[DO NOT MERGE] Perf experiment with different cargo defaults

[lqd]

I'm not sure this is even going to build on CI, or whether the results I see locally are going to show up on perf.rlo: the collector mostly benchmarks leaf crates and this changes how the dependencies are built, not the leaf crate.

Maybe it'll have an effect on bootstrap.

In any case it'll at least show whether this is the correct way to benchmark with a different cargo.

r? @ghost

[lqd]

@bors try @rust-timer queue

[rust-timer]

Awaiting bors try build completion.

@rustbot label: +S-waiting-on-perf

[bors]

⌛ Trying commit 0a122f4 with merge 69f654c9aa82e79f56e16f66b3c8a17019ac7289...

[bors]

☀️ Try build successful - checks-actions
Build commit: 69f654c9aa82e79f56e16f66b3c8a17019ac7289 (69f654c9aa82e79f56e16f66b3c8a17019ac7289)

[rust-timer]

Queued 69f654c9aa82e79f56e16f66b3c8a17019ac7289 with parent f58d51b, future comparison URL.

[rust-timer]

Finished benchmarking commit (69f654c9aa82e79f56e16f66b3c8a17019ac7289): comparison url.

Summary: This benchmark run shows 31 relevant improvements 🎉 to instruction counts.

• Arithmetic mean of relevant regressions: 0.4%
• Arithmetic mean of relevant improvements: -1.5%
• Arithmetic mean of all relevant changes: -1.4%
• Largest improvement in instruction counts: -6.6% on incr-unchanged builds of cargo check

If you disagree with this performance assessment, please file an issue in rust-lang/rustc-perf.

Benchmarking this pull request likely means that it is perf-sensitive, so we're automatically marking it as not fit for rolling up. While you can manually mark this PR as fit for rollup, we strongly recommend not doing so since this PR led to changes in compiler perf.

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