Update rustc-perf submodule

[Kobzol]

Mostly to include rust-lang/rustc-perf#2204.

[rustbot]

r? @Mark-Simulacrum

rustbot has assigned @Mark-Simulacrum.
They will have a look at your PR within the next two weeks and either review your PR or reassign to another reviewer.

Use r? to explicitly pick a reviewer

[Kobzol]

@bors try @rust-timer queue

[rustbot]

⚠️ Warning ⚠️

• Some commits in this PR modify submodules.

[rust-bors]

⌛ Trying commit 0b807fc with merge 0891bf8…

To cancel the try build, run the command @bors try cancel.

[lqd]

r? lqd r=me with green/neutral perf :3

[rustbot]

There are changes to the tidy tool.

cc @jieyouxu

The list of allowed third-party dependencies may have been modified! You must ensure that any new dependencies have compatible licenses before merging.

cc @davidtwco, @wesleywiser

[rust-bors]

☀️ Try build successful (CI)
Build commit: 0891bf8 (0891bf8d28a77573eaa3ab46ecc65bdb8b00dbc8, parent: 7278554d82fa474a4e8b5c67afb009e11e41a841)

[rust-timer]

Finished benchmarking commit (0891bf8): comparison URL.

Overall result: no relevant changes - no action needed

Benchmarking this pull request means it may be perf-sensitive – we'll automatically label it not fit for rolling up. You can override this, but we strongly advise not to, due to possible changes in compiler perf.

@bors rollup=never
@rustbot label: -S-waiting-on-perf -perf-regression

Instruction count

This benchmark run did not return any relevant results for this metric.

Max RSS (memory usage)

This benchmark run did not return any relevant results for this metric.

Cycles

Results (primary 3.8%, secondary 19.5%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	3.8%	[3.8%, 3.8%]	1
Regressions ❌ (secondary)	19.5%	[18.2%, 20.7%]	6
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	3.8%	[3.8%, 3.8%]	1

Binary size

This benchmark run did not return any relevant results for this metric.

Bootstrap: 467.638s -> 468.356s (0.15%)
Artifact size: 376.88 MiB -> 376.85 MiB (-0.01%)

[lqd]

@Kobzol how stable are cycles and wall times on the new server? This no op change has weird metrics there :/

[Kobzol]

https://perf.rust-lang.org/index.html?kind=raw&stat=cycles%3Au cycles are relatively stable (compare e.g. with wall-time, which is much more noisy). I don't know what caused this blip, but I haven't seen anything like it recently. Looking at the ctfe-stress results it looks like that benchmark is particularly noisy on cycles though, not sure why.

[lqd]

Strange yes. Thanks!

@bors r+ rollup

[bors]

📌 Commit b60026a has been approved by lqd

It is now in the queue for this repository.