[kv_cache] Expose kv_cache_pull duration as a metric - #678
Open
copybara-service[bot] wants to merge 1 commit into
Open
[kv_cache] Expose kv_cache_pull duration as a metric#678copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
Changes include:
* Define the `kTransferDurationMs` metric in `metrics_api.h`.
* Instrument `KVCacheManagerWithTransfer` to track `start_time` for
receive entries and recording the total duration in milliseconds
upon transfer completion.
* Introduce `mock_metrics_backend.h` with `MockMetricsBackend` and
`ScopedMetricsBackendReset` to facilitate the testing of telemetry metrics.
* Add unit tests in `kv_cache_manager_with_transfer_test` and
`kv_cache_manager_with_transfer_pool_reshard_test` to verify that the
duration metric is properly recorded on success and omitted on failure.
PiperOrigin-RevId: 965213481
copybara-service
Bot
force-pushed
the
test_965213481
branch
from
August 16, 2026 10:28
0a70342 to
d8a9501
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
[kv_cache] Expose kv_cache_pull duration as a metric
Changes include:
kTransferDurationMsmetric inmetrics_api.h.KVCacheManagerWithTransferto trackstart_timeforreceive entries and recording the total duration in milliseconds
upon transfer completion.
mock_metrics_backend.hwithMockMetricsBackendandScopedMetricsBackendResetto facilitate the testing of telemetry metrics.kv_cache_manager_with_transfer_testandkv_cache_manager_with_transfer_pool_reshard_testto verify that theduration metric is properly recorded on success and omitted on failure.