Files
neon/pageserver/Cargo.toml
Vlad Lazar 0e490f3be7 pageserver: allow concurrent rw IO on in-mem layer (#12151)
## Problem

Previously, we couldn't read from an in-memory layer while a batch was
being written to it. Vice-versa, we couldn't write to it while there
was an on-going read.

## Summary of Changes

The goal of this change is to improve concurrency. Writes happened
through a &mut self method so the enforcement was at the type system
level.

We attempt to improve by:
1. Adding interior mutability to EphemeralLayer. This involves wrapping
   the buffered writer in a read-write lock.
2. Minimise the time that the read lock is held for. Only hold the read
   lock while reading from the buffers (recently flushed or pending
   flush). If we need to read from the file, drop the lock and allow IO
   to be concurrent.
   
The new benchmark variants with concurrent reads improve between 70 to
200 percent (against main).
Benchmark results are in this
[commit](891f094ce6).

## Future Changes

We can push the interior mutability into the buffered writer. The
mutable tail goes under a read lock, the flushed part goes into an
ArcSwap and then we can read from anything that is flushed _without_ any
locking.
2025-06-23 13:17:30 +00:00

146 lines
4.0 KiB
TOML

[package]
name = "pageserver"
version = "0.1.0"
edition = "2024"
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", "pageserver_api/testing", "wal_decoder/testing", "pageserver_client/testing"]
fuzz-read-path = ["testing"]
# Enables benchmarking only APIs
benchmarking = []
[dependencies]
anyhow.workspace = true
arc-swap.workspace = true
async-compression.workspace = true
async-stream.workspace = true
bincode.workspace = true
bit_field.workspace = true
byteorder.workspace = true
bytes.workspace = true
camino-tempfile.workspace = true
camino.workspace = true
chrono = { workspace = true, features = ["serde"] }
clap = { workspace = true, features = ["string"] }
consumption_metrics.workspace = true
crc32c.workspace = true
either.workspace = true
enum-map.workspace = true
enumset = { workspace = true, features = ["serde"]}
fail.workspace = true
futures.workspace = true
hashlink.workspace = true
hex.workspace = true
http.workspace = true
http-utils.workspace = true
humantime-serde.workspace = true
humantime.workspace = true
hyper0.workspace = true
itertools.workspace = true
jsonwebtoken.workspace = true
md5.workspace = true
metrics.workspace = true
nix.workspace = true
num_cpus.workspace = true # hack to get the number of worker threads tokio uses
num-traits.workspace = true
once_cell.workspace = true
pageserver_api.workspace = true
pageserver_client.workspace = true # for ResponseErrorMessageExt TOOD refactor that
pageserver_compaction.workspace = true
pageserver_page_api.workspace = true
pem.workspace = true
pin-project-lite.workspace = true
postgres_backend.workspace = true
postgres_connection.workspace = true
postgres_ffi.workspace = true
postgres_ffi_types.workspace = true
postgres_initdb.workspace = true
postgres-protocol.workspace = true
postgres-types.workspace = true
posthog_client_lite.workspace = true
pprof.workspace = true
pq_proto.workspace = true
rand.workspace = true
range-set-blaze = { version = "0.1.16", features = ["alloc"] }
regex.workspace = true
remote_storage.workspace = true
reqwest.workspace = true
rpds.workspace = true
rustls.workspace = true
scopeguard.workspace = true
send-future.workspace = true
serde_json = { workspace = true, features = ["raw_value"] }
serde_path_to_error.workspace = true
serde_with.workspace = true
serde.workspace = true
smallvec.workspace = true
storage_broker.workspace = true
strum_macros.workspace = true
strum.workspace = true
sysinfo.workspace = true
tenant_size_model.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-rustls.workspace = true
tokio-stream.workspace = true
tokio-tar.workspace = true
tokio-util.workspace = true
toml_edit = { workspace = true, features = [ "serde" ] }
tonic.workspace = true
tonic-reflection.workspace = true
tower.workspace = true
tracing.workspace = true
tracing-utils.workspace = true
url.workspace = true
utils.workspace = true
wal_decoder.workspace = true
walkdir.workspace = true
workspace_hack.workspace = true
twox-hash.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"] }
indoc.workspace = true
uuid.workspace = true
rstest.workspace = true
[[bench]]
name = "bench_layer_map"
harness = false
[[bench]]
name = "bench_walredo"
harness = false
[[bench]]
name = "bench_ingest"
harness = false
required-features = ["benchmarking"]
[[bench]]
name = "upload_queue"
harness = false
[[bench]]
name = "bench_metrics"
harness = false
[[bin]]
name = "test_helper_slow_client_reads"
required-features = [ "testing" ]