Skip to main content

Set a throughput ceiling with ONTAP QoS policy groups

Contributors netapp-aherbin netapp-aaron-holt netapp-dbagwell netapp-barbe netapp-thomi
PDFs

A QoS maximum or throughput ceiling guarantees that throughput for a workload does not exceed a maximum number of IOPS or MBps, or IOPS and MBps regardless of competing workloads. Set a throughput ceiling to prevent less critical workloads from consuming excessive performance resources and degrading the performance of more critical workloads.

You can specify the throughput ceiling when you create a QoS policy group or you can wait until you monitor your workloads to specify it.

Learn more about throughput ceilings.

Before you begin

  • You must be a cluster administrator to create a policy group and to apply it to an SVM.

About this task

  • Adaptive and non-adaptive QoS policy groups are automatically enabled to temporarily increase a workload’s throughput ceiling by 50% for a duration of 1 second to respond to short-term demands for higher performance by default. Beginning with ONTAP 9.19.1, you can modify these default settings. In ONTAP 9.18.1 and earlier these settings cannot be changed.

    Use the following options to modify the default settings:

    Option Description Default setting

    burst-percent

    Throughput increase in percentage

    50%

    burst duration

    Duration for the throughput increase in seconds

    1 second

    burst-iops

    Maximum number of IOPs above the throughput ceiling for the specified burst duration

    0

  • You can use a non-shared QoS policy group to specify that the defined throughput ceiling applies to each member workload individually. Otherwise, the policy group is shared: the total throughput for the workloads assigned to the policy group cannot exceed the specified ceiling.

    Set -is-shared=false for the qos policy-group create command to specify a non-shared policy group.

  • You can specify the throughput limit for the ceiling in IOPS, MB/s, or IOPS, MB/s. If you specify both IOPS and MB/s, whichever limit is reached first is enforced.

    Note

    If you set a ceiling and a floor for the same workload, you can specify the throughput limit for the ceiling in IOPS only.

  • A storage object that is subject to a QoS limit must be contained by the SVM to which the policy group belongs. Multiple policy groups can belong to the same SVM.

  • You cannot assign a storage object to a policy group if its containing object or its child objects belong to the policy group.

  • It is a QoS best practice to apply a policy group to the same type of storage objects.

Steps

  1. Create a policy group:

    qos policy-group create -policy-group <policy_group> -vserver <SVM> -max-throughput <number_of_iops_|Mb/S|iops,Mb/S> -is-shared <true|false>

    Learn more about qos policy-group create in the ONTAP command reference.

    You can use the qos policy-group modify command to adjust throughput ceilings.

    The following example creates the shared policy group pg-vs1 with a maximum throughput of 5,000 IOPS:

    cluster1::> qos policy-group create -policy-group pg-vs1 -vserver vs1 -max-throughput 5000iops -is-shared true

    The following example creates the non-shared policy group pg-vs3 with a maximum throughput of 100 IOPS and 400 Kb/S:

    cluster1::> qos policy-group create -policy-group pg-vs3 -vserver vs3 -max-throughput 100iops,400KB/s -is-shared false

    The following example creates the non-shared policy group pg-vs4 without a throughput limit:

    cluster1::> qos policy-group create -policy-group pg-vs4 -vserver vs4 -is-shared false

    Learn more about qos policy-group modify in the ONTAP command reference.

  2. Apply a policy group to an SVM, file, volume, or LUN:

    vserver create -vserver <SVM> -qos-policy-group <policy_group>

    The following example applies policy group pg-vs1 to SVM vs1:

    cluster1::> vserver create -vserver vs1 -qos-policy-group pg-vs1

    The following examples apply policy group pg-app to the volumes app1 and app2:

    cluster1::> volume create -vserver vs2 -volume app1 -aggregate aggr1 -qos-policy-group pg-app
    cluster1::> volume create -vserver vs2 -volume app2 -aggregate aggr1 -qos-policy-group pg-app

  3. Monitor policy group performance:

    qos statistics performance show

    Learn more about qos statistics performance show in the ONTAP command reference.

    Note

    Monitor performance from the cluster. Do not use a tool on the host to monitor performance.

    The following example shows policy group performance:

    cluster1::> qos statistics performance show
Policy Group           IOPS      Throughput   Latency
-------------------- -------- --------------- ----------
-total-                 12316       47.76MB/s  1264.00us
pg_vs1                   5008       19.56MB/s     2.45ms
_System-Best-Effort        62       13.36KB/s     4.13ms
_System-Background         30           0KB/s        0ms

  4. Monitor workload performance:

    qos statistics workload performance show
    Note

    Monitor performance from the cluster. Do not use a tool on the host to monitor performance.

    The following example shows workload performance:

    cluster1::> qos statistics workload performance show
Workload          ID     IOPS      Throughput    Latency
--------------- ------ -------- ---------------- ----------
-total-              -    12320        47.84MB/s  1215.00us
app1-wid7967      7967     7219        28.20MB/s   319.00us
vs1-wid12279     12279     5026        19.63MB/s     2.52ms
_USERSPACE_APPS     14       55        10.92KB/s   236.00us
_Scan_Backgro..   5688       20            0KB/s        0ms

    The following is an example of output for a workload with max-throughput set to 2000 IOPS and burst-percent set to 25 for a 5 second burst duration.

    cluster1::> qos statistics workload performance show -workload test_vol_nfs_pct25-wid54260

Workload	                ID	    IOPS
--------------------------- -----   ----
test_vol_nfs_pct25-wid54260	54260	2564
-total-	-	                        3704
test_vol_nfs_pct25-wid54260	54260	2527
-total-	-	                        3105
test_vol_nfs_pct25-wid54260	54260	2550
-total-	-	                        3445
test_vol_nfs_pct25-wid54260	54260	2476
-total-	-	                        3460
test_vol_nfs_pct25-wid54260	54260	2479
-total-	-	                        3511
test_vol_nfs_pct25-wid54260	54260	1996
-total-	-	                        2197
test_vol_nfs_pct25-wid54260	54260	2068
-total-	-	                        2057
test_vol_nfs_pct25-wid54260	54260	2087
-total-	-	                        3119

    Learn more about qos statistics workload performance show in the ONTAP command reference.

    You can use the qos statistics workload latency show command to view detailed latency statistics for QoS workloads.

    Learn more about qos statistics workload latency show in the ONTAP command reference.