Skip to content

v2.15.1 — HiCache scheduler and resource metrics

Choose a tag to compare

View all tags
@ketor ketor released this 11 Aug 06:49
· 10 commits to main since this release
v2.15.1
7a17394

HiCache / SGLang metric visibility

The native client already exported v2.14 read-scheduler and process-wide RDMA resource metrics, but the connector allowlist silently discarded them. HiCache and SGLang /metrics now expose:

  • pending batches, pending shards, and active shards
  • cumulative scheduler queue delay and fairness yields
  • endpoint, QP, WR-slot, and registered-slot-byte budgets with bounded kind=used|limit
  • resource-budget admission timeouts
  • endpoint-cache hits, misses, and pressure evictions

No C++ data-path behavior changed.

Compatibility

This patch only extends the Python connector metric allowlist. Unknown native metrics remain ignored and all labels remain fixed-cardinality.

Verification

PR #315 and release PR #316 passed all 8 CI jobs. Post-merge main CI run 31466216686 passed all 8 jobs. The release artifact reports 2.15.1 for dfkv_server, dfkvctl, dfkv_mds, and libdfkv.so. SHA256: a62dfe8c6e035d1229bc82cdd9003c9b34ee4bd0d8c588a11ab4d667ac279043.

Assets 4
Loading