Rollup of 3 perf-sensitive pull requests by JonathanBrouwer · Pull Request #162183 · rust-lang/rust

JonathanBrouwer · 2026-09-02T10:46:17Z

Successful merges:

Store LiveLoans more densely packed #161850 (Store LiveLoans more densely packed)
Reduce next-solver memory usage by interning CanonicalQueryInput #162031 (Reduce next-solver memory usage by interning CanonicalQueryInput)
Optimize empty token streams #162047 (Optimize empty token streams)

Empty token streams are common. Every one causes an allocation for the `Arc::new()`. We can instead have a single shared empty `TokenStream` and `AttrTokenStream`.

…nterned

…jackh726 Store LiveLoans more densely packed `LiveLoans` originally used `SparseBitMatrix<PointIndex, BorrowIndex>` in a way that didn't use "the sparseness" very effectively. The borrow dimension is usually very low (<10 bits 90% of the time), while the point dimension is typically order of magnitude higher. This means that we used to allocate a bunch of 32-byte `DenseBitSet`s that only point to a few bits in heap-allocated `u64`. We only saved some memory by not allocating the whole `PointIndex` range, but we still often need to allocatate most of it. This PR changes the representation to use a single flat representation with `GrowableBitSet` storing all bits in a single Vec. There's still a room for improvement but this should be a positive step forward. r? lqd

@lcnr

…lcnr Reduce next-solver memory usage by interning CanonicalQueryInput Goal: Reduce memory usage of next-solver especially when exceeding recursion limit Changes: - Added Interner::CanonicalInput associated type and surrounding interning machinery (mostly copied from ExternalConstraints) - Changed Cx::Input to be I:CanonicalInput and adjusted other places in the code to match, including calling the interning during canonicalize_goal Results: According to Heaptrack (and btop) peak memory usage for compiling `bevy_render` (like rust-lang#161748) with next-solver enabled was reduced from ~15GiB to ~4GiB since most of it was the HashMap index for NestedGoals (and search_graph::GlobalCache), which used to be 56 bytes (IIRC), but now is a single reference thanks to Interned. Closes (maybe): rust-lang#161748 Tracking issue: rust-lang/goals#113 and rust-lang#160895 (comment) r? @lcnr

@Kobzol

…Kobzol Optimize empty token streams Empty token streams are common. Every one causes an allocation for the `Arc::new()`. We can instead have a single shared empty `TokenStream` and `AttrTokenStream`. r? @Kobzol

JonathanBrouwer · 2026-09-02T10:46:25Z

@bors r+ p=5

Trying commonly failed jobs
@bors try jobs=dist-various-1,test-various,x86_64-gnu-aux,x86_64-gnu-llvm-21-3,x86_64-msvc-1,aarch64-apple-1,aarch64-apple-2,x86_64-mingw-1,i686-msvc-1,i686-msvc-2

rust-bors · 2026-09-02T10:46:28Z

📌 Commit d5b8ff4 has been approved by JonathanBrouwer

It is now in the queue for this repository.

Rollup of 3 pull requests try-job: dist-various-1 try-job: test-various try-job: x86_64-gnu-aux try-job: x86_64-gnu-llvm-21-3 try-job: x86_64-msvc-1 try-job: aarch64-apple-1 try-job: aarch64-apple-2 try-job: x86_64-mingw-1 try-job: i686-msvc-1 try-job: i686-msvc-2

rust-bors · 2026-09-02T13:47:53Z

☀️ Try build successful (CI)
Build commit: 24bb055 (24bb0551fd052ad99a8eebb500e8edc05d453613)
Base parent: 3a43cb6 (3a43cb66f97d08ccde87a00599fac2d3c50eb177)

rust-bors · 2026-09-02T16:58:06Z

☀️ Test successful - CI
Approved by: JonathanBrouwer
Duration: 3h 7m 5s
Pushing 824336a to main...

github-actions · 2026-09-02T17:01:41Z

What is this?

This is an experimental post-merge analysis report that shows differences in test outcomes between the merged PR and its parent PR.

Comparing 59dabe5 (parent) -> 824336a (this PR)

Test differences

No test diffs found

Test dashboard

Run

cargo run --manifest-path src/ci/citool/Cargo.toml -- \
    test-dashboard 824336ad4127ce295849937a24c08a4aeff6ada7 --output-dir test-dashboard

And then open test-dashboard/index.html in your browser to see an overview of all executed tests.

Job duration changes

x86_64-gnu-stdlib-semver-check: 11m 19s -> 17m 54s (+58.2%)
x86_64-gnu-llvm-21-2: 1h 9m -> 1h 43m (+49.3%)
x86_64-gnu: 1h 43m -> 2h 31m (+46.7%)
dist-ohos-armv7: 54m 55s -> 1h 18m (+43.5%)
x86_64-gnu-tools: 49m 43s -> 1h 9m (+40.2%)
x86_64-gnu-gcc: 57m 28s -> 1h 19m (+38.1%)
dist-arm-linux-musl: 1h 19m -> 1h 47m (+35.9%)
x86_64-gnu-distcheck: 1h 43m -> 2h 18m (+34.3%)
dist-s390x-linux: 1h 31m -> 1h 4m (-29.9%)
dist-x86_64-netbsd: 1h 29m -> 1h 3m (-29.0%)

How to interpret the job duration changes?

Job durations can vary a lot, based on the actual runner instance
that executed the job, system noise, invalidated caches, etc. The table above is provided
mostly for t-infra members, for simpler debugging of potential CI slow-downs.

rust-bors · 2026-09-02T18:00:02Z

📌 Perf builds for each rolled up PR:

PR#	Message	Perf Build Sha
#161850	Store LiveLoans more densely packed	`a9c8aa3e069626765fa9492fcd7d2030ee024a6a` (link)
#162031	Reduce next-solver memory usage by interning CanonicalQuery…	`cd59165899980b4f1ed4ef005ad26b81afb52271` (link)
#162047	Optimize empty token streams	`2d373c084c0ad231045112828dff4e7deb769cfe` (link)

parent commit: 59dabe56f7

In the case of a perf regression, run the following command for each PR you suspect might be the cause: @rust-timer build $SHA

rust-timer · 2026-09-02T18:17:42Z

Finished benchmarking commit (824336a): comparison URL.

Overall result: ❌✅ regressions and improvements - please read:

Our benchmarks found a performance regression caused by this PR.
This might be an actual regression, but it can also be just noise.

Next Steps:

If the regression was expected or you think it can be justified,
please write a comment with sufficient written justification, and add
@rustbot label: +perf-regression-triaged to it, to mark the regression as triaged.
If you think that you know of a way to resolve the regression, try to create
a new PR with a fix for the regression.
If you do not understand the regression or you think that it is just noise,
you can ask the @rust-lang/wg-compiler-performance working group for help (members of this group
were already notified of this PR).

@rustbot label: +perf-regression
cc @rust-lang/wg-compiler-performance

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
Regressions ❌ (secondary)	0.1%	[0.1%, 0.2%]	9
Improvements ✅ (primary)	-0.3%	[-1.3%, -0.1%]	49
Improvements ✅ (secondary)	-0.3%	[-0.7%, -0.1%]	39
All ❌✅ (primary)	-0.3%	[-1.3%, -0.1%]	49

Max RSS (memory usage)

Results (primary -1.9%, secondary -0.4%)

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)	4.4%	[1.8%, 11.2%]	8
Improvements ✅ (primary)	-1.9%	[-4.1%, -0.5%]	8
Improvements ✅ (secondary)	-2.5%	[-6.3%, -0.7%]	18
All ❌✅ (primary)	-1.9%	[-4.1%, -0.5%]	8

Cycles

Results (primary -2.5%, secondary -0.3%)

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)	8.5%	[4.3%, 12.2%]	4
Improvements ✅ (primary)	-2.5%	[-2.7%, -2.0%]	3
Improvements ✅ (secondary)	-5.4%	[-8.5%, -2.7%]	7
All ❌✅ (primary)	-2.5%	[-2.7%, -2.0%]	3

Binary size

This perf run didn't have relevant results for this metric.

Bootstrap: 473.905s -> 473.106s (-0.17%)
Artifact size: 400.83 MiB -> 401.09 MiB (0.06%)

JonathanBrouwer · 2026-09-02T19:08:46Z

@rust-timer triage a9c8aa3 cd59165 2d373c0

rust-timer · 2026-09-02T19:08:51Z

Running triage with 26 benchmarks

Triage only executes the benchmarks on rollup members, that were changed significantly on the rollup.
For this rollup, these benchmarks are:

cargo-0.87.1
clap_derive-4.5.32
clap_derive-4.5.32-nll
cranelift-codegen-0.119.0
derive
externs
html5ever-0.31.0
hyper-1.6.0
image-0.25.6
include-blob
libc-0.2.172
many-assoc-items
match-stress
nalgebra-0.33.0
nalgebra-0.33.0-new-solver
regex-automata-0.4.8
ripgrep-14.1.1
ripgrep-14.1.1-nll
serde-1.0.219
serde-1.0.219-nll
serde_derive-1.0.219
stm32f4-0.15.1
syn-2.0.101
tt-muncher
typenum-1.18.0-new-solver
unused-warnings

#161850 `a9c8aa3` Store LiveLoans more densely packed

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
Regressions ❌ (secondary)	-	-	0
Improvements ✅ (primary)	-0.4%	[-1.2%, -0.1%]	22
Improvements ✅ (secondary)	-0.2%	[-0.4%, -0.0%]	7
All ❌✅ (primary)	-0.4%	[-1.2%, -0.1%]	22

Max RSS (memory usage)

Results (primary -1.7%, secondary 0.5%)

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

	mean	range	count
Regressions ❌ (primary)	2.6%	[2.6%, 2.6%]	1
Regressions ❌ (secondary)	4.0%	[3.3%, 4.7%]	3
Improvements ✅ (primary)	-3.1%	[-4.1%, -2.5%]	3
Improvements ✅ (secondary)	-3.0%	[-3.1%, -2.8%]	3
All ❌✅ (primary)	-1.7%	[-4.1%, 2.6%]	4

Cycles

Results (primary 2.3%, secondary 5.0%)

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

	mean	range	count
Regressions ❌ (primary)	2.3%	[2.3%, 2.3%]	1
Regressions ❌ (secondary)	5.0%	[2.9%, 7.6%]	7
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	2.3%	[2.3%, 2.3%]	1

Binary size

This perf run didn't have relevant results for this metric.

#162031 `cd59165` Reduce next-solver memory usage by interning CanonicalQueryInput

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
Regressions ❌ (secondary)	0.2%	[0.1%, 0.3%]	5
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-0.3%	[-0.5%, -0.0%]	6
All ❌✅ (primary)	-	-	0

Max RSS (memory usage)

Results (secondary -1.6%)

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)	-	-	0
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-1.6%	[-2.3%, -0.8%]	6
All ❌✅ (primary)	-	-	0

Cycles

Results (secondary -1.2%)

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)	10.4%	[9.1%, 12.7%]	3
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-5.5%	[-8.8%, -2.2%]	8
All ❌✅ (primary)	-	-	0

Binary size

This perf run didn't have relevant results for this metric.

#162047 `2d373c0` Optimize empty token streams

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
Regressions ❌ (secondary)	0.2%	[0.1%, 0.4%]	14
Improvements ✅ (primary)	-0.2%	[-0.4%, -0.1%]	18
Improvements ✅ (secondary)	-0.3%	[-0.7%, -0.1%]	29
All ❌✅ (primary)	-0.2%	[-0.4%, -0.1%]	18

Max RSS (memory usage)

Results (primary 1.1%, secondary -3.9%)

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

	mean	range	count
Regressions ❌ (primary)	2.7%	[2.7%, 2.7%]	1
Regressions ❌ (secondary)	-	-	0
Improvements ✅ (primary)	-0.4%	[-0.4%, -0.4%]	1
Improvements ✅ (secondary)	-3.9%	[-6.2%, -1.2%]	5
All ❌✅ (primary)	1.1%	[-0.4%, 2.7%]	2

Cycles

Results (primary -3.6%)

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)	-	-	0
Improvements ✅ (primary)	-3.6%	[-3.6%, -3.6%]	1
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	-3.6%	[-3.6%, -3.6%]	1

Binary size

This perf run didn't have relevant results for this metric.

laundmo and others added 8 commits August 30, 2026 15:46

use Interner for CanonicalInput

38795b1

run ./x fmt

b9978df

Optimize empty token streams

5f96a1c

Empty token streams are common. Every one causes an allocation for the `Arc::new()`. We can instead have a single shared empty `TokenStream` and `AttrTokenStream`.

clean up CanonicalInputRaw, CanonicalInputData, and comment why its I…

4189938

…nterned

Store LiveLoans more densely packed

e515460

Rollup merge of rust-lang#162047 - nnethercote:empty-token-stream, r=…

d5b8ff4

…Kobzol Optimize empty token streams Empty token streams are common. Every one causes an allocation for the `Arc::new()`. We can instead have a single shared empty `TokenStream` and `AttrTokenStream`. r? @Kobzol

rust-bors Bot added the rollup A PR which is a rollup label Sep 2, 2026

rustbot added S-waiting-on-review Status: Awaiting review from the assignee but also interested parties. T-compiler Relevant to the compiler team, which will review and decide on the PR/issue. WG-trait-system-refactor The Rustc Trait System Refactor Initiative (-Znext-solver) labels Sep 2, 2026

rust-bors Bot added S-waiting-on-bors Status: Waiting on bors to run and complete tests. Bors will change the label on completion. and removed S-waiting-on-review Status: Awaiting review from the assignee but also interested parties. labels Sep 2, 2026

JonathanBrouwer changed the title ~~Rollup of 3 pull requests~~ Rollup of 3 perf-sensitive pull requests Sep 2, 2026

This comment has been minimized.

Sign in to view

rust-bors Bot added merged-by-bors This PR was explicitly merged by bors. and removed S-waiting-on-bors Status: Waiting on bors to run and complete tests. Bors will change the label on completion. labels Sep 2, 2026

rust-bors Bot merged commit 824336a into rust-lang:main Sep 2, 2026
15 checks passed

rustbot added this to the 1.100.0 milestone Sep 2, 2026

rust-bors Bot mentioned this pull request Sep 2, 2026

[perf] Use a flat token stream representation when lexing #159378

Draft

rustbot added the perf-regression Performance regression. label Sep 2, 2026

Navigation Menu

Uh oh!

Uh oh!

Rollup of 3 perf-sensitive pull requests - #162183

Rollup of 3 perf-sensitive pull requests#162183
rust-bors[bot] merged 8 commits into
rust-lang:mainfrom
JonathanBrouwer:rollup-IgUDpJR

JonathanBrouwer commented Sep 2, 2026

Uh oh!

JonathanBrouwer commented Sep 2, 2026

Uh oh!

rust-bors Bot commented Sep 2, 2026

Uh oh!

This comment has been minimized.

rust-bors Bot commented Sep 2, 2026

Uh oh!

This comment has been minimized.

rust-bors Bot commented Sep 2, 2026

Uh oh!

Uh oh!

github-actions Bot commented Sep 2, 2026

Uh oh!

rust-bors Bot commented Sep 2, 2026

Uh oh!

rust-timer commented Sep 2, 2026

Uh oh!

JonathanBrouwer commented Sep 2, 2026

Uh oh!

rust-timer commented Sep 2, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

Uh oh!

Uh oh!

Conversation

JonathanBrouwer commented Sep 2, 2026

Uh oh!

JonathanBrouwer commented Sep 2, 2026

Uh oh!

rust-bors Bot commented Sep 2, 2026

Uh oh!

This comment has been minimized.

rust-bors Bot commented Sep 2, 2026

Uh oh!

This comment has been minimized.

rust-bors Bot commented Sep 2, 2026

Uh oh!

Uh oh!

github-actions Bot commented Sep 2, 2026

Test differences

Job duration changes

Uh oh!

rust-bors Bot commented Sep 2, 2026

Uh oh!

rust-timer commented Sep 2, 2026

Overall result: ❌✅ regressions and improvements - please read:

Uh oh!

JonathanBrouwer commented Sep 2, 2026

Uh oh!

rust-timer commented Sep 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

#161850 a9c8aa3 Store LiveLoans more densely packed

#162031 cd59165 Reduce next-solver memory usage by interning CanonicalQueryInput

#162047 2d373c0 Optimize empty token streams

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

rust-timer commented Sep 2, 2026 •

edited

Loading

#161850 `a9c8aa3` Store LiveLoans more densely packed

#162031 `cd59165` Reduce next-solver memory usage by interning CanonicalQueryInput

#162047 `2d373c0` Optimize empty token streams