Optimize dependency file search

[Kobzol]

I tried to look into the slowdown reported in rust-lang/cargo#16665.

I created a Rust hello world program, and used this Python script to create a directory containing 200k files:

from pathlib import Path

dir = Path("deps")
dir.mkdir(parents=True, exist_ok=True)
for i in range(200000):
    path = dir / f"file{i:07}.o"
    with open(path, "w") as f:
        f.write("\n")

Then I tried to do various small microoptimalizations and simplifications to the code that iterates the search directories. Each individual commit improved performance, with the third one having the biggest effect.

Here are the results on main vs the last commit with the stage1 compiler on Linux, using hyperfine "rustc +stage1 src/main.rs -L deps" -r 30 (there's IO involved, so it's good to let it run for a while):

Benchmark 1: rustc +stage1 src/main.rs -L deps
  Time (mean ± σ):     299.4 ms ±   2.7 ms    [User: 161.9 ms, System: 144.9 ms]
  Range (min … max):   294.8 ms … 307.1 ms    30 runs

Benchmark 1: rustc +stage1 src/main.rs -L deps
  Time (mean ± σ):     208.1 ms ±   4.5 ms    [User: 87.3 ms, System: 128.7 ms]
  Range (min … max):   202.4 ms … 219.6 ms    30 runs

Would be cool if someone could try this on macOS (maybe @ehuss - not sure if you have macOS or you only commented about its behavior on the Cargo issue :) ).

I also tried to prefilter the paths (not in this PR); right now we load everything and then we filter files with given prefixes, that's wasteful. Filtering just files starting with lib would get us down to ~150ms here. (The baseline without -L is ~80ms on my PC). The rest of the 70ms is essentially allocations from iterating the directory entries and sorting. That would be very hard to change - iterating the directory entries (de)allocates a lot of intermediate paths :( We'd have to implement the iteration by hand with either arena allocation, or at least some better management of memory.

r? @nnethercote

[Kobzol]

Not expecting any big wins there, but let's check:

@bors try @rust-timer queue

[rust-bors]

☀️ Try build successful (CI)
Build commit: 71d4456 (71d445654a32204fbf86bfec11e657fb97adcd22, parent: 69b78537fac74de40f009b076bcbbf54b77683ad)

[ehuss]

Unfortunately I am unable to test because of #153077, I am unable to get rustc to build.

[rust-timer]

Finished benchmarking commit (71d4456): comparison URL.

Overall result: ❌✅ regressions and improvements - please read the text below

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.

Next Steps: If you can justify the regressions found in this try perf run, please do so in sufficient writing along with @rustbot label: +perf-regression-triaged. If not, please fix the regressions and do another perf run. If its results are neutral or positive, the label will be automatically removed.

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

Instruction count

Our most reliable metric. Used to determine the overall result above. However, even this metric can be noisy.

	mean	range	count
Regressions ❌ (primary)	0.3%	[0.2%, 0.3%]	4
Regressions ❌ (secondary)	0.0%	[0.0%, 0.0%]	1
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-0.4%	[-0.6%, -0.1%]	7
All ❌✅ (primary)	0.3%	[0.2%, 0.3%]	4

Max RSS (memory usage)

Results (secondary 0.1%)

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

	mean	range	count
Regressions ❌ (primary)	-	-	0
Regressions ❌ (secondary)	6.8%	[6.8%, 6.8%]	1
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-6.7%	[-6.7%, -6.7%]	1
All ❌✅ (primary)	-	-	0

Cycles

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

Binary size

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

Bootstrap: 480.132s -> 480.258s (0.03%)
Artifact size: 395.80 MiB -> 395.77 MiB (-0.01%)

[ehuss]

OK, got some data:

With this PR:

Benchmark 1: ~/Proj/rust/rust/build/aarch64-apple-darwin/stage1/bin/rustc src/main.rs -L deps
  Time (mean ± σ):     197.4 ms ±   3.9 ms    [User: 143.7 ms, System: 117.9 ms]
  Range (min … max):   192.4 ms … 207.7 ms    30 runs

Without:

Benchmark 1: ~/Proj/rust/rust/build/aarch64-apple-darwin/stage1/bin/rustc src/main.rs -L deps
  Time (mean ± σ):     248.9 ms ±   5.1 ms    [User: 189.5 ms, System: 124.2 ms]
  Range (min … max):   241.1 ms … 262.6 ms    30 runs

The tests are super noisy, though (I get significantly different results between runs). But it seems like a pretty good win.