Add perf triage for 2024-11-05

triage/2024-11-05.md

@@ -0,0 +1,111 @@
+# 2024-11-05 Triage Log
+
+A week dominated by one large improvement and one large regression where luckily the improvement had a larger impact. The regression seems to have been caused by a newly introduced lint that might have performance issues. The improvement was in building rustc with protected visibility which reduces the number of dynamic relocations needed leading to some nice performance gains. Across a large swath of the perf suit, the compiler is on average 1% faster after this week compared to last week.
+
+Triage done by **@rylev**.
+Revision range: [c8a8c820..27e38f8f](https://perf.rust-lang.org/?start=c8a8c82035439cb2404b8f24ca0bc18209d534ca&end=27e38f8fc7efc57b75e9a763d7a0ee44822cd5f7&absolute=false&stat=instructions%3Au)
+
+**Summary**:
+
+| (instructions:u)                   | mean  | range           | count |
+|:----------------------------------:|:-----:|:---------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | 0.8%  | [0.1%, 2.0%]    | 80    |
+| Regressions ❌ <br /> (secondary)  | 1.9%  | [0.2%, 3.4%]    | 45    |
+| Improvements ✅ <br /> (primary)   | -1.9% | [-31.6%, -0.1%] | 148   |
+| Improvements ✅ <br /> (secondary) | -5.1% | [-27.8%, -0.1%] | 180   |
+| All ❌✅ (primary)                 | -1.0% | [-31.6%, 2.0%]  | 228   |
+
+
+1 Regression, 1 Improvement, 5 Mixed; 3 of them in rollups
+46 artifact comparisons made in total
+
+#### Regressions
+
+Rollup of 6 pull requests [#132326](https://github.com/rust-lang/rust/pull/132326) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=e473783d90e2289b8a97575fa60d6315f0a318eb&end=1e4f10ba6476e48a42a79b9f846a2d9366525b9e&stat=instructions:u)
+
+| (instructions:u)                   | mean | range        | count |
+|:----------------------------------:|:----:|:------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | 0.7% | [0.2%, 1.9%] | 104   |
+| Regressions ❌ <br /> (secondary)  | 1.5% | [0.1%, 4.4%] | 68    |
+| Improvements ✅ <br /> (primary)   | -    | -            | 0     |
+| Improvements ✅ <br /> (secondary) | -    | -            | 0     |
+| All ❌✅ (primary)                 | 0.7% | [0.2%, 1.9%] | 104   |
+- Fairly large regression caused by https://github.com/rust-lang/rust/pull/131984.
+- Most likely due to a non-performant lint being run that wasn't previously.
+- Checked with the author and reviewer.
+
+
+#### Improvements
+
+Use protected visibility when building rustc with LLD [#131634](https://github.com/rust-lang/rust/pull/131634) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=a8e1186e3c14a54f7a38cc1183117dc7e77f4f82&end=9fa9ef385c0aad8f5d4c8f7d92dca474367943a3&stat=instructions:u)
+
+| (instructions:u)                   | mean  | range           | count |
+|:----------------------------------:|:-----:|:---------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | -     | -               | 0     |
+| Regressions ❌ <br /> (secondary)  | -     | -               | 0     |
+| Improvements ✅ <br /> (primary)   | -1.8% | [-31.3%, -0.1%] | 174   |
+| Improvements ✅ <br /> (secondary) | -4.2% | [-27.5%, -0.2%] | 224   |
+| All ❌✅ (primary)                 | -1.8% | [-31.3%, -0.1%] | 174   |
+
+
+#### Mixed
+
+Rollup of 12 pull requests [#132317](https://github.com/rust-lang/rust/pull/132317) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=c8a8c82035439cb2404b8f24ca0bc18209d534ca&end=2dece5bb62f234f5622a08289c5a3d1555cd7843&stat=instructions:u)
+
+| (instructions:u)                   | mean  | range          | count |
+|:----------------------------------:|:-----:|:--------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | 0.2%  | [0.2%, 0.4%]   | 4     |
+| Regressions ❌ <br /> (secondary)  | 0.2%  | [0.2%, 0.2%]   | 1     |
+| Improvements ✅ <br /> (primary)   | -0.2% | [-0.4%, -0.1%] | 6     |
+| Improvements ✅ <br /> (secondary) | -0.3% | [-0.3%, -0.3%] | 1     |
+| All ❌✅ (primary)                 | -0.0% | [-0.4%, 0.4%]  | 10    |
+- Looks like a bit more time spent in LLVM? Might have been caused by a few PRs in this rollup, but the total result is a wash, so I don't think it's needed to dig deeper into this.
+
+
+Rc/Arc: don't leak the allocation if drop panics [#132231](https://github.com/rust-lang/rust/pull/132231) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=2dece5bb62f234f5622a08289c5a3d1555cd7843&end=e473783d90e2289b8a97575fa60d6315f0a318eb&stat=instructions:u)
+
+| (instructions:u)                   | mean  | range          | count |
+|:----------------------------------:|:-----:|:--------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | 0.6%  | [0.6%, 0.6%]   | 1     |
+| Regressions ❌ <br /> (secondary)  | 2.3%  | [1.1%, 3.5%]   | 6     |
+| Improvements ✅ <br /> (primary)   | -0.9% | [-1.4%, -0.3%] | 3     |
+| Improvements ✅ <br /> (secondary) | -0.4% | [-0.6%, -0.2%] | 5     |
+| All ❌✅ (primary)                 | -0.5% | [-1.4%, 0.6%]  | 4     |
+- There probably isn't too much to be done regarding perf, all of the major regressions come from one small stress test crate. 
+
+
+Mark `simplify_aggregate_to_copy` mir-opt as unsound [#132356](https://github.com/rust-lang/rust/pull/132356) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=20c909ff9cdd88d33768a4ddb8952927a675b0ad&end=a0d98ff0e5b6e1f2c63fd26f68484792621b235c&stat=instructions:u)
+
+| (instructions:u)                   | mean  | range          | count |
+|:----------------------------------:|:-----:|:--------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | 0.7%  | [0.3%, 1.9%]   | 14    |
+| Regressions ❌ <br /> (secondary)  | 0.7%  | [0.2%, 2.3%]   | 16    |
+| Improvements ✅ <br /> (primary)   | -0.3% | [-0.3%, -0.3%] | 1     |
+| Improvements ✅ <br /> (secondary) | -0.3% | [-0.4%, -0.3%] | 5     |
+| All ❌✅ (primary)                 | 0.7%  | [-0.3%, 1.9%]  | 15    |
+- This deactivated an unsound MIR optimization until it is fixed.
+
+
+add const_panic macro to make it easier to fall back to non-formatting panic in const [#132542](https://github.com/rust-lang/rust/pull/132542) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=7028d9318fadc20e5e3058d52e44d785d31a6aaa&end=e3a918ece026cec748fc64af5b4983095b46097e&stat=instructions:u)
+
+| (instructions:u)                   | mean  | range          | count |
+|:----------------------------------:|:-----:|:--------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | 0.8%  | [0.2%, 1.8%]   | 6     |
+| Regressions ❌ <br /> (secondary)  | -     | -              | 0     |
+| Improvements ✅ <br /> (primary)   | -0.5% | [-0.9%, -0.1%] | 5     |
+| Improvements ✅ <br /> (secondary) | -     | -              | 0     |
+| All ❌✅ (primary)                 | 0.2%  | [-0.9%, 1.8%]  | 11    |
+- Looks like most of the regressions are taking longer in LLVM related queries (e.g., LLVM_module_codegen_emit_obj) which doesn't make a ton of sense to me.
+
+
+Rollup of 11 pull requests [#132626](https://github.com/rust-lang/rust/pull/132626) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=96477c55bcfa7121470ed225f602c1c639aeaa18&end=27e38f8fc7efc57b75e9a763d7a0ee44822cd5f7&stat=instructions:u)
+
+| (instructions:u)                   | mean  | range          | count |
+|:----------------------------------:|:-----:|:--------------:|:-----:|
+| Regressions ❌ <br /> (primary)    | -     | -              | 0     |
+| Regressions ❌ <br /> (secondary)  | 0.6%  | [0.5%, 0.9%]   | 7     |
+| Improvements ✅ <br /> (primary)   | -     | -              | 0     |
+| Improvements ✅ <br /> (secondary) | -0.3% | [-0.3%, -0.3%] | 2     |
+| All ❌✅ (primary)                 | -     | -              | 0     |
+- It's not obvious to me which PR might be the culprit here and the regression is small and contained enough that I don't think it's worth investigating.
+