docs(proposal): add EP-002 for MSR fallback power meter support #2271
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sthaha
force-pushed
the
feat-rapl-msr
branch
5 times, most recently
from
7fd5fd5 to
f64731f
Compare
Introduces enhancement proposal for adding MSR (Model Specific Register) support as a fallback mechanism when Intel RAPL powercap sysfs interface is unavailable. This improves Kepler's deployment flexibility in environments with restricted powercap access. The proposal includes: - Architecture design using powerReader abstraction - Security considerations for MSR access (PLATYPUS mitigation) - Phased implementation plan with backward compatibility - Configuration for opt-in MSR fallback behavior Signed-off-by: Sunil Thaha <sthaha@redhat.com>
|
request not use AI to generate enhancement proposals. a short, concise proposal can convey the intention better, IMHO. |
vimalk78
reviewed
Aug 12, 2025
Comment on lines
+45
to
+49
| - **Primary Goal**: Implement MSR-based RAPL reading as automatic fallback when | ||
| powercap is unavailable | ||
| - **Secondary Goal**: Maintain existing CPUPowerMeter interface compatibility | ||
| - **Tertiary Goal**: Provide configurable control over fallback behavior for | ||
| security-conscious deployments |
There was a problem hiding this comment.
Suggested change
| - **Primary Goal**: Implement MSR-based RAPL reading as automatic fallback when | |
| powercap is unavailable | |
| - **Secondary Goal**: Maintain existing CPUPowerMeter interface compatibility | |
| - **Tertiary Goal**: Provide configurable control over fallback behavior for | |
| security-conscious deployments | |
| - Implement MSR-based RAPL reading as automatic fallback when | |
| powercap is unavailable | |
| - Maintain existing CPUPowerMeter interface compatibility | |
| - Provide configurable control over fallback behavior for | |
| security-conscious deployments |
Comment on lines
+105
to
+109
| style CPUPowerMeter fill:#e1f5fe | ||
| style raplPowerMeter fill:#b3e5fc | ||
| style powercapReader fill:#81d4fa | ||
| style msrReader fill:#ffccbc | ||
| style zoneAdapter fill:#c5e1a5 |
There was a problem hiding this comment.
Suggested change
| style CPUPowerMeter fill:#e1f5fe | |
| style raplPowerMeter fill:#b3e5fc | |
| style powercapReader fill:#81d4fa | |
| style msrReader fill:#ffccbc | |
| style zoneAdapter fill:#c5e1a5 |
Comment on lines
+340
to
+342
| kepler_node_package_energy_millijoule{node="node1"} 12345 | ||
| kepler_node_core_energy_millijoule{node="node1"} 6789 | ||
| kepler_node_dram_energy_millijoule{node="node1"} 3456 |
Comment on lines
+324
to
+325
| 2. **Phase 2**: Enable MSR fallback in staging environments | ||
| 3. **Phase 3**: Gradual rollout to production with monitoring |
There was a problem hiding this comment.
what is meant by "staging environment", and "rollout to production" ?
| style zoneAdapter fill:#c5e1a5 | ||
| ``` | ||
|
|
||
| ### Key Design Choices |
There was a problem hiding this comment.
reading MSR will require higher privileges
I agree, let me strip to down to bare minimal and resubmit. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Introduces enhancement proposal for adding MSR (Model Specific Register) support as a fallback mechanism when Intel RAPL powercap sysfs interface is unavailable. This improves Kepler's deployment flexibility in environments with restricted powercap access.
The proposal includes: