Data ONTAP 8.2 Reference - qos statistics workload latency show

qos statistics workload latency show

Display latency breakdown data per QoS workload

Availability: This command is available to cluster administrators at the admin privilege level.

Description

The qos statistics workload latency show command displays the average latencies for QoS workloads on Data ONTAP subsystems.

The command displays the following data:

The QoS workload name (Workload)
The QoS workload ID (ID)
Total latency observed per I/O operation (Latency)
Latency observed per I/O operation in the Network subsystem (Network)
Latency observed per I/O operation across the internally connected nodes in a Cluster (Cluster)
Latency observed per I/O operation in the Data management subsystem (Data)
Latency observed per I/O operation in the Storage subsystem (Disk)
Latency observed per I/O operation in the QoS subsystem (QoS)

The results displayed per iteration are sorted by the total latency field. Each iteration starts with a row that displays the average latency, in microseconds (us) or milliseconds (ms) observed across all QoS workloads.

Parameters

[-node {<nodename>|local}] - Node

Selects the QOS workloads that match this parameter value. If you do not specify this parameter, the command displays data for the entire cluster.

[-iterations <integer>] - Number of Iterations

Specifies the number of times that the command refreshes the display with updated data before terminating. If you do not specify this parameter, the command continues to run until you interrupt it by pressing Ctrl-C.

[-rows <integer>] - Number of Rows in the Output

Specifies the number of busiest QoS workloads to display. The default setting is 10. The allowed range of values is 1 to 20.

[-refresh-display {true|false}] - Toggle Screen Refresh Between Each Iteration

Specifies the display style. If true, the command clears the display after each data iteration. If false, the command displays each data iteration below the previous one. The default is false.

Examples

    cluster1::> qos statistics workload latency show -iterations 100 -rows 3
Workload          ID   Latency     Network  Cluster     Data     Disk     QoS
--------------- ------ --------   -------- --------   -------- -------- --------
-total-                110.35ms   110.02ms      0ms   327.00us      0ms      0ms
vs1vol0            111 167.82ms   167.22ms      0ms   603.00us      0ms      0ms
vol1              1234 117.76ms   117.56ms      0ms   191.00us      0ms      0ms
vol2               999  44.24ms    44.05ms      0ms   190.00us      0ms      0ms
-total-             -   38.89ms    38.63ms      0ms   256.00us      0ms      0ms
vol2               999  64.47ms    64.20ms      0ms   266.00us      0ms      0ms
vol1              1234  27.28ms    27.03ms      0ms   253.00us      0ms      0ms
vs1vol0            111  23.72ms    23.47ms      0ms   249.00us      0ms      0ms
-total-              - 409.81ms   409.65ms      0ms   169.00us      0ms      0ms
vol1              1234 816.92ms   816.80ms      0ms   120.00us      0ms      0ms
vol2               999 407.88ms   407.66ms      0ms   219.00us      0ms      0ms
vs1vol0            111   3.68ms     3.49ms      0ms   193.00us      0ms      0ms

The example above displays latencies for the 3 QoS workloads with the highest latencies and it refreshes the display 100 times before terminating.