Use thread local dep graph encoding #139758

Zoxc · 2025-04-13T18:40:33Z

This adds thread local encoding of dep graph nodes. Each thread has a MemEncoder that gets flushed to the global FileEncoder when it exceeds 64 kB. Each thread also has a local cache of dep indices. This means there can now be empty gaps in SerializedDepGraph.

Indices are marked green and also allocated by the new atomic operation DepNodeColorMap::try_mark_green as the encoder lock is removed.

rustbot · 2025-04-13T18:40:38Z

r? @lcnr

rustbot has assigned @lcnr.
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

Zoxc · 2025-04-13T19:49:15Z

@bors try @rust-timer queue

bors · 2025-04-13T19:50:26Z

⌛ Trying commit 8167fdb with merge 5545f9c...

Use thread local dep graph encoding This adds thread local encoding of dep graph nodes. Each thread has a `MemEncoder` that gets flushed to the global `FileEncoder` when it exceeds 64 kB. Each thread also has a local cache of dep indices. This means there can now be empty gaps in `SerializedDepGraph`. Indices are marked green and also allocated by the new atomic operation `DepNodeColorMap::try_mark_green` as the encoder lock is removed. This is based on rust-lang#139636 and rust-lang#139756.

Zoxc · 2025-04-13T19:51:47Z

Local results, 1 thread, including #139756, excluding #139636:

Benchmark	Before	After		Before	After		Before	After
Benchmark	Time	Time	%	Physical Memory	Physical Memory	%	Committed Memory	Committed Memory	%
🟣 clap:check:unchanged	0.3046s	0.3076s	0.98%	96.94 MiB	98.15 MiB	💔 1.24%	168.25 MiB	169.79 MiB	0.92%
🟣 hyper:check:unchanged	0.1211s	0.1221s	0.84%	61.84 MiB	62.02 MiB	0.29%	125.11 MiB	125.54 MiB	0.35%
🟣 regex:check:unchanged	0.2250s	0.2271s	0.92%	78.13 MiB	78.98 MiB	💔 1.08%	145.56 MiB	146.65 MiB	0.75%
🟣 syn:check:unchanged	0.4928s	0.4971s	0.88%	118.76 MiB	120.38 MiB	💔 1.36%	193.57 MiB	195.51 MiB	💔 1.00%
Total	1.1436s	1.1540s	0.91%	355.67 MiB	359.52 MiB	💔 1.08%	632.49 MiB	637.50 MiB	0.79%
Summary	1.0000s	1.0090s	0.90%	1 byte	1.01 bytes	0.99%	1 byte	1.01 bytes	0.75%

Local results, 7 threads, including #139756, excluding #139636:

Benchmark	Before	After		Before	After		Before	After
Benchmark	Time	Time	%	Physical Memory	Physical Memory	%	Committed Memory	Committed Memory	%
🟣 clap:check:unchanged	0.3710s	0.3140s	💚 -15.37%	133.25 MiB	134.96 MiB	💔 1.29%	235.08 MiB	237.04 MiB	0.83%
🟣 hyper:check:unchanged	0.1466s	0.1303s	💚 -11.11%	85.72 MiB	86.31 MiB	0.69%	191.98 MiB	192.88 MiB	0.47%
🟣 regex:check:unchanged	0.2831s	0.2353s	💚 -16.86%	113.02 MiB	114.25 MiB	💔 1.09%	212.53 MiB	214.18 MiB	0.78%
🟣 syn:check:unchanged	0.5756s	0.5078s	💚 -11.78%	157.85 MiB	160.31 MiB	💔 1.56%	260.80 MiB	263.61 MiB	💔 1.08%
Total	1.3763s	1.1875s	💚 -13.72%	489.84 MiB	495.83 MiB	💔 1.22%	900.39 MiB	907.70 MiB	0.81%
Summary	1.0000s	0.8622s	💚 -13.78%	1 byte	1.01 bytes	💔 1.16%	1 byte	1.01 bytes	0.79%

bors · 2025-04-13T21:56:54Z

☀️ Try build successful - checks-actions
Build commit: 5545f9c (5545f9c456a47860eda2f034f2d7636b31cff81c)

rust-timer · 2025-04-13T23:11:44Z

Finished benchmarking commit (5545f9c): comparison URL.

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

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 may lead to changes in compiler perf.

Next Steps: If you can justify the regressions found in this try perf run, please indicate this with @rustbot label: +perf-regression-triaged along with sufficient written justification. If you cannot justify the regressions please fix the regressions and do another perf run. If the next run shows neutral or positive results, the label will be automatically removed.

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

Instruction count

This is the most reliable metric that we have; it was used to determine the overall result at the top of this comment. However, even this metric can sometimes exhibit noise.

	mean	range	count
Regressions ❌ (primary)	0.3%	[0.2%, 0.5%]	16
Regressions ❌ (secondary)	0.5%	[0.4%, 0.8%]	11
Improvements ✅ (primary)	-0.6%	[-0.9%, -0.4%]	103
Improvements ✅ (secondary)	-0.6%	[-1.0%, -0.3%]	24
All ❌✅ (primary)	-0.4%	[-0.9%, 0.5%]	119

Max RSS (memory usage)

Results (primary 1.8%, secondary 0.3%)

This is a less reliable metric that may be of interest but was not used to determine the overall result at the top of this comment.

	mean	range	count
Regressions ❌ (primary)	1.8%	[1.1%, 3.0%]	35
Regressions ❌ (secondary)	3.8%	[2.2%, 9.2%]	7
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-3.3%	[-5.1%, -2.3%]	7
All ❌✅ (primary)	1.8%	[1.1%, 3.0%]	35

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: 779.607s -> 782.154s (0.33%)
Artifact size: 365.51 MiB -> 365.50 MiB (-0.00%)

lcnr · 2025-04-14T07:25:51Z

r? compiler

Zoxc · 2025-04-16T05:00:03Z

I'd probably disregard the instruction improvements here and in #139756 as they don't translate into wall time improvements nor are they expected. Maybe MemEncoder uses less instructions?

I think the trade off towards the parallel compiler is reasonable here as incremental builds tends to have more free cores. Do note the 8.6% regression in dep graph size due to the added indices too.

#139756 is split out mostly to get a separate perf run and doesn't make sense without also merging this PR.

r? @oli-obk

compiler/rustc_query_system/src/dep_graph/graph.rs

bors · 2025-04-17T05:55:01Z

☔ The latest upstream changes (presumably #139938) made this pull request unmergeable. Please resolve the merge conflicts.

compiler/rustc_query_system/src/dep_graph/graph.rs

cjgillot · 2025-04-18T23:33:01Z

compiler/rustc_query_system/src/dep_graph/serialized.rs

@@ -76,6 +80,9 @@ const DEP_NODE_PAD: usize = DEP_NODE_SIZE - 1;
 const DEP_NODE_WIDTH_BITS: usize = DEP_NODE_SIZE / 2;

 /// Data for use when recompiling the **current crate**.
+///
+/// There may be unused indices with DEP_KIND_NULL in this graph due to batch allocation of
+/// indices to threads.


Is this batch allocation really necessary? Could we have a single atomic counter to assign the index and avoid the complexity?

We need at least 1 thread local allocation to avoid races when marking nodes green. A single counter would probably result in some congestion as promoting nodes is fairly hot too.

bors · 2025-04-25T19:55:18Z

☔ The latest upstream changes (presumably #139756) made this pull request unmergeable. Please resolve the merge conflicts.

oli-obk · 2025-05-06T08:32:00Z

@bors r+

bors · 2025-05-06T08:32:02Z

📌 Commit e1e8857 has been approved by oli-obk

It is now in the queue for this repository.

Use thread local dep graph encoding This adds thread local encoding of dep graph nodes. Each thread has a `MemEncoder` that gets flushed to the global `FileEncoder` when it exceeds 64 kB. Each thread also has a local cache of dep indices. This means there can now be empty gaps in `SerializedDepGraph`. Indices are marked green and also allocated by the new atomic operation `DepNodeColorMap::try_mark_green` as the encoder lock is removed.

bors · 2025-05-06T09:46:39Z

⌛ Testing commit e1e8857 with merge 64d1378...

bors · 2025-05-06T10:26:20Z

💔 Test failed - checks-actions

oli-obk · 2025-05-06T15:51:50Z

Is the latest change related to the CI failure?

Zoxc · 2025-05-06T16:39:25Z

Yeah, but I changed it to use the portable AtomicU64 fallback now.

oli-obk · 2025-05-06T18:22:25Z

@bors r+

bors · 2025-05-06T18:22:28Z

📌 Commit cdd1049 has been approved by oli-obk

It is now in the queue for this repository.

bors · 2025-05-07T12:39:58Z

⌛ Testing commit cdd1049 with merge 3ef8e64...

bors · 2025-05-07T15:57:32Z

☀️ Test successful - checks-actions
Approved by: oli-obk
Pushing 3ef8e64 to master...

github-actions · 2025-05-07T16:01:00Z

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 db0e836 (parent) -> 3ef8e64 (this PR)

Test differences

No test diffs found

Test dashboard

Run

cargo run --manifest-path src/ci/citool/Cargo.toml -- \
    test-dashboard 3ef8e64ce9f72ee8d600d55bc43b36eed069b252 --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

dist-apple-various: 7408.3s -> 9319.7s (25.8%)
dist-x86_64-apple: 9051.9s -> 11149.8s (23.2%)
dist-aarch64-apple: 7024.6s -> 5794.5s (-17.5%)
dist-arm-linux: 5257.9s -> 4400.3s (-16.3%)
aarch64-apple: 4203.8s -> 4852.3s (15.4%)
x86_64-gnu-llvm-20-3: 6815.5s -> 7341.1s (7.7%)
x86_64-gnu-distcheck: 4386.0s -> 4724.3s (7.7%)
x86_64-apple-2: 4662.4s -> 4950.9s (6.2%)
dist-powerpc64le-linux: 9864.4s -> 9313.4s (-5.6%)
dist-armhf-linux: 5120.7s -> 5399.4s (5.4%)

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-timer · 2025-05-07T17:37:17Z

Finished benchmarking commit (3ef8e64): comparison URL.

Overall result: ❌ regressions - please read the text below

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

This is the most reliable metric that we have; it was used to determine the overall result at the top of this comment. However, even this metric can sometimes exhibit noise.

	mean	range	count
Regressions ❌ (primary)	0.3%	[0.2%, 0.7%]	90
Regressions ❌ (secondary)	0.3%	[0.2%, 0.5%]	12
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	0.3%	[0.2%, 0.7%]	90

Max RSS (memory usage)

Results (primary -0.6%, secondary -0.5%)

This is a less reliable metric that may be of interest but was not used to determine the overall result at the top of this comment.

	mean	range	count
Regressions ❌ (primary)	1.1%	[0.4%, 1.9%]	2
Regressions ❌ (secondary)	3.7%	[3.7%, 3.7%]	1
Improvements ✅ (primary)	-1.2%	[-3.8%, -0.4%]	6
Improvements ✅ (secondary)	-4.8%	[-4.8%, -4.8%]	1
All ❌✅ (primary)	-0.6%	[-3.8%, 1.9%]	8

Cycles

Results (primary 0.4%, secondary -4.2%)

This is a less reliable metric that may be of interest but was not used to determine the overall result at the top of this comment.

	mean	range	count
Regressions ❌ (primary)	0.6%	[0.4%, 0.8%]	15
Regressions ❌ (secondary)	-	-	0
Improvements ✅ (primary)	-0.5%	[-0.6%, -0.4%]	3
Improvements ✅ (secondary)	-4.2%	[-5.2%, -2.8%]	3
All ❌✅ (primary)	0.4%	[-0.6%, 0.8%]	18

Binary size

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

Bootstrap: 768.419s -> 770.356s (0.25%)
Artifact size: 365.16 MiB -> 365.20 MiB (0.01%)

rustbot assigned lcnr Apr 13, 2025

This comment has been minimized.

Sign in to view

rustbot added the S-waiting-on-perf Status: Waiting on a perf run to be completed. label Apr 13, 2025

This comment has been minimized.

Sign in to view

rustbot added perf-regression Performance regression. and removed S-waiting-on-perf Status: Waiting on a perf run to be completed. labels Apr 13, 2025

rustbot assigned Nadrieril and unassigned lcnr Apr 14, 2025

Zoxc force-pushed the thread-local-graph branch from 8167fdb to 7d236d0 Compare April 15, 2025 18:18

rustbot assigned oli-obk and unassigned Nadrieril Apr 16, 2025

Zoxc marked this pull request as ready for review April 16, 2025 05:00

oli-obk reviewed Apr 16, 2025

View reviewed changes

compiler/rustc_query_system/src/dep_graph/graph.rs Show resolved Hide resolved

cjgillot reviewed Apr 18, 2025

View reviewed changes

Zoxc force-pushed the thread-local-graph branch from 7d236d0 to c1067ba Compare April 22, 2025 02:44

Zoxc force-pushed the thread-local-graph branch from c1067ba to 9bb8430 Compare April 25, 2025 23:46

Zoxc added 2 commits May 5, 2025 20:50

Tweak index chunk allocation

aeab281

Add some comments about thread local indices

e1e8857

bors 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-author Status: This is awaiting some action (such as code changes or more information) from the author. labels May 6, 2025

This comment has been minimized.

Sign in to view

bors added S-waiting-on-review Status: Awaiting review from the assignee but also interested parties. and removed S-waiting-on-bors Status: Waiting on bors to run and complete tests. Bors will change the label on completion. labels May 6, 2025

Use the portable AtomicU64

cdd1049

Zoxc force-pushed the thread-local-graph branch from 10096ce to cdd1049 Compare May 6, 2025 16:36

bors 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 May 6, 2025

bors added the merged-by-bors This PR was explicitly merged by bors. label May 7, 2025

bors merged commit 3ef8e64 into rust-lang:master May 7, 2025
7 checks passed

rustbot added this to the 1.88.0 milestone May 7, 2025

This was referenced May 7, 2025

Create the previous dep graph index on a background thread #116375

Draft

Handle rustc_query_system cases of rustc::potential_query_instability lint #131200

Open

Zoxc deleted the thread-local-graph branch May 7, 2025 16:54

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Use thread local dep graph encoding #139758

Use thread local dep graph encoding #139758

Zoxc commented Apr 13, 2025 •

edited

Loading

rustbot commented Apr 13, 2025

Zoxc commented Apr 13, 2025

This comment has been minimized.

bors commented Apr 13, 2025

Zoxc commented Apr 13, 2025

bors commented Apr 13, 2025

This comment has been minimized.

rust-timer commented Apr 13, 2025

lcnr commented Apr 14, 2025

Zoxc commented Apr 16, 2025

bors commented Apr 17, 2025

cjgillot Apr 18, 2025

Zoxc Apr 19, 2025

bors commented Apr 25, 2025

oli-obk commented May 6, 2025

bors commented May 6, 2025

bors commented May 6, 2025

This comment has been minimized.

bors commented May 6, 2025

oli-obk commented May 6, 2025

Zoxc commented May 6, 2025

oli-obk commented May 6, 2025

bors commented May 6, 2025

bors commented May 7, 2025

bors commented May 7, 2025

github-actions bot commented May 7, 2025

rust-timer commented May 7, 2025

Use thread local dep graph encoding #139758

Use thread local dep graph encoding #139758

Conversation

Zoxc commented Apr 13, 2025 • edited Loading

rustbot commented Apr 13, 2025

Zoxc commented Apr 13, 2025

This comment has been minimized.

bors commented Apr 13, 2025

Zoxc commented Apr 13, 2025

bors commented Apr 13, 2025

This comment has been minimized.

rust-timer commented Apr 13, 2025

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

lcnr commented Apr 14, 2025

Zoxc commented Apr 16, 2025

bors commented Apr 17, 2025

Choose a reason for hiding this comment

Choose a reason for hiding this comment

bors commented Apr 25, 2025

oli-obk commented May 6, 2025

bors commented May 6, 2025

bors commented May 6, 2025

This comment has been minimized.

bors commented May 6, 2025

oli-obk commented May 6, 2025

Zoxc commented May 6, 2025

oli-obk commented May 6, 2025

bors commented May 6, 2025

bors commented May 7, 2025

bors commented May 7, 2025

github-actions bot commented May 7, 2025

Test differences

Job duration changes

rust-timer commented May 7, 2025

Overall result: ❌ regressions - please read the text below

Zoxc commented Apr 13, 2025 •

edited

Loading