Files
neon/pageserver/Cargo.toml
John Spray ca5390a89d pageserver: add bench_ingest (#7409)
## Problem

We lack a rust bench for the inmemory layer and delta layer write paths:
it is useful to benchmark these components independent of postgres & WAL
decoding.

Related: https://github.com/neondatabase/neon/issues/8452

## Summary of changes

- Refactor DeltaLayerWriter to avoid carrying a Timeline, so that it can
be cleanly tested + benched without a Tenant/Timeline test harness. It
only needed the Timeline for building `Layer`, so this can be done in a
separate step.
- Add `bench_ingest`, which exercises a variety of workload "shapes"
(big values, small values, sequential keys, random keys)
- Include a small uncontroversial optimization: in `freeze`, only
exhaustively walk values to assert ordering relative to end_lsn in debug
mode.

These benches are limited by drive performance on a lot of machines, but
still useful as a local tool for iterating on CPU/memory improvements
around this code path.

Anecdotal measurements on Hetzner AX102 (Ryzen 7950xd):

```

ingest-small-values/ingest 128MB/100b seq
                        time:   [1.1160 s 1.1230 s 1.1289 s]
                        thrpt:  [113.38 MiB/s 113.98 MiB/s 114.70 MiB/s]
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) low mild
Benchmarking ingest-small-values/ingest 128MB/100b rand: Warming up for 3.0000 s
Warning: Unable to complete 10 samples in 10.0s. You may wish to increase target time to 18.9s.
ingest-small-values/ingest 128MB/100b rand
                        time:   [1.9001 s 1.9056 s 1.9110 s]
                        thrpt:  [66.982 MiB/s 67.171 MiB/s 67.365 MiB/s]
Benchmarking ingest-small-values/ingest 128MB/100b rand-1024keys: Warming up for 3.0000 s
Warning: Unable to complete 10 samples in 10.0s. You may wish to increase target time to 11.0s.
ingest-small-values/ingest 128MB/100b rand-1024keys
                        time:   [1.0715 s 1.0828 s 1.0937 s]
                        thrpt:  [117.04 MiB/s 118.21 MiB/s 119.46 MiB/s]
ingest-small-values/ingest 128MB/100b seq, no delta
                        time:   [425.49 ms 429.07 ms 432.04 ms]
                        thrpt:  [296.27 MiB/s 298.32 MiB/s 300.83 MiB/s]
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) low mild

ingest-big-values/ingest 128MB/8k seq
                        time:   [373.03 ms 375.84 ms 379.17 ms]
                        thrpt:  [337.58 MiB/s 340.57 MiB/s 343.13 MiB/s]
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) high mild
ingest-big-values/ingest 128MB/8k seq, no delta
                        time:   [81.534 ms 82.811 ms 83.364 ms]
                        thrpt:  [1.4994 GiB/s 1.5095 GiB/s 1.5331 GiB/s]
Found 1 outliers among 10 measurements (10.00%)


```
2024-08-06 16:39:40 +00:00

115 lines
3.2 KiB
TOML

[package]
name = "pageserver"
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]
anyhow.workspace = true
arc-swap.workspace = true
async-compression.workspace = true
async-stream.workspace = true
async-trait.workspace = true
byteorder.workspace = true
bytes.workspace = true
camino.workspace = true
camino-tempfile.workspace = true
chrono = { workspace = true, features = ["serde"] }
clap = { workspace = true, features = ["string"] }
const_format.workspace = true
consumption_metrics.workspace = true
crc32c.workspace = true
crossbeam-utils.workspace = true
either.workspace = true
flate2.workspace = true
fail.workspace = true
futures.workspace = true
git-version.workspace = true
hex.workspace = true
humantime.workspace = true
humantime-serde.workspace = true
hyper.workspace = true
itertools.workspace = true
leaky-bucket.workspace = true
md5.workspace = true
nix.workspace = true
# hack to get the number of worker threads tokio uses
num_cpus = { version = "1.15" }
num-traits.workspace = true
once_cell.workspace = true
pin-project-lite.workspace = true
postgres.workspace = true
postgres_backend.workspace = true
postgres-protocol.workspace = true
postgres-types.workspace = true
rand.workspace = true
range-set-blaze = { version = "0.1.16", features = ["alloc"] }
regex.workspace = true
scopeguard.workspace = true
serde.workspace = true
serde_json = { workspace = true, features = ["raw_value"] }
serde_path_to_error.workspace = true
serde_with.workspace = true
signal-hook.workspace = true
smallvec = { workspace = true, features = ["write"] }
svg_fmt.workspace = true
sync_wrapper.workspace = true
sysinfo.workspace = true
tokio-tar.workspace = true
thiserror.workspace = true
tikv-jemallocator.workspace = true
tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time"] }
tokio-epoll-uring.workspace = true
tokio-io-timeout.workspace = true
tokio-postgres.workspace = true
tokio-stream.workspace = true
tokio-util.workspace = true
toml_edit = { workspace = true, features = [ "serde" ] }
tracing.workspace = true
twox-hash.workspace = true
url.workspace = true
walkdir.workspace = true
metrics.workspace = true
pageserver_api.workspace = true
pageserver_compaction.workspace = true
postgres_connection.workspace = true
postgres_ffi.workspace = true
pq_proto.workspace = true
remote_storage.workspace = true
storage_broker.workspace = true
tenant_size_model.workspace = true
utils.workspace = true
workspace_hack.workspace = true
reqwest.workspace = true
rpds.workspace = true
enum-map.workspace = true
enumset = { workspace = true, features = ["serde"]}
strum.workspace = true
strum_macros.workspace = true
[target.'cfg(target_os = "linux")'.dependencies]
procfs.workspace = true
[dev-dependencies]
criterion.workspace = true
hex-literal.workspace = true
tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time", "test-util"] }
[[bench]]
name = "bench_layer_map"
harness = false
[[bench]]
name = "bench_walredo"
harness = false
[[bench]]
name = "bench_ingest"
harness = false