Skip to content

Commit 6b72e95

Browse files
Mark-SimulacrumMark-Simulacrum
committed
Add triage for this week
1 parent 8dfb8bf commit 6b72e95

File tree

1 file changed

+118
-0
lines changed

1 file changed

+118
-0
lines changed

‎triage/2022-11-08.md

Lines changed: 118 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
1+
# 2022-11-08 Triage Log
2+
3+
A relatively noisy week (most of those have been dropped below, and comments
4+
left on GitHub), but otherwise a quiet one in terms of performance changes,
5+
with essentially no significant changes occuring.
6+
7+
Triage done by **@simulacrum**.
8+
Revision range: [822f8c22f540b12f296d844ad5bf39aaa47bfeb4..57d3c58ed6e0faf89a62411f96c000ffc9fd3937](https://perf.rust-lang.org/?start=822f8c22f540b12f296d844ad5bf39aaa47bfeb4&end=57d3c58ed6e0faf89a62411f96c000ffc9fd3937&absolute=false&stat=instructions%3Au)
9+
10+
**Summary**:
11+
12+
| (instructions:u) | mean | range | count |
13+
|:----------------------------------:|:-----:|:--------------:|:-----:|
14+
| Regressions ❌ <br /> (primary) | 1.2% | [0.2%, 1.8%] | 13 |
15+
| Regressions ❌ <br /> (secondary) | 1.2% | [0.2%, 2.1%] | 47 |
16+
| Improvements ✅ <br /> (primary) | -1.5% | [-4.0%, -0.2%] | 21 |
17+
| Improvements ✅ <br /> (secondary) | -1.8% | [-3.9%, -0.3%] | 61 |
18+
| All ❌✅ (primary) | -0.4% | [-4.0%, 1.8%] | 34 |
19+
20+
21+
2 Regressions, 2 Improvements, 3 Mixed; 3 of them in rollups
22+
39 artifact comparisons made in total
23+
24+
#### Regressions
25+
26+
Rollup of 6 pull requests [#103998](https://github.com/rust-lang/rust/pull/103998) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=5b3e9090757da9a95b22f589fe39b6a4b5455b96&end=452cf4f7109f58433ac38be7d3da527408571054&stat=instructions:u)
27+
28+
| (instructions:u) | mean | range | count |
29+
|:----------------------------------:|:-----:|:--------------:|:-----:|
30+
| Regressions ❌ <br /> (primary) | 2.5% | [0.3%, 3.9%] | 6 |
31+
| Regressions ❌ <br /> (secondary) | 1.4% | [0.4%, 3.5%] | 43 |
32+
| Improvements ✅ <br /> (primary) | - | - | 0 |
33+
| Improvements ✅ <br /> (secondary) | -1.3% | [-1.5%, -1.0%] | 2 |
34+
| All ❌✅ (primary) | 2.5% | [0.3%, 3.9%] | 6 |
35+
36+
Appears to be a genuine regression. Mostly limited to smaller benchmarks, so
37+
most likely just a slight increase in the minimum work rustc does. Suspected to
38+
be due to the changes in sysroot detection; have enqueued a build to try and
39+
find out.
40+
41+
std: sync "Dependencies of the `backtrace` crate" with `backtrace` [#103934](https://github.com/rust-lang/rust/pull/103934) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=d69c33ad4c65e42a7a2d018a5c2ee1c7dbd0fc15&end=73c9eaf21454b718e7c549984d9eb6e1f75e995c&stat=instructions:u)
42+
43+
| (instructions:u) | mean | range | count |
44+
|:----------------------------------:|:----:|:------------:|:-----:|
45+
| Regressions ❌ <br /> (primary) | 1.4% | [0.9%, 1.8%] | 10 |
46+
| Regressions ❌ <br /> (secondary) | 1.5% | [0.3%, 3.3%] | 47 |
47+
| Improvements ✅ <br /> (primary) | - | - | 0 |
48+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
49+
| All ❌✅ (primary) | 1.4% | [0.9%, 1.8%] | 10 |
50+
51+
Some of this may be noise, but it's also possible that the newer dependencies
52+
are doing slightly different things causing some regressions -- it's possible
53+
we're computing backtraces somewhere, and even modulo that, the changes to the
54+
standard library may cause different inlining decisions, etc.
55+
56+
#### Improvements
57+
58+
Make rustdoc Item::visibility computed on-demand [#103690](https://github.com/rust-lang/rust/pull/103690) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=822f8c22f540b12f296d844ad5bf39aaa47bfeb4&end=c0a76127283bc963b085f54a1b275a8e281e81e6&stat=instructions:u)
59+
60+
| (instructions:u) | mean | range | count |
61+
|:----------------------------------:|:-----:|:--------------:|:-----:|
62+
| Regressions ❌ <br /> (primary) | - | - | 0 |
63+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
64+
| Improvements ✅ <br /> (primary) | -0.8% | [-1.7%, -0.4%] | 11 |
65+
| Improvements ✅ <br /> (secondary) | -1.6% | [-2.7%, -0.6%] | 23 |
66+
| All ❌✅ (primary) | -0.8% | [-1.7%, -0.4%] | 11 |
67+
68+
69+
Rollup of 7 pull requests [#103962](https://github.com/rust-lang/rust/pull/103962) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=47c008e440e59d793c2883f7dd712481dc965045&end=6330c27ae24ec1556cf2b97eeac333dc23391686&stat=instructions:u)
70+
71+
| (instructions:u) | mean | range | count |
72+
|:----------------------------------:|:-----:|:--------------:|:-----:|
73+
| Regressions ❌ <br /> (primary) | - | - | 0 |
74+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
75+
| Improvements ✅ <br /> (primary) | -0.2% | [-0.3%, -0.2%] | 6 |
76+
| Improvements ✅ <br /> (secondary) | -0.4% | [-0.4%, -0.3%] | 4 |
77+
| All ❌✅ (primary) | -0.2% | [-0.3%, -0.2%] | 6 |
78+
79+
80+
#### Mixed
81+
82+
Revert "ci: Bring back ninja for dist builders" [#103846](https://github.com/rust-lang/rust/pull/103846) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=edf0182213a9e30982eb34f3925ddc4cf5ed3471&end=5b1304a03bbefe618cf16d6f4b3c41f4bd8e390a&stat=instructions:u)
83+
84+
| (instructions:u) | mean | range | count |
85+
|:----------------------------------:|:-----:|:--------------:|:-----:|
86+
| Regressions ❌ <br /> (primary) | - | - | 0 |
87+
| Regressions ❌ <br /> (secondary) | 2.5% | [2.5%, 2.5%] | 1 |
88+
| Improvements ✅ <br /> (primary) | -1.7% | [-7.4%, -0.2%] | 19 |
89+
| Improvements ✅ <br /> (secondary) | -2.0% | [-6.6%, -0.2%] | 71 |
90+
| All ❌✅ (primary) | -1.7% | [-7.4%, -0.2%] | 19 |
91+
92+
This change was reverted precisely due to the performance regression it introduced, so this is no surprise.
93+
94+
Rollup of 5 pull requests [#104017](https://github.com/rust-lang/rust/pull/104017) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=6b8d9dd0a09851b3e4f400ddd1303857945be25d&end=371100b1fb811e604f7451eff3b06960587fe1af&stat=instructions:u)
95+
96+
| (instructions:u) | mean | range | count |
97+
|:----------------------------------:|:-----:|:--------------:|:-----:|
98+
| Regressions ❌ <br /> (primary) | 1.4% | [1.4%, 1.4%] | 1 |
99+
| Regressions ❌ <br /> (secondary) | 0.5% | [0.3%, 0.8%] | 2 |
100+
| Improvements ✅ <br /> (primary) | -1.0% | [-3.2%, -0.3%] | 13 |
101+
| Improvements ✅ <br /> (secondary) | -2.3% | [-3.1%, -0.6%] | 19 |
102+
| All ❌✅ (primary) | -0.9% | [-3.2%, 1.4%] | 14 |
103+
104+
Minor regressions in two secondary benchmarks and in libc don't seem to warrant
105+
further investigation, especially given the general improvement across the
106+
board.
107+
108+
Some tracing and comment cleanups [#103975](https://github.com/rust-lang/rust/pull/103975) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=e6fead46dc21ba017f7c1a5130ff3d31535acb16&end=a4ab2e064306c2c3e5b1d2efe1d5c0e1a6e0346a&stat=instructions:u)
109+
110+
| (instructions:u) | mean | range | count |
111+
|:----------------------------------:|:-----:|:--------------:|:-----:|
112+
| Regressions ❌ <br /> (primary) | 1.0% | [0.2%, 1.5%] | 3 |
113+
| Regressions ❌ <br /> (secondary) | 1.9% | [0.3%, 4.2%] | 13 |
114+
| Improvements ✅ <br /> (primary) | - | - | 0 |
115+
| Improvements ✅ <br /> (secondary) | -0.6% | [-0.6%, -0.6%] | 3 |
116+
| All ❌✅ (primary) | 1.0% | [0.2%, 1.5%] | 3 |
117+
118+
Most of the regressions are probably noise, so this change is likely actually an improvement or neutral.

0 commit comments

Comments
 (0)