dell_powerflex.rfcache.reads_pending (gauge)	Number of RF cache reads pending.
dell_powerflex.rfcache.reads_received (gauge)	Number of read requests received by the RF cache.
dell_powerflex.rfcache.write_hit (gauge)	Number of RF cache write hits.
dell_powerflex.rfcache.write_miss (gauge)	Number of RF cache write misses.
dell_powerflex.rfcache.writes_received (gauge)	Number of write requests received by the RF cache.
dell_powerflex.rmcache.size_in_kb (gauge)	Total size of the RAM read cache. Shown as kibibyte
dell_powerflex.rmcache.size_in_use_in_kb (gauge)	RAM read cache capacity currently in use. Shown as kibibyte
dell_powerflex.rpl_total_journal_cap (gauge)	Total replication journal capacity. Shown as kibibyte
dell_powerflex.rpl_used_journal_cap (gauge)	Used replication journal capacity. Shown as kibibyte
dell_powerflex.sdc.count (gauge)	Timeseries with value 1 for each SDC. Use ‘sum by {X}’ queries to count all SDCs with the tag X.
dell_powerflex.sds.count (gauge)	Timeseries with value 1 for each SDS. Use ‘sum by {X}’ queries to count all SDSs with the tag X.
dell_powerflex.secondary_read_bwc.num_occured (gauge)	Number of secondary read I/O operations.
dell_powerflex.secondary_read_bwc.num_seconds (gauge)	Duration of the secondary read sampling window. Shown as second
dell_powerflex.secondary_read_bwc.total_weight_in_kb (gauge)	Total secondary read bandwidth. Shown as kibibyte
dell_powerflex.secondary_write_bwc.num_occured (gauge)	Number of secondary write I/O operations.
dell_powerflex.secondary_write_bwc.num_seconds (gauge)	Duration of the secondary write sampling window. Shown as second
dell_powerflex.secondary_write_bwc.total_weight_in_kb (gauge)	Total secondary write bandwidth. Shown as kibibyte
dell_powerflex.snap_capacity.in_use_in_kb (gauge)	Snapshot capacity in use. Shown as kibibyte
dell_powerflex.snapshot.capacity_in_kb (gauge)	Total capacity allocated for snapshots. Shown as kibibyte
dell_powerflex.spare_capacity.in_kb (gauge)	Spare capacity reserved. Shown as kibibyte
dell_powerflex.storage_pool.count (gauge)	Timeseries with value 1 for each storage pool. Use ‘sum by {X}’ queries to count all storage pools with the tag X.
dell_powerflex.system.count (gauge)	Timeseries with value 1 for each system. Use ‘sum by {X}’ queries to count all systems with the tag X.
dell_powerflex.target_read_latency.num_occured (gauge)	Number of target read I/O operations.
dell_powerflex.target_read_latency.num_seconds (gauge)	Duration of the target read latency sampling window. Shown as second
dell_powerflex.target_read_latency.total_weight_in_kb (gauge)	Total weight of target read latency samples. Shown as kibibyte
dell_powerflex.target_write_latency.num_occured (gauge)	Number of target write I/O operations.
dell_powerflex.target_write_latency.num_seconds (gauge)	Duration of the target write latency sampling window. Shown as second
dell_powerflex.target_write_latency.total_weight_in_kb (gauge)	Total weight of target write latency samples. Shown as kibibyte
dell_powerflex.thick_capacity.in_use_in_kb (gauge)	Thick-provisioned capacity in use. Shown as kibibyte
dell_powerflex.thin_capacity.in_use_in_kb (gauge)	Thin-provisioned capacity in use. Shown as kibibyte
dell_powerflex.total_read_bwc.num_occured (gauge)	Number of total read I/O operations.
dell_powerflex.total_read_bwc.num_seconds (gauge)	Duration of the total read sampling window. Shown as second
dell_powerflex.total_read_bwc.total_weight_in_kb (gauge)	Total read bandwidth. Shown as kibibyte
dell_powerflex.total_write_bwc.num_occured (gauge)	Number of total write I/O operations.
dell_powerflex.total_write_bwc.num_seconds (gauge)	Duration of the total write sampling window. Shown as second
dell_powerflex.total_write_bwc.total_weight_in_kb (gauge)	Total write bandwidth. Shown as kibibyte
dell_powerflex.unreachable_unused_capacity.in_kb (gauge)	Unreachable unused capacity. Shown as kibibyte
dell_powerflex.unused_capacity.in_kb (gauge)	Unused capacity available. Shown as kibibyte
dell_powerflex.user_data.capacity_in_kb (gauge)	Capacity consumed by user data. Shown as kibibyte
dell_powerflex.user_data_read_bwc.num_occured (gauge)	Number of user data read I/O operations in the sampling window.
dell_powerflex.user_data_read_bwc.num_seconds (gauge)	Duration of the user data read sampling window. Shown as second
dell_powerflex.user_data_read_bwc.total_weight_in_kb (gauge)	Total user data read bandwidth in the sampling window. Shown as kibibyte
dell_powerflex.user_data_sdc_read_latency.num_occured (gauge)	Number of SDC read I/O operations in the sampling window.
dell_powerflex.user_data_sdc_read_latency.num_seconds (gauge)	Duration of the SDC read latency sampling window. Shown as second
dell_powerflex.user_data_sdc_read_latency.total_weight_in_kb (gauge)	Total weight of SDC read latency samples in the sampling window. Shown as kibibyte
dell_powerflex.user_data_sdc_trim_latency.num_occured (gauge)	Number of SDC trim I/O operations in the sampling window.
dell_powerflex.user_data_sdc_trim_latency.num_seconds (gauge)	Duration of the SDC trim latency sampling window. Shown as second
dell_powerflex.user_data_sdc_trim_latency.total_weight_in_kb (gauge)	Total weight of SDC trim latency samples in the sampling window. Shown as kibibyte
dell_powerflex.user_data_sdc_write_latency.num_occured (gauge)	Number of SDC write I/O operations in the sampling window.
dell_powerflex.user_data_sdc_write_latency.num_seconds (gauge)	Duration of the SDC write latency sampling window. Shown as second
dell_powerflex.user_data_sdc_write_latency.total_weight_in_kb (gauge)	Total weight of SDC write latency samples in the sampling window. Shown as kibibyte
dell_powerflex.user_data_trim_bwc.num_occured (gauge)	Number of user data trim I/O operations in the sampling window.
dell_powerflex.user_data_trim_bwc.num_seconds (gauge)	Duration of the user data trim sampling window. Shown as second
dell_powerflex.user_data_trim_bwc.total_weight_in_kb (gauge)	Total user data trim bandwidth in the sampling window. Shown as kibibyte
dell_powerflex.user_data_write_bwc.num_occured (gauge)	Number of user data write I/O operations in the sampling window.
dell_powerflex.user_data_write_bwc.num_seconds (gauge)	Duration of the user data write sampling window. Shown as second
dell_powerflex.user_data_write_bwc.total_weight_in_kb (gauge)	Total user data write bandwidth in the sampling window. Shown as kibibyte
dell_powerflex.vol_migration_read_bwc.num_occured (gauge)	Number of volume migration read I/O operations.
dell_powerflex.vol_migration_read_bwc.num_seconds (gauge)	Duration of the volume migration read sampling window. Shown as second
dell_powerflex.vol_migration_read_bwc.total_weight_in_kb (gauge)	Total volume migration read bandwidth. Shown as kibibyte
dell_powerflex.vol_migration_write_bwc.num_occured (gauge)	Number of volume migration write I/O operations.
dell_powerflex.vol_migration_write_bwc.num_seconds (gauge)	Duration of the volume migration write sampling window. Shown as second
dell_powerflex.vol_migration_write_bwc.total_weight_in_kb (gauge)	Total volume migration write bandwidth. Shown as kibibyte
dell_powerflex.volume.count (gauge)	Timeseries with value 1 for each volume. Use ‘sum by {X}’ queries to count all volumes with the tag X.
dell_powerflex.volume.sdc_mapping (gauge)	Indicates a volume-to-SDC mapping relationship. A value of 1 is emitted for each SDC mapped to a volume.
dell_powerflex.volume_allocation_limit.in_kb (gauge)	Volume allocation limit. Shown as kibibyte

Uninstallation

To uninstall the integration, rename the configuration file from dell_powerflex.d/conf.yaml to dell_powerflex.d/conf.yaml.example. Alternatively, if you are running a containerized environment, you can remove the annotation used to enable the integration.

Support

Need help? Contact Datadog Support.