Skip to content

Commit

Permalink
feat(validator): add support to validate essential metrics produced b…
Browse files Browse the repository at this point in the history 
…y Kepler

This commit introduces functionality to validate essential metrics produced by Kepler
The following comparisons are included:

- Node Exporter Comparison
   - Validates `node_rapl_<package|core|dram>` metrics against `kepler_node_<package|core|dram>{dev}`

- Kepler Process Comparison
   - Compares `kepler_process_<package|core|dram|platform|other|uncore>{latest}` metrics to
      `kepler_process_<package|core|dram|platform|other|uncore>{dev}`

- Kepler Node Comparison
   - Validates `kepler_node_<package|core|dram|platform|other|uncore>{latest}` against
      `kepler_node_<package|core|dram|platform|other|uncore>{dev}`

Additionally, the following changes are made to existing functionality:

- Adds a new `metric_validations.yaml` file which includes promql queries for comparisons along with threshold values
- Update the existing `stressor.sh` script to now support few more parameters to make it more flexible
  - warmup time: time to wait before starting the stressor
  - cooldown time: time to wait after the stressor is finished
  - repeats: number of times to repeat the stressor. Since for
    regression test we don't want to repeat the stressor multiple times
- Adds a new `validator-regression.yaml` file which includes the configuration for the regression test

Signed-off-by: vprashar2929 <[email protected]>
  • Loading branch information
@vprashar2929
vprashar2929 committed Dec 16, 2024
1 parent 021b544 commit 28889fe
Show file tree
Hide file tree
Showing 9 changed files with 524 additions and 13 deletions.
354 changes: 354 additions & 0 deletions e2e/tools/validator/metric_validations.yaml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,354 @@
config:
mapping:
actual: latest
predicted: dev

validations:
# node rapl comparison
- name: node-rapl - kepler-package
units: Watts
mapping:
actual: node-rapl
predicted: kepler-package

node-rapl: |
sum(
rate(
node_rapl_package_joules_total[{rate_interval}]
)
)
kepler-package: |
sum(
rate(
kepler_node_package_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 1.01

- name: node-rapl - kepler-core
units: Watts
mapping:
actual: node-rapl
predicted: kepler-core

node-rapl: |
sum(
rate(
node_rapl_core_joules_total[{rate_interval}]
)
)
kepler-core: |
sum(
rate(
kepler_node_core_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 1.01

- name: node-rapl - kepler-dram
units: Watts
mapping:
actual: node-rapl
predicted: kepler-dram

node-rapl: |
sum(
rate(
node_rapl_dram_joules_total[{rate_interval}]
)
)
kepler-dram: |
sum(
rate(
kepler_node_dram_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 1.01

# absolute power comparison
- name: Total - absolute
latest: |
sum(
rate(
kepler_process_joules_total{{
job="latest",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_joules_total{{
job="dev",
}}[{rate_interval}]
)
)
max_mae: 2.01

# CPU time comparison
- name: cpu-time
units: Milliseconds
latest: |
sum(
rate(
kepler_process_bpf_cpu_time_ms_total{{
job="latest"
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_bpf_cpu_time_ms_total{{
job="dev",
}}[{rate_interval}]
)
)
# max_mae: 20.0

# process comparison
- name: platform - dynamic
latest: |
sum(
rate(
kepler_process_platform_joules_total{{
job="latest", mode="dynamic",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_platform_joules_total{{
job="dev", mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 2.01

- name: package - dynamic
units: Watts
latest: |
sum(
rate(
kepler_process_package_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_package_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 2.01

- name: core - dynamic
units: Watts
latest: |
sum(
rate(
kepler_process_core_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_core_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 2.01

- name: dram - dynamic
units: Watts
latest: |
sum(
rate(
kepler_process_dram_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_dram_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 2.01

- name: other - dynamic
units: Watts
latest: |
sum(
rate(
kepler_process_other_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_other_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 2.01

- name: uncore - dynamic
units: Watts
latest: |
sum(
rate(
kepler_process_uncore_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
)
dev: |
sum(
rate(
kepler_process_uncore_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
)
max_mae: 2.01

# node comparison
- name: node platform - dynamic
units: Watts
latest: |
rate(kepler_node_platform_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
dev: |
rate(kepler_node_platform_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
max_mae: 2.01

- name: node package - dynamic
units: Watts
latest: |
rate(kepler_node_package_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
dev: |
rate(kepler_node_package_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
max_mae: 2.01

- name: node core - dynamic
units: Watts
latest: |
rate(kepler_node_core_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
dev: |
rate(kepler_node_core_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
max_mae: 2.01

- name: node dram - dynamic
units: Watts
latest: |
rate(kepler_node_dram_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
dev: |
rate(kepler_node_dram_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
max_mae: 2.01

- name: node other - dynamic
units: Watts
latest: |
rate(kepler_node_other_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
dev: |
rate(kepler_node_other_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
max_mae: 2.01

- name: node uncore - dynamic
units: Watts
latest: |
rate(kepler_node_uncore_joules_total{{
job="latest",
mode="dynamic",
}}[{rate_interval}]
)
dev: |
rate(kepler_node_uncore_joules_total{{
job="dev",
mode="dynamic",
}}[{rate_interval}]
)
max_mae: 2.01
Loading

0 comments on commit 28889fe

Please sign in to comment.