Demote HiCache/CacheCtrl per-op logs from info to debug

The [HiCache-write]/[HiCache-load]/[HiCache-collective] and
[CacheCtrl-write] per-operation logs fired at INFO on the scheduler
thread during serving (every write-through, load-back, ack release,
and rate-limited collective summary), eating into stream gaps.
Demote all 29 to debug; one-time [HiCache-draft] init logs stay INFO
and genuine failures stay WARNING (write_backup CP FAILED after
deterministic retry).

Also repair TestHiCacheEvictLoggingLevels, which asserted markers
that no longer exist in this tree (stale list, failing on the
pristine branch): pin the current hot-path markers as debug-only and
extend the check to cache_controller.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-06-10 05:10:45 +00:00
co-authored by Claude Fable 5
parent d221212565
commit e6864fbea7
3 changed files with 50 additions and 40 deletions
@@ -152,20 +152,30 @@ class TestHiCacheEvictLoggingLevels(CustomTestCase):
self.assert_debug_marker(common_source, marker)
for marker in (
"[HiCache-load] owner-lane device eviction before CP load-back: ",
"[HiCache-evict] owner-lane evict found no contributing victims: ",
"[HiCache-evict] owner-lane evict victim no longer evictable: ",
"[HiCache-evict] owner-lane evict END: requested_tokens=%d ",
"[HiCache-evict] deterministic CP host eviction before write: ",
"[HiCache-write] write_backup CP retry after deterministic host eviction: ",
"[HiCache-evict] evict START:",
"[HiCache-evict] evict END:",
"[HiCache-evict] _evict_backuped:",
"[HiCache-evict] _evict_regular:",
"[HiCache-evict] _evict_host_for_physical_slots:",
"[HiCache-write] write_backup triggered: node_id=%d",
"[HiCache-write] write_backup CP SUBMITTED: node_id=%d",
"[HiCache-write] write_backup non-CP SUCCESS: node_id=%d",
"[HiCache-write] write_backup non-CP FAILED (host full): node_id=%d",
"[HiCache-write] _inc_hit_count triggering write_through: node_id=%d",
"[HiCache-write] writing_check released %d write locks:",
"[HiCache-load] load_back CP: node_id=%d",
"[HiCache-load] load_back CP SUCCESS: node_id=%d",
"[HiCache-load] load_back non-CP SUCCESS: node_id=%d",
"[HiCache-collective] tag=%s",
):
self.assert_debug_marker(hiradix_source, marker)
import sglang.srt.managers.cache_controller as cache_controller_mod
cache_controller_source = inspect.getsource(cache_controller_mod)
for marker in (
"[CacheCtrl-write] write: node_id=%d",
"[CacheCtrl-write] write non-CP submitted: node_id=%d",
"[CacheCtrl-write] submit_write_cp_all_layer submitted: node_id=%d",
"[CacheCtrl-write] submit_write_cp_layer final ack: node_id=%d",
):
self.assert_debug_marker(cache_controller_source, marker)
self.assertRegex(
hiradix_source,
r"logger\.warning\(\s*\n\s*\"\[HiCache-write\] write_backup CP FAILED after deterministic retry:",