Skip to content

Commit 36df6da

Browse files
Mark-SimulacrumMark-Simulacrum
committed
Add triage for this week
1 parent 6aeb1f8 commit 36df6da

File tree

1 file changed

+263
-0
lines changed

1 file changed

+263
-0
lines changed

‎triage/2025-06-02.md

Lines changed: 263 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,263 @@
1+
# 2025-06-02 Triage Log
2+
3+
A fairly busy week, with lots of changes to performance. Most of the changes
4+
(at least in quantity of benchmarks) are attributable to an update of our PGO
5+
collection to newer benchmarks as part of the 2025 refresh.
6+
7+
Triage done by **@simulacrum**.
8+
Revision range: [2805e1dc..2fc3deed](https://perf.rust-lang.org/?start=2805e1dc4c18ed4c84d161502c48da870c56f68a&end=2fc3deed9fcb8762ad57191e0195f06f7543e4a5&absolute=false&stat=instructions%3Au)
9+
10+
**Summary**:
11+
12+
| (instructions:u) | mean | range | count |
13+
|:----------------------------------:|:-----:|:---------------:|:-----:|
14+
| Regressions ❌ <br /> (primary) | 0.7% | [0.1%, 6.7%] | 56 |
15+
| Regressions ❌ <br /> (secondary) | 0.6% | [0.1%, 1.3%] | 69 |
16+
| Improvements ✅ <br /> (primary) | -1.2% | [-8.9%, -0.1%] | 133 |
17+
| Improvements ✅ <br /> (secondary) | -2.7% | [-20.2%, -0.1%] | 115 |
18+
| All ❌✅ (primary) | -0.6% | [-8.9%, 6.7%] | 189 |
19+
20+
2 Regressions, 6 Improvements, 13 Mixed; 9 of them in rollups
21+
40 artifact comparisons made in total
22+
23+
#### Regressions
24+
25+
Add some track_caller info to precondition panics [#129658](https://github.com/rust-lang/rust/pull/129658) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=45f256d9d7cffb66185c0bf1b8a864cba79db90c&end=be422939446d7c5b27ba98debb6b4b8d6a261f1a&stat=instructions:u)
26+
27+
| (instructions:u) | mean | range | count |
28+
|:----------------------------------:|:-----:|:--------------:|:-----:|
29+
| Regressions ❌ <br /> (primary) | 1.0% | [0.1%, 6.2%] | 14 |
30+
| Regressions ❌ <br /> (secondary) | 0.8% | [0.4%, 1.2%] | 4 |
31+
| Improvements ✅ <br /> (primary) | -0.5% | [-0.5%, -0.5%] | 1 |
32+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
33+
| All ❌✅ (primary) | 0.9% | [-0.5%, 6.2%] | 15 |
34+
35+
Expected regressions to performance for better user experience. No further follow-up warranted.
36+
37+
Rollup of 8 pull requests [#141753](https://github.com/rust-lang/rust/pull/141753) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=1c0849d8bae6f1af08a8b64a011b2ffa7c24f136&end=6de3a733122a82d9b3c3427c7ee16a1e1a022718&stat=instructions:u)
38+
39+
| (instructions:u) | mean | range | count |
40+
|:----------------------------------:|:-----:|:--------------:|:-----:|
41+
| Regressions ❌ <br /> (primary) | 0.4% | [0.1%, 1.4%] | 78 |
42+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.1%, 0.6%] | 46 |
43+
| Improvements ✅ <br /> (primary) | - | - | 0 |
44+
| Improvements ✅ <br /> (secondary) | -0.2% | [-0.3%, -0.1%] | 3 |
45+
| All ❌✅ (primary) | 0.4% | [0.1%, 1.4%] | 78 |
46+
47+
[#141407](https://github.com/rust-lang/rust/pull/141407) seems to be the
48+
primary cause of the impact. This is (in part) a correctness fix so marking the
49+
regression as triaged.
50+
51+
#### Improvements
52+
53+
Rollup of 8 pull requests [#141662](https://github.com/rust-lang/rust/pull/141662) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=c583fa6d8425dbb38fe5d1dbd007f9ca8e4aa128&end=45f256d9d7cffb66185c0bf1b8a864cba79db90c&stat=instructions:u)
54+
55+
| (instructions:u) | mean | range | count |
56+
|:----------------------------------:|:-----:|:--------------:|:-----:|
57+
| Regressions ❌ <br /> (primary) | - | - | 0 |
58+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
59+
| Improvements ✅ <br /> (primary) | - | - | 0 |
60+
| Improvements ✅ <br /> (secondary) | -1.3% | [-4.3%, -0.0%] | 56 |
61+
| All ❌✅ (primary) | - | - | 0 |
62+
63+
Unclear cause. Probably not worth digging deeper as solely improvements and only in secondary benchmarks.
64+
65+
Rollup of 8 pull requests [#141668](https://github.com/rust-lang/rust/pull/141668) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=be422939446d7c5b27ba98debb6b4b8d6a261f1a&end=04a67d5a0587ed98632f82c404ae20f9f0a51a1d&stat=instructions:u)
66+
67+
| (instructions:u) | mean | range | count |
68+
|:----------------------------------:|:-----:|:--------------:|:-----:|
69+
| Regressions ❌ <br /> (primary) | - | - | 0 |
70+
| Regressions ❌ <br /> (secondary) | 0.1% | [0.1%, 0.1%] | 2 |
71+
| Improvements ✅ <br /> (primary) | -0.2% | [-0.2%, -0.1%] | 34 |
72+
| Improvements ✅ <br /> (secondary) | -0.2% | [-0.3%, -0.0%] | 19 |
73+
| All ❌✅ (primary) | -0.2% | [-0.2%, -0.1%] | 34 |
74+
75+
Unclear cause. Probably not worth digging deeper as solely improvements and only in secondary benchmarks.
76+
Started a [PR build](https://github.com/rust-lang/rust/pull/141252#issuecomment-2930408560) to check one potential root cause.
77+
78+
rustdoc: cleanups relating to allocations [#141573](https://github.com/rust-lang/rust/pull/141573) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=6de3a733122a82d9b3c3427c7ee16a1e1a022718&end=e6152cdf5b31bd844a4cc1049433859d54863602&stat=instructions:u)
79+
80+
| (instructions:u) | mean | range | count |
81+
|:----------------------------------:|:-----:|:--------------:|:-----:|
82+
| Regressions ❌ <br /> (primary) | - | - | 0 |
83+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
84+
| Improvements ✅ <br /> (primary) | -0.4% | [-0.6%, -0.2%] | 8 |
85+
| Improvements ✅ <br /> (secondary) | -0.6% | [-0.6%, -0.6%] | 1 |
86+
| All ❌✅ (primary) | -0.4% | [-0.6%, -0.2%] | 8 |
87+
88+
89+
Add fast path for maybe-initializedness in liveness [#141667](https://github.com/rust-lang/rust/pull/141667) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=7a7bcbbcdbf2845164a94377d0e0efebb737ffd3&end=ec28ae9454139023117270985f114823d6570657&stat=instructions:u)
90+
91+
| (instructions:u) | mean | range | count |
92+
|:----------------------------------:|:-----:|:---------------:|:-----:|
93+
| Regressions ❌ <br /> (primary) | - | - | 0 |
94+
| Regressions ❌ <br /> (secondary) | 0.5% | [0.5%, 0.5%] | 1 |
95+
| Improvements ✅ <br /> (primary) | -1.0% | [-10.6%, -0.2%] | 67 |
96+
| Improvements ✅ <br /> (secondary) | -0.5% | [-1.2%, -0.2%] | 59 |
97+
| All ❌✅ (primary) | -1.0% | [-10.6%, -0.2%] | 67 |
98+
99+
100+
cstore: Use IndexSet as backing store for postorder dependencies [#141730](https://github.com/rust-lang/rust/pull/141730) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=13a4540908d25642c0fa0ab726095cf57bbe6824&end=ba55b7ce3cd931af7123e334647584f6fbdb3c20&stat=instructions:u)
101+
102+
| (instructions:u) | mean | range | count |
103+
|:----------------------------------:|:-----:|:--------------:|:-----:|
104+
| Regressions ❌ <br /> (primary) | - | - | 0 |
105+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
106+
| Improvements ✅ <br /> (primary) | - | - | 0 |
107+
| Improvements ✅ <br /> (secondary) | -2.3% | [-5.2%, -0.4%] | 11 |
108+
| All ❌✅ (primary) | - | - | 0 |
109+
110+
Tweak fast path trait handling [#141731](https://github.com/rust-lang/rust/pull/141731) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=ba55b7ce3cd931af7123e334647584f6fbdb3c20&end=9b0268a43b0a5b58f50c96ded25364037c019a61&stat=instructions:u)
111+
112+
| (instructions:u) | mean | range | count |
113+
|:----------------------------------:|:-----:|:--------------:|:-----:|
114+
| Regressions ❌ <br /> (primary) | - | - | 0 |
115+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
116+
| Improvements ✅ <br /> (primary) | - | - | 0 |
117+
| Improvements ✅ <br /> (secondary) | -1.0% | [-2.4%, -0.2%] | 10 |
118+
| All ❌✅ (primary) | - | - | 0 |
119+
120+
#### Mixed
121+
122+
add additional `TypeFlags` fast paths [#141581](https://github.com/rust-lang/rust/pull/141581) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=ebe9b0060240953d721508ceb4d02a745efda88f&end=5f025f363df11c65bd31ade9fe6f48fd4f4239af&stat=instructions:u)
123+
124+
| (instructions:u) | mean | range | count |
125+
|:----------------------------------:|:-----:|:--------------:|:-----:|
126+
| Regressions ❌ <br /> (primary) | 0.1% | [0.1%, 0.2%] | 8 |
127+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.2%, 0.5%] | 20 |
128+
| Improvements ✅ <br /> (primary) | -0.3% | [-0.4%, -0.3%] | 5 |
129+
| Improvements ✅ <br /> (secondary) | -2.5% | [-5.7%, -0.2%] | 10 |
130+
| All ❌✅ (primary) | -0.0% | [-0.4%, 0.2%] | 13 |
131+
132+
Mostly no significant delta (averaging out to 0% change) but worth it in more pathological cases, so makes sense to land the change.
133+
134+
Rollup of 16 pull requests [#141716](https://github.com/rust-lang/rust/pull/141716) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=5f025f363df11c65bd31ade9fe6f48fd4f4239af&end=38081f22c2d7380f272aa1d7fa9b935637701c2d&stat=instructions:u)
135+
136+
| (instructions:u) | mean | range | count |
137+
|:----------------------------------:|:-----:|:--------------:|:-----:|
138+
| Regressions ❌ <br /> (primary) | 0.2% | [0.2%, 0.2%] | 3 |
139+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.3%, 0.3%] | 1 |
140+
| Improvements ✅ <br /> (primary) | - | - | 0 |
141+
| Improvements ✅ <br /> (secondary) | -0.1% | [-0.1%, -0.1%] | 1 |
142+
| All ❌✅ (primary) | 0.2% | [0.2%, 0.2%] | 3 |
143+
144+
Correctness fix in wfcheck ([#136429](https://github.com/rust-lang/rust/pull/136429)). No further investigation needed.
145+
146+
Bump rustc-perf and update PGO crates [#141490](https://github.com/rust-lang/rust/pull/141490) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=13718eb788622ef8c998650451174570230d2971&end=1bbd62e547ba5cc08ccb44c27def3d33195d2dd5&stat=instructions:u)
147+
148+
| (instructions:u) | mean | range | count |
149+
|:----------------------------------:|:-----:|:--------------:|:-----:|
150+
| Regressions ❌ <br /> (primary) | 0.3% | [0.1%, 2.0%] | 46 |
151+
| Regressions ❌ <br /> (secondary) | 0.7% | [0.1%, 3.2%] | 110 |
152+
| Improvements ✅ <br /> (primary) | -0.4% | [-0.9%, -0.1%] | 72 |
153+
| Improvements ✅ <br /> (secondary) | -0.9% | [-4.8%, -0.2%] | 62 |
154+
| All ❌✅ (primary) | -0.1% | [-0.9%, 2.0%] | 118 |
155+
156+
Broad changes due to many benchmark crates getting updated, no particular outcome expected.
157+
158+
Rollup of 11 pull requests [#141739](https://github.com/rust-lang/rust/pull/141739) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=1bbd62e547ba5cc08ccb44c27def3d33195d2dd5&end=1ac1950c337039add1a83113ed6d1bd64bcb1142&stat=instructions:u)
159+
160+
| (instructions:u) | mean | range | count |
161+
|:----------------------------------:|:-----:|:--------------:|:-----:|
162+
| Regressions ❌ <br /> (primary) | 0.1% | [0.1%, 0.1%] | 4 |
163+
| Regressions ❌ <br /> (secondary) | 0.5% | [0.4%, 0.6%] | 2 |
164+
| Improvements ✅ <br /> (primary) | - | - | 0 |
165+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.5%, -0.4%] | 2 |
166+
| All ❌✅ (primary) | 0.1% | [0.1%, 0.1%] | 4 |
167+
168+
Nothing obvious in one cachegrind diff, not worth digging deeper.
169+
170+
Make some assertions in solver into debug assertions [#141651](https://github.com/rust-lang/rust/pull/141651) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=1ac1950c337039add1a83113ed6d1bd64bcb1142&end=1c0849d8bae6f1af08a8b64a011b2ffa7c24f136&stat=instructions:u)
171+
172+
| (instructions:u) | mean | range | count |
173+
|:----------------------------------:|:-----:|:--------------:|:-----:|
174+
| Regressions ❌ <br /> (primary) | - | - | 0 |
175+
| Regressions ❌ <br /> (secondary) | 0.4% | [0.3%, 0.5%] | 2 |
176+
| Improvements ✅ <br /> (primary) | -0.1% | [-0.1%, -0.1%] | 2 |
177+
| Improvements ✅ <br /> (secondary) | -0.8% | [-1.1%, -0.2%] | 11 |
178+
| All ❌✅ (primary) | -0.1% | [-0.1%, -0.1%] | 2 |
179+
180+
Rollup of 5 pull requests [#141765](https://github.com/rust-lang/rust/pull/141765) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=e6152cdf5b31bd844a4cc1049433859d54863602&end=aa5832b142a2bfd322659d60f5d57e25d2a1bd5d&stat=instructions:u)
181+
182+
| (instructions:u) | mean | range | count |
183+
|:----------------------------------:|:-----:|:--------------:|:-----:|
184+
| Regressions ❌ <br /> (primary) | 0.3% | [0.3%, 0.3%] | 6 |
185+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
186+
| Improvements ✅ <br /> (primary) | - | - | 0 |
187+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.4%, -0.4%] | 1 |
188+
| All ❌✅ (primary) | 0.3% | [0.3%, 0.3%] | 6 |
189+
190+
rustc_codegen_llvm: use `threadlocal.address` intrinsic to access TLS [#139385](https://github.com/rust-lang/rust/pull/139385) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=aa5832b142a2bfd322659d60f5d57e25d2a1bd5d&end=15825b7161f8bd6a3482211fbf6727a52aa1166b&stat=instructions:u)
191+
192+
| (instructions:u) | mean | range | count |
193+
|:----------------------------------:|:-----:|:--------------:|:-----:|
194+
| Regressions ❌ <br /> (primary) | - | - | 0 |
195+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.3%, 0.3%] | 1 |
196+
| Improvements ✅ <br /> (primary) | -0.7% | [-2.0%, -0.2%] | 22 |
197+
| Improvements ✅ <br /> (secondary) | -1.4% | [-1.5%, -1.4%] | 3 |
198+
| All ❌✅ (primary) | -0.7% | [-2.0%, -0.2%] | 22 |
199+
200+
Expected speed up to thread local access.
201+
202+
Rollup of 8 pull requests [#141791](https://github.com/rust-lang/rust/pull/141791) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=70b3f4666e24ce22fc32f5e357dbcf85d3254e63&end=0b00e6847b576656d80d7d1e845100fe1663ce0e&stat=instructions:u)
203+
204+
| (instructions:u) | mean | range | count |
205+
|:----------------------------------:|:-----:|:--------------:|:-----:|
206+
| Regressions ❌ <br /> (primary) | 2.9% | [2.9%, 2.9%] | 1 |
207+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.3%, 0.3%] | 1 |
208+
| Improvements ✅ <br /> (primary) | -1.6% | [-1.6%, -1.6%] | 1 |
209+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.4%, -0.3%] | 2 |
210+
| All ❌✅ (primary) | 0.7% | [-1.6%, 2.9%] | 2 |
211+
212+
https://github.com/rust-lang/rust/pull/141765#issuecomment-2930545642
213+
214+
Revert "increase perf of charsearcher for single ascii characters" [#141678](https://github.com/rust-lang/rust/pull/141678) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=ec28ae9454139023117270985f114823d6570657&end=e0d014a3dffbb3f0575cfbeb0f480c5080c4d018&stat=instructions:u)
215+
216+
| (instructions:u) | mean | range | count |
217+
|:----------------------------------:|:-----:|:--------------:|:-----:|
218+
| Regressions ❌ <br /> (primary) | 1.9% | [1.6%, 2.2%] | 2 |
219+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
220+
| Improvements ✅ <br /> (primary) | -1.4% | [-7.3%, -0.2%] | 36 |
221+
| Improvements ✅ <br /> (secondary) | -1.6% | [-4.2%, -0.3%] | 25 |
222+
| All ❌✅ (primary) | -1.2% | [-7.3%, 2.2%] | 38 |
223+
224+
This fixes a perf regression from a previous week.
225+
226+
PGO new solver [#141453](https://github.com/rust-lang/rust/pull/141453) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=e0d014a3dffbb3f0575cfbeb0f480c5080c4d018&end=738c08b63c4f9e3ebdaec5eece7b6fbc354f6467&stat=instructions:u)
227+
228+
| (instructions:u) | mean | range | count |
229+
|:----------------------------------:|:-----:|:---------------:|:-----:|
230+
| Regressions ❌ <br /> (primary) | 0.3% | [0.2%, 0.4%] | 10 |
231+
| Regressions ❌ <br /> (secondary) | 0.2% | [0.2%, 0.3%] | 6 |
232+
| Improvements ✅ <br /> (primary) | -0.2% | [-0.2%, -0.2%] | 1 |
233+
| Improvements ✅ <br /> (secondary) | -8.1% | [-15.0%, -3.3%] | 14 |
234+
| All ❌✅ (primary) | 0.3% | [-0.2%, 0.4%] | 11 |
235+
236+
Expected improvements primarily to new solver benchmarks as we now collect PGO
237+
data. Some regressions are expected due to less precise PGO data for old solver
238+
patterns.
239+
240+
`slice.get(i)` should use a slice projection in MIR, like `slice[i]` does [#139118](https://github.com/rust-lang/rust/pull/139118) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=4d08223c054cf5a56d9761ca925fd46ffebe7115&end=f0999ffdc4818e498949d3b1f2a0ce6be02a0436&stat=instructions:u)
241+
242+
| (instructions:u) | mean | range | count |
243+
|:----------------------------------:|:-----:|:--------------:|:-----:|
244+
| Regressions ❌ <br /> (primary) | - | - | 0 |
245+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.2%, 0.4%] | 3 |
246+
| Improvements ✅ <br /> (primary) | -1.2% | [-1.3%, -1.1%] | 2 |
247+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
248+
| All ❌✅ (primary) | -1.2% | [-1.3%, -1.1%] | 2 |
249+
250+
Within noise threshold for (new) regressed benchmark, otherwise see [#139118 (comment)](https://github.com/rust-lang/rust/pull/139118#issuecomment-2925635519).
251+
252+
Merge coroutine obligation checking into borrowck parallel loop [#141773](https://github.com/rust-lang/rust/pull/141773) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=2fc3deed9fcb8762ad57191e0195f06f7543e4a5&end=91fad92585b2dafc52a074e502b2a6c1f093ca35&stat=instructions:u)
253+
254+
| (instructions:u) | mean | range | count |
255+
|:----------------------------------:|:-----:|:--------------:|:-----:|
256+
| Regressions ❌ <br /> (primary) | - | - | 0 |
257+
| Regressions ❌ <br /> (secondary) | 0.4% | [0.3%, 0.5%] | 2 |
258+
| Improvements ✅ <br /> (primary) | -2.9% | [-2.9%, -2.9%] | 1 |
259+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
260+
| All ❌✅ (primary) | -2.9% | [-2.9%, -2.9%] | 1 |
261+
262+
Not really measurable on (at least) perf, new -Zthreads=4 benchmark doesn't see
263+
any meaningful improvement from this.

0 commit comments

Comments
 (0)