Files
neon/pageserver/Cargo.toml
Christian Schwarz 850421ec06 refactor(pageserver): rely on serde derive for toml deserialization (#7656)
This PR simplifies the pageserver configuration parsing as follows:

* introduce the `pageserver_api::config::ConfigToml` type
* implement `Default` for `ConfigToml`
* use serde derive to do the brain-dead leg-work of processing the toml
document
  * use `serde(default)` to fill in default values
* in `pageserver` crate:
* use `toml_edit` to deserialize the pageserver.toml string into a
`ConfigToml`
  * `PageServerConfig::parse_and_validate` then
    * consumes the `ConfigToml`
    * destructures it exhaustively into its constituent fields
    * constructs the `PageServerConfig`

The rules are:

* in `ConfigToml`, use `deny_unknown_fields` everywhere
* static default values go in `pageserver_api`
* if there cannot be a static default value (e.g. which default IO
engine to use, because it depends on the runtime), make the field in
`ConfigToml` an `Option`
* if runtime-augmentation of a value is needed, do that in
`parse_and_validate`
* a good example is `virtual_file_io_engine` or `l0_flush`, both of
which need to execute code to determine the effective value in
`PageServerConf`

The benefits:

* massive amount of brain-dead repetitive code can be deleted
* "unused variable" compile-time errors when removing a config value,
due to the exhaustive destructuring in `parse_and_validate`
* compile-time errors guide you when adding a new config field

Drawbacks:

* serde derive is sometimes a bit too magical
* `deny_unknown_fields` is easy to miss

Future Work / Benefits:
* make `neon_local` use `pageserver_api` to construct `ConfigToml` and
write it to `pageserver.toml`
* This provides more type safety / coompile-time errors than the current
approach.

### Refs

Fixes #3682 

### Future Work

* `remote_storage` deser doesn't reject unknown fields
https://github.com/neondatabase/neon/issues/8915
* clean up `libs/pageserver_api/src/config.rs` further
  * break up into multiple files, at least for tenant config
* move `models` as appropriate / refine distinction between config and
API models / be explicit about when it's the same
  * use `pub(crate)` visibility on `mod defaults` to detect stale values
2024-09-05 14:59:49 +02:00

117 lines
3.3 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", "pageserver_api/testing" ]
[dependencies]
anyhow.workspace = true
arc-swap.workspace = true
async-compression.workspace = true
async-stream.workspace = true
async-trait.workspace = true
bit_field.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
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
send-future.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"] }
indoc.workspace = true
[[bench]]
name = "bench_layer_map"
harness = false
[[bench]]
name = "bench_walredo"
harness = false
[[bench]]
name = "bench_ingest"
harness = false