Files
neon/safekeeper/Cargo.toml
Erik Grinaker 190e8cebac safekeeper,pageserver: add CPU profiling (#9764)
## 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](https://grafana.com/products/cloud/profiles-for-continuous-profiling/).
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/cpu` that takes a CPU profile and returns
it. Defaults to a 5-second pprof Protobuf profile for use with e.g.
`pprof` or Grafana Alloy, but can also emit an SVG flamegraph. Query
parameters:

* `format`: output format (`pprof` or `svg`)
* `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 under `target/criterion/*/profile/flamegraph.svg`.

Example profiles:

* pprof profile (use [`pprof`](https://github.com/google/pprof)):
[profile.pb.gz](https://github.com/user-attachments/files/17756788/profile.pb.gz)
  * Web interface: `pprof -http :6060 profile.pb.gz`
* Interactive flamegraph:
[profile.svg.gz](https://github.com/user-attachments/files/17756782/profile.svg.gz)
2024-11-21 18:59:46 +00:00

76 lines
1.9 KiB
TOML

[package]
name = "safekeeper"
version = "0.1.0"
edition.workspace = true
license.workspace = true
[features]
default = []
# Enables test-only APIs, incuding failpoints. In particular, enables the `fail_point!` macro,
# which adds some runtime cost to run tests on outage conditions
testing = ["fail/failpoints"]
[dependencies]
async-stream.workspace = true
anyhow.workspace = true
byteorder.workspace = true
bytes.workspace = true
camino.workspace = true
camino-tempfile.workspace = true
chrono.workspace = true
clap = { workspace = true, features = ["derive"] }
crc32c.workspace = true
fail.workspace = true
hex.workspace = true
humantime.workspace = true
http.workspace = true
hyper0.workspace = true
futures.workspace = true
once_cell.workspace = true
parking_lot.workspace = true
postgres.workspace = true
postgres-protocol.workspace = true
pprof.workspace = true
rand.workspace = true
regex.workspace = true
scopeguard.workspace = true
reqwest = { workspace = true, features = ["json"] }
serde.workspace = true
serde_json.workspace = true
strum.workspace = true
strum_macros.workspace = true
thiserror.workspace = true
tokio = { workspace = true, features = ["fs"] }
tokio-util = { workspace = true }
tokio-io-timeout.workspace = true
tokio-postgres.workspace = true
tokio-tar.workspace = true
tracing.workspace = true
url.workspace = true
metrics.workspace = true
postgres_backend.workspace = true
postgres_ffi.workspace = true
pq_proto.workspace = true
remote_storage.workspace = true
safekeeper_api.workspace = true
sha2.workspace = true
sd-notify.workspace = true
storage_broker.workspace = true
tokio-stream.workspace = true
utils.workspace = true
workspace_hack.workspace = true
[dev-dependencies]
criterion.workspace = true
itertools.workspace = true
walproposer.workspace = true
rand.workspace = true
desim.workspace = true
tracing.workspace = true
tracing-subscriber = { workspace = true, features = ["json"] }
[[bench]]
name = "receive_wal"
harness = false