perf(metric-engine)!: Replace mur3 with fxhash for faster TSID generation (#7316)

* feat/change-tsid-gen:
 perf(metric-engine): replace mur3 with fxhash for faster TSID generation

 - Switches from mur3::Hasher128 to fxhash::FxHasher for TSID hashing
 - Pre-computes label-name hash when no nulls are present, avoiding redundant work
 - Adds fast-path for rows without nulls; falls back to slow path otherwise
 - Updates Cargo.toml and lockfile to reflect dependency change

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* feat/change-tsid-gen:
 fix: only check primary-key labels for null when re-using cached hash

 - Rename has_null() → has_null_labels() and restrict the check to the
   primary-key columns so that non-label NULLs do not force a full
   TSID re-computation.
 - Update expected hashes in tests to match the new logic.

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* feat/change-tsid-gen:
 test: add comprehensive TSID generation tests for label ordering and null handling

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* feat/change-tsid-gen:
 bench: add criterion benchmark for TSID generator

 - Compare original mur3 vs current fxhash fast/slow paths
 - Test 2, 5, 10 label sets plus null-value slow path
 - Add mur3 & criterion dev-deps; register bench target

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* feat/change-tsid-gen:
 test: stabilize metric-engine tests by fixing non-deterministic row order

 - Add ORDER BY to SELECTs in TTL tests to ensure consistent output
 - Update expected __tsid values after hash function change
 - Swap expected OTLP metric rows to match new ordering

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

* feat/change-tsid-gen:
 refactor: simplify Default impls and remove redundant code

 - Replace manual Default for TsidGenerator with derive
 - Remove unnecessary into_iter() call
 - Simplify Option::unwrap_or_else to unwrap_or

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>

---------

Signed-off-by: Lei, HUANG <mrsatangel@gmail.com>
This commit is contained in:
Lei, HUANG
2025-12-02 00:38:29 -08:00
committed by GitHub
parent 69f0249039
commit 931556dbd3
12 changed files with 658 additions and 79 deletions

View File

@@ -4327,7 +4327,7 @@ pub async fn test_otlp_metrics_new(store_type: StorageType) {
.await;
// select metrics data
let expected = "[[1753780559836,0.0052544,\"arm64\",\"claude-code\",\"claude-3-5-haiku-20241022\",\"25.0.0\",\"com.anthropic.claude_code\",\"\",\"1.0.62\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"],[1753780559836,2.244618,\"arm64\",\"claude-code\",\"claude-sonnet-4-20250514\",\"25.0.0\",\"com.anthropic.claude_code\",\"\",\"1.0.62\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"]]";
let expected = "[[1753780559836,2.244618,\"arm64\",\"claude-code\",\"claude-sonnet-4-20250514\",\"25.0.0\",\"com.anthropic.claude_code\",\"\",\"1.0.62\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"],[1753780559836,0.0052544,\"arm64\",\"claude-code\",\"claude-3-5-haiku-20241022\",\"25.0.0\",\"com.anthropic.claude_code\",\"\",\"1.0.62\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"]]";
validate_data(
"otlp_metrics_all_select",
&client,
@@ -4399,7 +4399,7 @@ pub async fn test_otlp_metrics_new(store_type: StorageType) {
.await;
// select metrics data
let expected = "[[1753780559836,2.244618,\"claude-code\",\"claude-sonnet-4-20250514\",\"darwin\",\"25.0.0\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"],[1753780559836,0.0052544,\"claude-code\",\"claude-3-5-haiku-20241022\",\"darwin\",\"25.0.0\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"]]";
let expected = "[[1753780559836,0.0052544,\"claude-code\",\"claude-3-5-haiku-20241022\",\"darwin\",\"25.0.0\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"],[1753780559836,2.244618,\"claude-code\",\"claude-sonnet-4-20250514\",\"darwin\",\"25.0.0\",\"claude-code\",\"1.0.62\",\"736525A3-F5D4-496B-933E-827AF23A5B97\",\"ghostty\",\"6DA02FD9-B5C5-4E61-9355-9FE8EC9A0CF4\"]]";
validate_data(
"otlp_metrics_select",
&client,

View File

@@ -363,7 +363,7 @@ pub async fn test_metric_table_region_migration_by_sql(
let result = cluster
.frontend
.instance
.do_query("select * from t1", query_ctx.clone())
.do_query("select * from t1 order by host desc", query_ctx.clone())
.await
.remove(0);
@@ -379,7 +379,7 @@ pub async fn test_metric_table_region_migration_by_sql(
let result = cluster
.frontend
.instance
.do_query("select * from t2", query_ctx)
.do_query("select * from t2 order by job desc", query_ctx)
.await
.remove(0);