Finished triage for this week.

pnkfelix · pnkfelix · commit 9804362a1bf5 · 2023-11-08T09:33:20.000-05:00
diff --git a/triage/2023-11-07.md b/triage/2023-11-07.md
@@ -1,6 +1,11 @@
 # 2023-11-07 Triage Log
 
-TODO: Summary
+A difficult week for triage, due to what appears to be system-level disruption to
+measurement apparatus, yielding transient noise (and potentially masking actual
+problems). The main non-noise performance change was huge regression to bitmaps introduced
+by PR 117131, and that already has a fix in-flight fix (PR #117542). The other thing
+worth noting is that the parallel rustc front-end has been enabled in the nighlty builds,
+which has introduced some overhead that was expected by wg-parallel-rustc.
 
 Triage done by **@pnkfelix**.
 Revision range: [650991d6..7b97a5ca](https://perf.rust-lang.org/?start=650991d62c3a2c80ba27009d06839adbb038bf5e&end=7b97a5ca8422d1495a8918106d3249aa405812d4&absolute=false&stat=instructions%3Au)
@@ -31,6 +36,9 @@ Accept less invalid Rust in rustdoc [#117450](https://github.com/rust-lang/rust/
 | Improvements ✅ <br /> (secondary) | -    | -             | 0     |
 | All ❌✅ (primary)                 | 4.1% | [0.6%, 21.0%] | 17    |
 
+* primary regressions are to doc benchmarks, were anticipated, and are unavoidable.
+* marking as triaged.
+
 
 Fix order of implementations in the "implementations on foreign types" section [#117521](https://github.com/rust-lang/rust/pull/117521) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=c5afe0a61e39bdd912803eae8d1887a513bdd172&end=b20f40dba9feabf4b446d9b09d15996f0c046eff&stat=instructions:u)
 
@@ -42,6 +50,9 @@ Fix order of implementations in the "implementations on foreign types" section [
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 2.4% | [0.7%, 3.3%] | 3     |
 
+* the primary regressions are to diesel-doc-full (3.35%), syn-opt-full (3.07%) and serde-doc-full (0.69%).
+* the syn-opt-full "regression" is noise; the other two primary benchmarks are doc; this is rustdoc fix and that team has already said they don't think they can do much to address the situation there.
+* marking as triaged.
 
 dropck_outlives check whether generator witness needs_drop [#117134](https://github.com/rust-lang/rust/pull/117134) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=e8418e092a643ef87019192af7ed6bbd23cc4a63&end=a2f5f9691b6ce64c1703feaf9363710dfd7a56cf&stat=instructions:u)
 
@@ -53,6 +64,9 @@ dropck_outlives check whether generator witness needs_drop [#117134](https://git
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 0.3% | [0.2%, 0.3%] | 5     |
 
+* regressed ripgrep check for incr-patched:println (0.35%), incr-full (0.26%), and full (0.21%); regressed regex check for incr-patched:Job (0.29%) and incr-patched:println (0.24%).
+* this is easily justified; it is fixing a code-acceptance regression
+* marking as triaged
 
 Add track_caller to transmute_copy [#117510](https://github.com/rust-lang/rust/pull/117510) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=1d6f05fd3735efc8f5af2f6278a3391543c2790b&end=49112241e96aaca646b1aa8ef704e494f56feed4&stat=instructions:u)
 
@@ -64,6 +78,9 @@ Add track_caller to transmute_copy [#117510](https://github.com/rust-lang/rust/p
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 0.4% | [0.4%, 0.4%] | 3     |
 
+* regressed bitmaps incr-full for check (0.37%), opt (0.36%), and debug (0.36%).
+* this seems likely to be noise. It certainly paled in comparison to the regression associated with #117131 for this benchmark (see below).
+* marking as triaged.
 
 Guarantee representation of None in NPO [#115333](https://github.com/rust-lang/rust/pull/115333) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=9c20ddd956426d577d77cb3f57a7db2227a3c6e9&end=1bb6553b967b69eed9ed8147e78b4f65cfc48e11&stat=instructions:u)
 
@@ -75,6 +92,10 @@ Guarantee representation of None in NPO [#115333](https://github.com/rust-lang/r
 | Improvements ✅ <br /> (secondary) | -     | -             | 0     |
 | All ❌✅ (primary)                 | 12.2% | [0.9%, 30.1%] | 8     |
 
+* this is a docs change.
+* There was a spike of noise that somehow significantly (but temporarily) affected three instances of stm32f4 debug, as well as clap opt (all of which immediately went away in the next commit).
+* there is more [discussion of why on zulip](https://rust-lang.zulipchat.com/#narrow/stream/242791-t-infra/topic/perf.20is.20slow.20again/near/400329622)
+* already marked as triaged.
 
 clone less [#117540](https://github.com/rust-lang/rust/pull/117540) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=5020f7c3b8bd8bf57077389bca5c19f7911fde7a&end=f1b104f52350c800f78d4372aec52080bd6f9164&stat=instructions:u)
 
@@ -86,6 +107,8 @@ clone less [#117540](https://github.com/rust-lang/rust/pull/117540) [(Comparison
 | Improvements ✅ <br /> (secondary) | -     | -             | 0     |
 | All ❌✅ (primary)                 | 16.5% | [1.1%, 30.2%] | 3     |
 
+* the regressions here seem to be correlated with the same spike of noise that afflicted #115333.
+* marking as triaged
 
 Run tidy license checker on more workspaces [#115274](https://github.com/rust-lang/rust/pull/115274) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=f1b104f52350c800f78d4372aec52080bd6f9164&end=3aaa0f57b7b877ef58532a8de075d1e5a79142bf&stat=instructions:u)
 
@@ -97,6 +120,8 @@ Run tidy license checker on more workspaces [#115274](https://github.com/rust-la
 | Improvements ✅ <br /> (secondary) | -    | -             | 0     |
 | All ❌✅ (primary)                 | 8.8% | [3.3%, 17.8%] | 3     |
 
+* the regressions here seem to be correlated with the same spike of noise that afflicted #115333.
+* already marked as triaged
 
 Warn users who set `non_exhaustive_omitted_patterns` lint level on a match arm [#117094](https://github.com/rust-lang/rust/pull/117094) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=2db26d3d55387930f1b1dfb84810bcde5a787a09&end=f81d6f0cb00b1e314107b81bcb9aa72b9df9f564&stat=instructions:u)
 
@@ -108,6 +133,10 @@ Warn users who set `non_exhaustive_omitted_patterns` lint level on a match arm [
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 0.2% | [0.2%, 0.3%] | 3     |
 
+* regressed check incr-full for cranelift-codegen (0.25%), cargo (0.22%) and hyper (0.21%).
+* this small amount does not appear to be noise
+* but it shouldn't have any (significant) effect if the `non_exhaustive_omitted_patterns` lint is not in use.
+* marking as triaged
 
 Rollup of 6 pull requests [#117590](https://github.com/rust-lang/rust/pull/117590) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=a42d94ebb883116f2867cbe3016d9bde9ca6d3f7&end=4b85902b438f791c5bfcb6b1c5b476d5b88e2bef&stat=instructions:u)
 
@@ -119,6 +148,8 @@ Rollup of 6 pull requests [#117590](https://github.com/rust-lang/rust/pull/11759
 | Improvements ✅ <br /> (secondary) | -     | -             | 0     |
 | All ❌✅ (primary)                 | 12.7% | [0.4%, 30.9%] | 6     |
 
+* the primary regressions (bitmaps and cargo), while huge, are also clearly noise.
+* marking as triaged.
 
 enable parallel rustc front end in nightly builds [#117435](https://github.com/rust-lang/rust/pull/117435) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=fcca978aa0c9a7443649305dd0ed48c4691a1e89&end=f9b644636f8c74d1d9a3283dc65a6a6f02a97718&stat=instructions:u)
 
@@ -130,6 +161,9 @@ enable parallel rustc front end in nightly builds [#117435](https://github.com/r
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 2.9% | [0.4%, 5.1%] | 209   |
 
+* I was not sure that wg-parallel-rustc was anticipating there being this much of a regression here.
+* after followup in [zulip for wg-parallel-rustc](https://rust-lang.zulipchat.com/#narrow/stream/187679-t-compiler.2Fwg-parallel-rustc/topic/performance.20results/near/400790214), they clarified that their expectation of a 1.65% regression was based on wall-time that includes so-called "non-relevant results". (Our default rustc-perf presentation filters out the non-relevant results, which will boost outliers and thus inflate the true mean effect.)
+* concluded that this was anticipated and marking as triaged
 
 #### Improvements
 
@@ -143,6 +177,8 @@ bootstrap: do not purge docs on CI environment [#117471](https://github.com/rust
 | Improvements ✅ <br /> (secondary) | -     | -              | 0     |
 | All ❌✅ (primary)                 | -3.0% | [-3.0%, -3.0%] | 1     |
 
+* single improvement to syn-opt-full that is almost certainly noise.
+* and was reverted anyway in PR #117533
 
 Remove support for compiler plugins. [#116412](https://github.com/rust-lang/rust/pull/116412) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=1bb6553b967b69eed9ed8147e78b4f65cfc48e11&end=5020f7c3b8bd8bf57077389bca5c19f7911fde7a&stat=instructions:u)
 
@@ -154,6 +190,7 @@ Remove support for compiler plugins. [#116412](https://github.com/rust-lang/rust
 | Improvements ✅ <br /> (secondary) | -      | -               | 0     |
 | All ❌✅ (primary)                 | -10.1% | [-23.2%, -0.9%] | 8     |
 
+* perf improvements here are mostly noise.
 
 Rollup of 3 pull requests [#117564](https://github.com/rust-lang/rust/pull/117564) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=3aaa0f57b7b877ef58532a8de075d1e5a79142bf&end=a9b03ffe9b23a0832c897e25f246439d99d3026d&stat=instructions:u)
 
@@ -165,6 +202,7 @@ Rollup of 3 pull requests [#117564](https://github.com/rust-lang/rust/pull/11756
 | Improvements ✅ <br /> (secondary) | -     | -               | 0     |
 | All ❌✅ (primary)                 | -9.6% | [-15.4%, -3.0%] | 4     |
 
+* again, perf improvements here seem to be noise
 
 Hint optimizer about try-reserved capacity [#117503](https://github.com/rust-lang/rust/pull/117503) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=4b85902b438f791c5bfcb6b1c5b476d5b88e2bef&end=f5ca57e153afaed818f8be88abf5ce46715c0f9a&stat=instructions:u)
 
@@ -176,6 +214,8 @@ Hint optimizer about try-reserved capacity [#117503](https://github.com/rust-lan
 | Improvements ✅ <br /> (secondary) | -13.5% | [-19.5%, -7.5%] | 2     |
 | All ❌✅ (primary)                 | -10.4% | [-23.6%, -0.4%] | 6     |
 
+* improvement here is transient noise on bitmaps and cargo.
+
 
 #### Mixed
 
@@ -189,6 +229,11 @@ Update cargo [#117462](https://github.com/rust-lang/rust/pull/117462) [(Comparis
 | Improvements ✅ <br /> (secondary) | -1.5% | [-1.5%, -1.5%] | 1     |
 | All ❌✅ (primary)                 | 0.2%  | [-0.6%, 1.1%]  | 4     |
 
+* regressions are to unicode-normalization-opt-incr-patched:println (1.06%) and clar-opt-full (0.81%)
+* the regressions to instruction counts seem small but they persist; i.e. this is not transient noise. (It is not clear whether the cost is borne from cargo itself, or if something has changed about how cargo is invoking rustc that incurs this cost.)
+* on the other hand, cycle counts and wall time are not impacted at all, which implies to me that this is probably not worth investigating.
+* marking as triaged.
+
 
 Rollup of 5 pull requests [#117459](https://github.com/rust-lang/rust/pull/117459) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=9d83ac217957eece2189eccf4a7232caec7232ee&end=09ac6e4b6dbec74dc4718191a6650a1b7e04a7a6&stat=instructions:u)
 
@@ -200,6 +245,8 @@ Rollup of 5 pull requests [#117459](https://github.com/rust-lang/rust/pull/11745
 | Improvements ✅ <br /> (secondary) | -     | -              | 0     |
 | All ❌✅ (primary)                 | -0.2% | [-0.3%, -0.1%] | 3     |
 
+* regressons are all minor and to variants of secondary benchmark coercions
+* marking as triaged
 
 Add all RPITITs when augmenting param-env with GAT bounds in `check_type_bounds` [#117131](https://github.com/rust-lang/rust/pull/117131) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=a2f5f9691b6ce64c1703feaf9363710dfd7a56cf&end=2520ca8566e596b10b0a163d31d9ce216876fafc&stat=instructions:u)
 
@@ -211,41 +258,7 @@ Add all RPITITs when augmenting param-env with GAT bounds in `check_type_bounds`
 | Improvements ✅ <br /> (secondary) | -1.4% | [-1.7%, -1.0%] | 6     |
 | All ❌✅ (primary)                 | 32.3% | [0.3%, 99.8%]  | 19    |
 
-
-#### Untriaged Pull Requests
-
-- [#117590 Rollup of 6 pull requests](https://github.com/rust-lang/rust/pull/117590)
-- [#117540 clone less](https://github.com/rust-lang/rust/pull/117540)
-- [#117521 Fix order of implementations in the "implementations on foreign types" section](https://github.com/rust-lang/rust/pull/117521)
-- [#117510 Add track_caller to transmute_copy](https://github.com/rust-lang/rust/pull/117510)
-- [#117462 Update cargo](https://github.com/rust-lang/rust/pull/117462)
-- [#117459 Rollup of 5 pull requests](https://github.com/rust-lang/rust/pull/117459)
-- [#117450 Accept less invalid Rust in rustdoc](https://github.com/rust-lang/rust/pull/117450)
-- [#117435 enable parallel rustc front end in nightly builds](https://github.com/rust-lang/rust/pull/117435)
-- [#117180 Rollup of 7 pull requests](https://github.com/rust-lang/rust/pull/117180)
-- [#117134 dropck_outlives check whether generator witness needs_drop](https://github.com/rust-lang/rust/pull/117134)
-- [#117131 Add all RPITITs when augmenting param-env with GAT bounds in `check_type_bounds`](https://github.com/rust-lang/rust/pull/117131)
-- [#117094 Warn users who set `non_exhaustive_omitted_patterns` lint level on a match arm](https://github.com/rust-lang/rust/pull/117094)
-- [#116940 Rollup of 4 pull requests](https://github.com/rust-lang/rust/pull/116940)
-- [#116889 Eat close paren if capture_cfg to avoid unbalanced parens](https://github.com/rust-lang/rust/pull/116889)
-- [#116492 Rollup of 7 pull requests](https://github.com/rust-lang/rust/pull/116492)
-- [#116391 exhaustiveness: Rework constructor splitting](https://github.com/rust-lang/rust/pull/116391)
-- [#116183 Always preserve DebugInfo in DeadStoreElimination.](https://github.com/rust-lang/rust/pull/116183)
-- [#116033 report `unused_import` for empty reexports even it is pub](https://github.com/rust-lang/rust/pull/116033)
-- [#115762 Explain revealing of opaque types in layout_of ParamEnv](https://github.com/rust-lang/rust/pull/115762)
-- [#115751 some inspect improvements](https://github.com/rust-lang/rust/pull/115751)
-- [#115740 Cache reachable_set on disk](https://github.com/rust-lang/rust/pull/115740)
-- [#115252 Represent MIR composite debuginfo as projections instead of aggregates](https://github.com/rust-lang/rust/pull/115252)
-- [#115082 Fix races conditions with `SyntaxContext` decoding](https://github.com/rust-lang/rust/pull/115082)
-- [#115025 Make subtyping explicit in MIR](https://github.com/rust-lang/rust/pull/115025)
-- [#114892 Remove conditional use of `Sharded` from query caches](https://github.com/rust-lang/rust/pull/114892)
-- [#114481 Rollup of 9 pull requests](https://github.com/rust-lang/rust/pull/114481)
-- [#114459 Do not run ConstProp on mir_for_ctfe.](https://github.com/rust-lang/rust/pull/114459)
-- [#114321 get auto traits for parallel rustc](https://github.com/rust-lang/rust/pull/114321)
-- [#114023 Warn on inductive cycle in coherence leading to impls being considered not overlapping](https://github.com/rust-lang/rust/pull/114023)
-- [#114004 Add `riscv64gc-unknown-hermit` target](https://github.com/rust-lang/rust/pull/114004)
-
-#### Nags requiring follow up
-
-TODO: Nags
-
+* the regression to bitmaps (to 13 variants, ranging from 10.8% to 99.8%) appears persistent (non-noise)
+* it carries over to cycle-count and wall-clock time.
+* compiler-errors has been investigating, and it looks like PR #117542 will address it.
+* marking as triaged
