-
Type: Task
-
Status: Open
-
Priority: Minor
-
Resolution: Unresolved
-
Affects Version/s: None
-
Fix Version/s: None
-
Component/s: Performance
-
Team:PLATFORM
-
Story Points:3
Context
Current Continuous benchmarks are run against C4.xlarge AWS instances that use x86 based CPUs.
It would be good to have a sense of how our stack behaves on ARM based Graviton2 Instances types.
Get a baseline
It would be useful to get a first performance baseline.
We can start this experimentation by running the standard benchmark on a c6g instance type.
This may be as simple as changing the deployment to replace
c4.xlarge by c6g.xlarge.
Looking at the instances types:
c4.xlarge 4 cores / 7.5 GiB => $0.199 per Hour c6g.xlarge 4 cores / 8 GiB => $0.136 per Hour
This means that cost goes down by 30% so if performance is similar or close enough, this may be an interesting path to follow.