Skip to content

Commit e395e6f

Browse files
KobzolKobzol
authored
Merge pull request #2333 from rust-lang/panstromek-patch-1
Add triage for 2025-11-19
2 parents 54257f3 + 634b10a commit e395e6f

File tree

1 file changed

+215
-0
lines changed

1 file changed

+215
-0
lines changed

‎triage/2025/2025-11-19.md‎

Lines changed: 215 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,215 @@
1+
# 2025-11-19 Triage Log
2+
3+
Positive week, most notably because of the new format_args!() and fmt::Arguments implementation from [#148789](https://github.com/rust-lang/rust/pull/148789). Another notable improvement came from moving some computations from one compiler stage to another to save memory and unnecessary tree traversals in [#148706](https://github.com/rust-lang/rust/pull/148706)
4+
5+
Triage done by **@panstromek**.
6+
Revision range: [055d0d6a..6159a440](https://perf.rust-lang.org/?start=055d0d6aaf937cc11b3d2a5b5725972723b7f3c6&end=6159a44067ebce42b38f062cc7df267a1348e092&absolute=false&stat=instructions%3Au)
7+
8+
**Summary**:
9+
10+
| (instructions:u) | mean | range | count |
11+
|:----------------------------------:|:-----:|:---------------:|:-----:|
12+
| Regressions ❌ <br /> (primary) | 1.6% | [0.2%, 5.6%] | 11 |
13+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.1%, 1.1%] | 26 |
14+
| Improvements ✅ <br /> (primary) | -0.8% | [-4.5%, -0.1%] | 161 |
15+
| Improvements ✅ <br /> (secondary) | -1.4% | [-38.1%, -0.1%] | 168 |
16+
| All ❌✅ (primary) | -0.6% | [-4.5%, 5.6%] | 172 |
17+
18+
19+
2 Regressions, 4 Improvements, 10 Mixed; 4 of them in rollups
20+
48 artifact comparisons made in total
21+
22+
#### Regressions
23+
24+
Rollup of 7 pull requests [#148885](https://github.com/rust-lang/rust/pull/148885) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=503dce33e2e2a5d2fe978b2723ab2a994cc27472&end=5dbf4069dc98bbbca98dd600a65f50c258fbfd56&stat=instructions:u)
25+
26+
| (instructions:u) | mean | range | count |
27+
|:----------------------------------:|:----:|:------------:|:-----:|
28+
| Regressions ❌ <br /> (primary) | 3.0% | [3.0%, 3.0%] | 1 |
29+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
30+
| Improvements ✅ <br /> (primary) | - | - | 0 |
31+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
32+
| All ❌✅ (primary) | 3.0% | [3.0%, 3.0%] | 1 |
33+
34+
`clap_derive` bimodal noise
35+
36+
Rollup of 11 pull requests [#148988](https://github.com/rust-lang/rust/pull/148988) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=54f417673c9733bf8f8ce126e4a0e299536cb3d6&end=67c4cf395f243afcb973dacdd39b16895c9ad295&stat=instructions:u)
37+
38+
| (instructions:u) | mean | range | count |
39+
|:----------------------------------:|:----:|:------------:|:-----:|
40+
| Regressions ❌ <br /> (primary) | 3.0% | [3.0%, 3.0%] | 1 |
41+
| Regressions ❌ <br /> (secondary) | 0.1% | [0.1%, 0.2%] | 2 |
42+
| Improvements ✅ <br /> (primary) | - | - | 0 |
43+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
44+
| All ❌✅ (primary) | 3.0% | [3.0%, 3.0%] | 1 |
45+
46+
Triaged by @Zalathar: The clap_derive result looks pretty clearly bimodal. The secondary regressions are plausibly real, but don’t seem big enough to be worth investigating.
47+
48+
#### Improvements
49+
50+
Upgrade `stringdex` to 0.0.3 [#147918](https://github.com/rust-lang/rust/pull/147918) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=5dbf4069dc98bbbca98dd600a65f50c258fbfd56&end=d682af88a57b0045f8348507682c16c6160b522d&stat=instructions:u)
51+
52+
| (instructions:u) | mean | range | count |
53+
|:----------------------------------:|:-----:|:--------------:|:-----:|
54+
| Regressions ❌ <br /> (primary) | - | - | 0 |
55+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
56+
| Improvements ✅ <br /> (primary) | -0.6% | [-2.9%, -0.1%] | 14 |
57+
| Improvements ✅ <br /> (secondary) | -0.7% | [-1.4%, -0.3%] | 3 |
58+
| All ❌✅ (primary) | -0.6% | [-2.9%, -0.1%] | 14 |
59+
60+
61+
rustdoc: microoptimize render_item, move stuff out of common path [#148877](https://github.com/rust-lang/rust/pull/148877) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=f35a2bee641e88742b6de10b25c748ef57475f24&end=e65b983161d52688ff8e05245ed5dc70ef01a904&stat=instructions:u)
62+
63+
| (instructions:u) | mean | range | count |
64+
|:----------------------------------:|:-----:|:--------------:|:-----:|
65+
| Regressions ❌ <br /> (primary) | - | - | 0 |
66+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
67+
| Improvements ✅ <br /> (primary) | -1.5% | [-3.0%, -0.3%] | 3 |
68+
| Improvements ✅ <br /> (secondary) | -1.1% | [-2.9%, -0.1%] | 4 |
69+
| All ❌✅ (primary) | -1.5% | [-3.0%, -0.3%] | 3 |
70+
71+
72+
const-eval: fix and re-enable pointer fragment support [#148259](https://github.com/rust-lang/rust/pull/148259) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=67c4cf395f243afcb973dacdd39b16895c9ad295&end=e1a2ec605124d9f9b0095435faef70bd4bd3f128&stat=instructions:u)
73+
74+
| (instructions:u) | mean | range | count |
75+
|:----------------------------------:|:-----:|:--------------:|:-----:|
76+
| Regressions ❌ <br /> (primary) | - | - | 0 |
77+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
78+
| Improvements ✅ <br /> (primary) | -3.0% | [-3.0%, -3.0%] | 1 |
79+
| Improvements ✅ <br /> (secondary) | -0.3% | [-0.4%, -0.2%] | 8 |
80+
| All ❌✅ (primary) | -3.0% | [-3.0%, -3.0%] | 1 |
81+
82+
83+
Rollup of 4 pull requests [#149059](https://github.com/rust-lang/rust/pull/149059) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=f9e7961506a97b318ad4815b8ce94bb045562f89&end=3d461af2a23456a2676aadb13b4253c87bdfe28d&stat=instructions:u)
84+
85+
| (instructions:u) | mean | range | count |
86+
|:----------------------------------:|:-----:|:--------------:|:-----:|
87+
| Regressions ❌ <br /> (primary) | - | - | 0 |
88+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
89+
| Improvements ✅ <br /> (primary) | -2.9% | [-2.9%, -2.9%] | 1 |
90+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.6%, -0.1%] | 4 |
91+
| All ❌✅ (primary) | -2.9% | [-2.9%, -2.9%] | 1 |
92+
93+
94+
#### Mixed
95+
96+
cleanup: merge `RvalueScopes` into `ScopeTree` [#148658](https://github.com/rust-lang/rust/pull/148658) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=2636cb4c1328f5a3ab05b8d13a666ac5f3a48a08&end=25d319a0f656ee8faa7a534da299e76e96068a40&stat=instructions:u)
97+
98+
| (instructions:u) | mean | range | count |
99+
|:----------------------------------:|:-----:|:--------------:|:-----:|
100+
| Regressions ❌ <br /> (primary) | 3.1% | [3.1%, 3.1%] | 1 |
101+
| Regressions ❌ <br /> (secondary) | 0.5% | [0.0%, 0.6%] | 5 |
102+
| Improvements ✅ <br /> (primary) | -0.1% | [-0.1%, -0.1%] | 1 |
103+
| Improvements ✅ <br /> (secondary) | -0.1% | [-0.1%, -0.0%] | 7 |
104+
| All ❌✅ (primary) | 1.5% | [-0.1%, 3.1%] | 2 |
105+
106+
`clap_derive` regression is noise. Other secondary regressions were identified in pre-merge perf run, investigated by in https://github.com/rust-lang/rust/pull/148658#issuecomment-3506150724 and accepted by reviewer in https://github.com/rust-lang/rust/pull/148658#issuecomment-3517842065
107+
108+
Rollup of 16 pull requests [#148851](https://github.com/rust-lang/rust/pull/148851) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=11339a0ef5ed586bb7ea4f85a9b7287880caac3a&end=0b329f801a09004dacb19aaf09d5cb8b4c51d3f8&stat=instructions:u)
109+
110+
| (instructions:u) | mean | range | count |
111+
|:----------------------------------:|:-----:|:--------------:|:-----:|
112+
| Regressions ❌ <br /> (primary) | 2.1% | [1.1%, 3.5%] | 20 |
113+
| Regressions ❌ <br /> (secondary) | 1.4% | [0.2%, 2.8%] | 25 |
114+
| Improvements ✅ <br /> (primary) | -3.0% | [-3.0%, -3.0%] | 1 |
115+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.5%, -0.2%] | 2 |
116+
| All ❌✅ (primary) | 1.9% | [-3.0%, 3.5%] | 21 |
117+
118+
Regression was identified as https://github.com/rust-lang/rust/pull/146627, which was reverted.
119+
120+
New format_args!() and fmt::Arguments implementation [#148789](https://github.com/rust-lang/rust/pull/148789) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=01867557cd7dbe256a031a7b8e28d05daecd75ab&end=503dce33e2e2a5d2fe978b2723ab2a994cc27472&stat=instructions:u)
121+
122+
| (instructions:u) | mean | range | count |
123+
|:----------------------------------:|:-----:|:---------------:|:-----:|
124+
| Regressions ❌ <br /> (primary) | 0.7% | [0.1%, 5.7%] | 17 |
125+
| Regressions ❌ <br /> (secondary) | 0.6% | [0.1%, 1.1%] | 40 |
126+
| Improvements ✅ <br /> (primary) | -0.7% | [-4.4%, -0.1%] | 120 |
127+
| Improvements ✅ <br /> (secondary) | -1.6% | [-38.5%, -0.0%] | 106 |
128+
| All ❌✅ (primary) | -0.5% | [-4.4%, 5.7%] | 137 |
129+
130+
Improvements outweigh regressions.
131+
132+
Revert "Rollup merge of #146627 - madsmtm:jemalloc-simplify, r=jdonszelmann" [#148896](https://github.com/rust-lang/rust/pull/148896) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=2286e5d224b3413484cf4f398a9f078487e7b49d&end=7a72c5459dd58f81b0e1a0e5436d145485889375&stat=instructions:u)
133+
134+
| (instructions:u) | mean | range | count |
135+
|:----------------------------------:|:-----:|:--------------:|:-----:|
136+
| Regressions ❌ <br /> (primary) | - | - | 0 |
137+
| Regressions ❌ <br /> (secondary) | 0.9% | [0.2%, 1.1%] | 7 |
138+
| Improvements ✅ <br /> (primary) | -2.1% | [-3.4%, -1.1%] | 20 |
139+
| Improvements ✅ <br /> (secondary) | -1.4% | [-2.7%, -0.2%] | 25 |
140+
| All ❌✅ (primary) | -2.1% | [-3.4%, -1.1%] | 20 |
141+
142+
Reverts a previous regression.
143+
144+
compute temporary scopes when building MIR, not THIR [#148706](https://github.com/rust-lang/rust/pull/148706) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=77761f314d7243da0fa3b6ca214eeecd51e956e0&end=733108b6d4acaa93fe26ae281ea305aacd6aac4e&stat=instructions:u)
145+
146+
| (instructions:u) | mean | range | count |
147+
|:----------------------------------:|:-----:|:--------------:|:-----:|
148+
| Regressions ❌ <br /> (primary) | 2.9% | [2.9%, 2.9%] | 1 |
149+
| Regressions ❌ <br /> (secondary) | 1.7% | [1.7%, 1.7%] | 1 |
150+
| Improvements ✅ <br /> (primary) | -0.4% | [-1.8%, -0.1%] | 55 |
151+
| Improvements ✅ <br /> (secondary) | -0.9% | [-3.1%, -0.0%] | 80 |
152+
| All ❌✅ (primary) | -0.3% | [-1.8%, 2.9%] | 56 |
153+
154+
`clap_derive` regression is noise, otherwise this is an improvement.
155+
156+
Update wasm-component-ld to 0.5.19 [#148954](https://github.com/rust-lang/rust/pull/148954) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=733108b6d4acaa93fe26ae281ea305aacd6aac4e&end=f35a2bee641e88742b6de10b25c748ef57475f24&stat=instructions:u)
157+
158+
| (instructions:u) | mean | range | count |
159+
|:----------------------------------:|:-----:|:--------------:|:-----:|
160+
| Regressions ❌ <br /> (primary) | - | - | 0 |
161+
| Regressions ❌ <br /> (secondary) | 0.0% | [0.0%, 0.0%] | 1 |
162+
| Improvements ✅ <br /> (primary) | -2.9% | [-2.9%, -2.9%] | 1 |
163+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
164+
| All ❌✅ (primary) | -2.9% | [-2.9%, -2.9%] | 1 |
165+
166+
`wg-grammar` looks like noise (it returned back in next PR). `clap_derive` improvement is also noise.
167+
168+
use funnel shift as fallback impl for rotating shifts [#148478](https://github.com/rust-lang/rust/pull/148478) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=69d4d5fc0e4db60272aac85ef27ecccef5764f3a&end=89fe96197d232f86d733566df31c6dcebd1750da&stat=instructions:u)
169+
170+
| (instructions:u) | mean | range | count |
171+
|:----------------------------------:|:-----:|:--------------:|:-----:|
172+
| Regressions ❌ <br /> (primary) | 3.8% | [3.8%, 3.8%] | 1 |
173+
| Regressions ❌ <br /> (secondary) | 0.2% | [0.1%, 0.3%] | 10 |
174+
| Improvements ✅ <br /> (primary) | -0.4% | [-0.4%, -0.4%] | 1 |
175+
| Improvements ✅ <br /> (secondary) | -0.1% | [-0.1%, -0.1%] | 1 |
176+
| All ❌✅ (primary) | 1.7% | [-0.4%, 3.8%] | 2 |
177+
178+
Investigated by author. Eza regression seems a bit mysterious. Pre-merge run from two weeks ago didn't indicate it.
179+
180+
Replace OffsetOf by an actual sum of calls to intrinsic. [#148151](https://github.com/rust-lang/rust/pull/148151) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=c1995621a44398ac33ab368adbfb69753218b49e&end=f9e7961506a97b318ad4815b8ce94bb045562f89&stat=instructions:u)
181+
182+
| (instructions:u) | mean | range | count |
183+
|:----------------------------------:|:-----:|:--------------:|:-----:|
184+
| Regressions ❌ <br /> (primary) | 3.1% | [3.1%, 3.1%] | 1 |
185+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.1%, 0.6%] | 6 |
186+
| Improvements ✅ <br /> (primary) | - | - | 0 |
187+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.9%, -0.0%] | 7 |
188+
| All ❌✅ (primary) | 3.1% | [3.1%, 3.1%] | 1 |
189+
190+
`clap_derive` is noise, `include-blob` is also noise (at least the `opt` variants, other ones didn't return to previous state, but they are tiny in absolute numbers).
191+
192+
Inherent const impl [#148434](https://github.com/rust-lang/rust/pull/148434) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=7c2c3c0ded2de378bfab2f5b55c387c66fbaf353&end=6159a44067ebce42b38f062cc7df267a1348e092&stat=instructions:u)
193+
194+
| (instructions:u) | mean | range | count |
195+
|:----------------------------------:|:-----:|:--------------:|:-----:|
196+
| Regressions ❌ <br /> (primary) | 2.9% | [2.9%, 2.9%] | 1 |
197+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
198+
| Improvements ✅ <br /> (primary) | -0.3% | [-0.3%, -0.3%] | 1 |
199+
| Improvements ✅ <br /> (secondary) | -0.5% | [-0.9%, -0.2%] | 9 |
200+
| All ❌✅ (primary) | 1.3% | [-0.3%, 2.9%] | 2 |
201+
202+
`clap_derive` noise.
203+
204+
Update wasm-related dependencies in CI [#149037](https://github.com/rust-lang/rust/pull/149037) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=6159a44067ebce42b38f062cc7df267a1348e092&end=a591113c0a2b7755514c47bde211fdb92d1d7002&stat=instructions:u)
205+
206+
| (instructions:u) | mean | range | count |
207+
|:----------------------------------:|:-----:|:--------------:|:-----:|
208+
| Regressions ❌ <br /> (primary) | 0.4% | [0.4%, 0.4%] | 1 |
209+
| Regressions ❌ <br /> (secondary) | 0.5% | [0.2%, 0.9%] | 9 |
210+
| Improvements ✅ <br /> (primary) | -2.8% | [-2.8%, -2.8%] | 1 |
211+
| Improvements ✅ <br /> (secondary) | -0.1% | [-0.1%, -0.1%] | 1 |
212+
| All ❌✅ (primary) | -1.2% | [-2.8%, 0.4%] | 2 |
213+
214+
215+
Triaged by @lqd: Gotta be noise. A bunch of the changes are benchmarks returning to their previous state, fixing a spurious win.

0 commit comments

Comments
 (0)