perf(core): eliminate avoidable per-call allocation in hot logging/config paths

[swicken]

Proposed Changes

• Logger lazy Supplier overloads are now actually lazy — the three debug(…, Supplier) and two info(…, Supplier) overloads called message.get() unconditionally; they now check the level first. ~900 call sites use suppliers specifically to skip message building, including ones that did reflectionToString on Contentlets via PermissionBitFactoryImpl debug logging on the reindex path.
• Config int/long/float/boolean getters no longer throw per read — the DOT_* env-alias probe used commons-configuration's throwing 1-arg getter wrapped in vavr Try, so every read of a non-env-overridden key allocated and discarded a NoSuchElementException (with full stack trace). Applied the containsKey guard that getBooleanProperty(name, default) already had.
• Logger.isVelocityMessage memoized via ClassValue — previously allocated a lowercased class name on every Class-keyed log call; ClassValue lookups are allocation-free, keyed per actual Class (no FQN conflation across OSGi classloaders), and entries are released with their class.
• LeakyTokenBucketImpl no longer walks Config per request-cost increment — the four config reads (enabled, refill, max bucket, add-header-info) are TTL-memoized (30s). Runtime overrides via system table / config refresh still take effect within the TTL, preserved deliberately so rate limiting can be toggled during an incident; a test with an injectable TTL pins that contract.

Why

Allocation profiling of a running instance (Pyroscope TLAB profiles under mixed REST/GraphQL/page-render load) attributed the Throwable.fillInStackTrace, Method.copy/Field.copy, and StringLatin1.toLowerCase allocation hotspots to these four spots; Config.get* subtrees alone were ~19% of sampled allocation in a mixed window (e.g. one full Config walk — exception included — per expired session via ClickstreamListener, per 250ms reindex-pause iteration, per request-cost increment). Expected effect is reduced allocation → less GC pressure, not a single-endpoint latency win.

Checklist

• Tests
• Translations
• Security Implications Contemplated (none — no input handling or auth paths touched; rate-limit values remain config-driven)

Additional Info

New/extended unit tests: LoggerTest (suppliers not evaluated when level disabled), LeakyTokenBucketImplTest (runtime config override reaches a running bucket; reads within TTL stay cached), ConfigTest (getLongProperty missing-key default; env-alias-present-but-unparseable falls back to default for int/long/float). The deprecated no-default Config getters still throw NoSuchElementException for missing base keys — that documented contract is unchanged (and pinned by existing tests).

Closes #36145

[github-actions]

❌ Codex Review failed — openai.gpt-5.5

The review job failed before producing output. See the run for details.

_{Run: #27437728136}

[claude]

Claude finished @swicken's task in 1m 8s —— View job

---

Rollback Safety Analysis

• Read rollback-unsafe categories reference
• Get full PR diff
• Analyze changes against unsafe categories
• Apply appropriate label and post findings

---

Result: ✅ Safe To Rollback

The label AI: Safe To Rollback has been applied.

---

Analysis

All six changed files were reviewed against every category in the rollback-unsafe reference. The changes are purely behavioral / in-memory — no database schema, no Elasticsearch mapping, no data migration, no API contract, no OSGi interface, no VTL viewtool surface change.

File	Change	Category checked	Verdict
Logger.java	Lazy Supplier guard + ClassValue memoization for isVelocityMessage	M-4 (OSGi), H-8 (VTL)	Safe — no public method signatures changed; isVelocityMessage is private static. ClassValue behavior is semantically identical to the old toLowerCase path — same result, just cached.
Config.java	containsKey guard before calling props.getInt/getLong/getFloat/getBoolean	None applicable	Safe — pure read-path optimization; no schema, no data, no API contract touched.
LeakyTokenBucketImpl.java	TTL-memoized suppliers for four Config reads; new @VisibleForTesting constructor overload	None applicable	Safe — no public interface changed (implements LeakyTokenBucket); the rate-limit behavior is preserved; config values still refresh within 30 s. New constructor overload is @VisibleForTesting only.
Test files (LoggerTest, ConfigTest, LeakyTokenBucketImplTest)	New / extended unit tests	N/A	Safe — test-only.

No matches against any rollback-unsafe category (C-1 through C-4, H-1 through H-8, M-1 through M-4).