safekeeper: add CPU profiling #9764
Open
+301
−10
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
erikgrinaker
commented
Nov 14, 2024
Comment on lines
578
to
+579
| static ALLOWLIST_ROUTES: Lazy<HashSet<Uri>> = Lazy::new(|| { | ||
| ["/v1/status", "/metrics"] | ||
| ["/v1/status", "/metrics", "/pprof/profile"] |
There was a problem hiding this comment.
I didn't put this behind auth, since it's pretty inconvenient. The perf impact is minor, and only one profile can run at a time, so it's not a DoS vector. It only exposes function and module names, so it's not a data leak risk.
There was a problem hiding this comment.
We should probably give this endpoint as well as the metrics endpoint actual JWT authentication eventually. I've filed a private issue https://github.com/neondatabase/cloud/issues/20372 as it is relevant to security.
For now I agree with you though.
erikgrinaker
commented
Nov 14, 2024
5 tasks
5490 tests run: 5247 passed, 0 failed, 243 skipped (full report)Code coverage* (full report)
* collected from Rust tests only The comment gets automatically updated with the latest test results
e28059c at 2024-11-18T11:02:32.872Z :recycle: |
|
The CDDL-1.0 license used by the |
erikgrinaker
added a commit
that referenced
this pull request
Nov 15, 2024
#9764, which adds profiling support to Safekeeper, pulls in the dependency [`inferno`](https://crates.io/crates/inferno) via [`pprof-rs`](https://crates.io/crates/pprof). This is licenced under the [Common Development and Distribution License 1.0](https://spdx.org/licenses/CDDL-1.0.html), which is not allowed by `cargo-deny`. This patch allows the CDDL-1.0 license. It is a derivative of the Mozilla Public License, which we already allow, but avoids some issues around European copyright law that the MPL had. As such, I don't expect this to be problematic.
erikgrinaker
changed the title
erikgrinaker
force-pushed
the
erik/pprof
branch
from
55768c9
to
e28059c
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Problem
We don't have a convenient way to gather CPU profiles from a running binary, e.g. during production incidents or end-to-end benchmarks, nor during microbenchmarks (particularly on macOS).
We would also like to have continuous profiling in production, likely using Grafana Cloud Profiles. We may choose to use either eBPF profiles or pprof profiles for this (pending testing and discussion with SREs), but pprof profiles appear useful regardless for the reasons listed above. See https://github.com/neondatabase/cloud/issues/14888.
This PR is intended as a proof of concept, to try it out in staging and drive further discussions about profiling more broadly.
Touches #9534.
Touches https://github.com/neondatabase/cloud/issues/14888.
Summary of changes
Adds a HTTP route
/profile/cputhat takes a CPU profile and returns it. Defaults to an SVG flamegraph over a 5-second duration, but can also emit pprof Protobuf profiles for use with e.g.pprofor Grafana Alloy. Query parameters:format: output format (pproforsvg)frequency: sampling frequency in microseconds (default 100)seconds: number of seconds to profile (default 5)Also integrates pprof profiles into Criterion benchmarks, such that flamegraph reports can be taken with
cargo bench ... --profile-duration <seconds>. Output undertarget/criterion/*/profile/flamegraph.svg.Example profiles:
pprof): profile.pb.gzpprof -http :6060 profile.pb.gz