Skip to main content
NetApp Knowledge Base

What is Adaptive QoS and how does it work?

Views:
3,610
Visibility:
Public
Votes:
2
Category:
ontap-9
Specialty:
perf
Last Updated:

Applies to

ONTAP 9.3 or newer

Answer

  • Adaptive QoS uses QoS Throughput Floors and Ceilings (Minimum and Maximum throttle limits) to set individual Volume limits.
  • Floors are used to guarantee nearly-idle workloads do not interfere with busier workloads.
  • Adaptive QoS is dynamic based upon volume size, meaning a 10GB volume would have a different Floor and Ceiling than a 10 TB volume.
    • This means the Ceiling is the greater of 1) Expected IOPs, 2) Peak IOPs, or 3) Absolute Minimum IOPs
    • The Floor is always Expected IOPs unless below the Absolute Minimum IOPs
  • Terms
    • Adaptive QoS: Dynamic QoS Ceilings and Floors which grow or shrink based upon volume size used or allocated
    • Throughput Floor (Minimum): The amount of IOPs required to not hit deadline scheduler and obtain optimal latency.
    • Throughput Ceiling (Maximum): A hard limit of how many IOPs a Volume is allocated (regular QoS)
    • Expected IOPs: The Throughput Floor value in IOPs per terabyte (unless specified different)
    • Absolute minimum IOPs: An IOP Throughput Floor, used when Expected IOPs becomes too low and overrides Expected IOPs or Peak
    • Example: A 10GB Volume with a default Adaptive QoS "value" policy group will have a Floor of 75 IOPs, not 1.28 IOPs Expected.
    • Peak IOPs: The value in IOPs per terabyte (unless specified different) is the Ceiling when greater than Expected and Absolute Minimum IOPs

 

  • By default, three buckets are created:
policy-group expected-iops peak-iops absolute-min-iops peak-iops-allocation
extreme 6144IOPS/TB 12288IOPS/TB 1000IOPS used-space
performance 2048IOPS/TB 4096IOPS/TB 500IOPS used-space
value 128IOPS/TB 512IOPS/TB 75IOPS used-space
 
 
How does Adaptive QoS decide when to throttle?
  1. In ONTAP 9.6 and earlier, Volumes not in an adaptive policy will be put into a deadline scheduler called Best Effort if CPU Headroom is over 100%
  2. In ONTAP 9.7 and later, Volumes not in an adaptive policy will be put into a deadline scheduler called Best Effort.
  3. Volumes in an adaptive policy with IOPs are below the Throughput Floor will be put into the deadline scheduler Best Effort.
  4. Volumes in an adaptive policy with IOPs above the Throughput Floor will not be throttled by QoS.
  5. Volumes in an adaptive policy with IOPs at the Throughput Ceiling will be throttled at that value.

Additional Information

 

  • Here is some additional examples of space usage and throttling levels for comparison:
    • Expected IOPS = 200/TB
    • Peak IOPS = 1000/TB
    • Absolute Min IOPS = 75
    • Expected IOPs = allocated space
    • Peak IOPs = used space
  • The minimum and maximum IOPS will be calculated as follows for used-space allocation:

Volume Size

Data Stored

QoS Min IOPS (SSD Aggregate only)

QoS Max IOPS

1 GB

0GB

75 (Absolute Minimum)

75 (Absolute Minimum)

1 TB

0 TB

75 (Absolute Minimum)

200 (Expected)

1 TB

.1 TB

75 (Absolute Minimum)

200

1 TB

.2 TB

75 (Absolute Minimum)

200 (Peak and Expected)

1 TB

.4 TB

80 (Expected)

400 (Peak)

1 TB

.5 TB

100

500

2 TB

1.5 TB

300

1500

2 TB

1.75 TB

350

1750

 

 

 

******************************************************* *******************************************************