garage/src/util/config.rs

228 lines
5.9 KiB
Rust
Raw Normal View History

2021-03-20 19:38:44 +00:00
//! Contains type and functions related to Garage configuration file
2020-04-23 17:05:46 +00:00
use std::io::Read;
use std::net::SocketAddr;
use std::path::PathBuf;
2021-10-14 09:50:12 +00:00
use serde::de::Error as SerdeError;
use serde::{de, Deserialize};
2020-04-23 17:05:46 +00:00
use netapp::util::parse_and_resolve_peer_addr;
use netapp::NodeID;
2021-10-14 09:50:12 +00:00
2020-04-23 17:05:46 +00:00
use crate::error::Error;
2021-03-20 19:38:44 +00:00
/// Represent the whole configuration
2020-04-23 17:05:46 +00:00
#[derive(Deserialize, Debug, Clone)]
pub struct Config {
/// Path where to store metadata. Should be fast, but low volume
2020-04-23 17:05:46 +00:00
pub metadata_dir: PathBuf,
/// Path where to store data. Can be slower, but need higher volume
2020-04-23 17:05:46 +00:00
pub data_dir: PathBuf,
/// Size of data blocks to save to disk
#[serde(default = "default_block_size")]
pub block_size: usize,
/// Replication mode. Supported values:
/// - none, 1 -> no replication
/// - 2 -> 2-way replication
/// - 3 -> 3-way replication
// (we can add more aliases for this later)
pub replication_mode: String,
/// Zstd compression level used on data blocks
#[serde(
deserialize_with = "deserialize_compression",
default = "default_compression"
)]
pub compression_level: Option<i32>,
2021-10-14 09:50:12 +00:00
/// RPC secret key: 32 bytes hex encoded
pub rpc_secret: String,
/// Address to bind for RPC
2020-04-23 17:05:46 +00:00
pub rpc_bind_addr: SocketAddr,
/// Public IP address of this node
pub rpc_public_addr: Option<SocketAddr>,
2020-04-23 17:05:46 +00:00
/// Bootstrap peers RPC address
#[serde(deserialize_with = "deserialize_vec_addr", default)]
2021-10-14 09:50:12 +00:00
pub bootstrap_peers: Vec<(NodeID, SocketAddr)>,
/// Consul host to connect to to discover more peers
pub consul_host: Option<String>,
/// Consul service name to use
pub consul_service_name: Option<String>,
/// Kubernetes namespace the service discovery resources are be created in
pub kubernetes_namespace: Option<String>,
/// Service name to filter for in k8s custom resources
pub kubernetes_service_name: Option<String>,
/// Skip creation of the garagenodes CRD
#[serde(default)]
pub kubernetes_skip_crd: bool,
2020-04-23 17:05:46 +00:00
Abstract database behind generic interface and implement alternative drivers (#322) - [x] Design interface - [x] Implement Sled backend - [x] Re-implement the SledCountedTree hack ~~on Sled backend~~ on all backends (i.e. over the abstraction) - [x] Convert Garage code to use generic interface - [x] Proof-read converted Garage code - [ ] Test everything well - [x] Implement sqlite backend - [x] Implement LMDB backend - [ ] (Implement Persy backend?) - [ ] (Implement other backends? (like RocksDB, ...)) - [x] Implement backend choice in config file and garage server module - [x] Add CLI for converting between DB formats - Exploit the new interface to put more things in transactions - [x] `.updated()` trigger on Garage tables Fix #284 **Bugs** - [x] When exporting sqlite, trees iterate empty?? - [x] LMDB doesn't work **Known issues for various back-ends** - Sled: - Eats all my RAM and also all my disk space - `.len()` has to traverse the whole table - Is actually quite slow on some operations - And is actually pretty bad code... - Sqlite: - Requires a lock to be taken on all operations. The lock is also taken when iterating on a table with `.iter()`, and the lock isn't released until the iterator is dropped. This means that we must be VERY carefull to not do anything else inside a `.iter()` loop or else we will have a deadlock! Most such cases have been eliminated from the Garage codebase, but there might still be some that remain. If your Garage-over-Sqlite seems to hang/freeze, this is the reason. - (adapter uses a bunch of unsafe code) - Heed (LMDB): - Not suited for 32-bit machines as it has to map the whole DB in memory. - (adpater uses a tiny bit of unsafe code) **My recommendation:** avoid 32-bit machines and use LMDB as much as possible. **Converting databases** is actually quite easy. For example from Sled to LMDB: ```bash cd src/db cargo run --features cli --bin convert -- -i path/to/garage/meta/db -a sled -o path/to/garage/meta/db.lmdb -b lmdb ``` Then, just add this to your `config.toml`: ```toml db_engine = "lmdb" ``` Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/322 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-06-08 08:01:44 +00:00
// -- DB
/// Database engine to use for metadata (options: sled, sqlite, lmdb)
#[serde(default = "default_db_engine")]
pub db_engine: String,
/// Sled cache size, in bytes
#[serde(default = "default_sled_cache_capacity")]
pub sled_cache_capacity: u64,
/// Sled flush interval in milliseconds
#[serde(default = "default_sled_flush_every_ms")]
pub sled_flush_every_ms: u64,
Abstract database behind generic interface and implement alternative drivers (#322) - [x] Design interface - [x] Implement Sled backend - [x] Re-implement the SledCountedTree hack ~~on Sled backend~~ on all backends (i.e. over the abstraction) - [x] Convert Garage code to use generic interface - [x] Proof-read converted Garage code - [ ] Test everything well - [x] Implement sqlite backend - [x] Implement LMDB backend - [ ] (Implement Persy backend?) - [ ] (Implement other backends? (like RocksDB, ...)) - [x] Implement backend choice in config file and garage server module - [x] Add CLI for converting between DB formats - Exploit the new interface to put more things in transactions - [x] `.updated()` trigger on Garage tables Fix #284 **Bugs** - [x] When exporting sqlite, trees iterate empty?? - [x] LMDB doesn't work **Known issues for various back-ends** - Sled: - Eats all my RAM and also all my disk space - `.len()` has to traverse the whole table - Is actually quite slow on some operations - And is actually pretty bad code... - Sqlite: - Requires a lock to be taken on all operations. The lock is also taken when iterating on a table with `.iter()`, and the lock isn't released until the iterator is dropped. This means that we must be VERY carefull to not do anything else inside a `.iter()` loop or else we will have a deadlock! Most such cases have been eliminated from the Garage codebase, but there might still be some that remain. If your Garage-over-Sqlite seems to hang/freeze, this is the reason. - (adapter uses a bunch of unsafe code) - Heed (LMDB): - Not suited for 32-bit machines as it has to map the whole DB in memory. - (adpater uses a tiny bit of unsafe code) **My recommendation:** avoid 32-bit machines and use LMDB as much as possible. **Converting databases** is actually quite easy. For example from Sled to LMDB: ```bash cd src/db cargo run --features cli --bin convert -- -i path/to/garage/meta/db -a sled -o path/to/garage/meta/db.lmdb -b lmdb ``` Then, just add this to your `config.toml`: ```toml db_engine = "lmdb" ``` Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/322 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-06-08 08:01:44 +00:00
// -- APIs
/// Configuration for S3 api
First implementation of K2V (#293) **Specification:** View spec at [this URL](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/k2v/doc/drafts/k2v-spec.md) - [x] Specify the structure of K2V triples - [x] Specify the DVVS format used for causality detection - [x] Specify the K2V index (just a counter of number of values per partition key) - [x] Specify single-item endpoints: ReadItem, InsertItem, DeleteItem - [x] Specify index endpoint: ReadIndex - [x] Specify multi-item endpoints: InsertBatch, ReadBatch, DeleteBatch - [x] Move to JSON objects instead of tuples - [x] Specify endpoints for polling for updates on single values (PollItem) **Implementation:** - [x] Table for K2V items, causal contexts - [x] Indexing mechanism and table for K2V index - [x] Make API handlers a bit more generic - [x] K2V API endpoint - [x] K2V API router - [x] ReadItem - [x] InsertItem - [x] DeleteItem - [x] PollItem - [x] ReadIndex - [x] InsertBatch - [x] ReadBatch - [x] DeleteBatch **Testing:** - [x] Just a simple Python script that does some requests to check visually that things are going right (does not contain parsing of results or assertions on returned values) - [x] Actual tests: - [x] Adapt testing framework - [x] Simple test with InsertItem + ReadItem - [x] Test with several Insert/Read/DeleteItem + ReadIndex - [x] Test all combinations of return formats for ReadItem - [x] Test with ReadBatch, InsertBatch, DeleteBatch - [x] Test with PollItem - [x] Test error codes - [ ] Fix most broken stuff - [x] test PollItem broken randomly - [x] when invalid causality tokens are given, errors should be 4xx not 5xx **Improvements:** - [x] Descending range queries - [x] Specify - [x] Implement - [x] Add test - [x] Batch updates to index counter - [x] Put K2V behind `k2v` feature flag Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/293 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-05-10 11:16:57 +00:00
pub s3_api: S3ApiConfig,
/// Configuration for K2V api
pub k2v_api: Option<K2VApiConfig>,
2020-10-31 16:28:56 +00:00
/// Configuration for serving files as normal web server
2022-09-07 15:54:16 +00:00
pub s3_web: Option<WebConfig>,
/// Configuration for the admin API endpoint
2022-03-10 09:51:40 +00:00
#[serde(default = "Default::default")]
pub admin: AdminConfig,
2020-04-23 17:05:46 +00:00
}
2021-03-20 19:38:44 +00:00
/// Configuration for S3 api
2020-04-24 17:46:52 +00:00
#[derive(Deserialize, Debug, Clone)]
First implementation of K2V (#293) **Specification:** View spec at [this URL](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/k2v/doc/drafts/k2v-spec.md) - [x] Specify the structure of K2V triples - [x] Specify the DVVS format used for causality detection - [x] Specify the K2V index (just a counter of number of values per partition key) - [x] Specify single-item endpoints: ReadItem, InsertItem, DeleteItem - [x] Specify index endpoint: ReadIndex - [x] Specify multi-item endpoints: InsertBatch, ReadBatch, DeleteBatch - [x] Move to JSON objects instead of tuples - [x] Specify endpoints for polling for updates on single values (PollItem) **Implementation:** - [x] Table for K2V items, causal contexts - [x] Indexing mechanism and table for K2V index - [x] Make API handlers a bit more generic - [x] K2V API endpoint - [x] K2V API router - [x] ReadItem - [x] InsertItem - [x] DeleteItem - [x] PollItem - [x] ReadIndex - [x] InsertBatch - [x] ReadBatch - [x] DeleteBatch **Testing:** - [x] Just a simple Python script that does some requests to check visually that things are going right (does not contain parsing of results or assertions on returned values) - [x] Actual tests: - [x] Adapt testing framework - [x] Simple test with InsertItem + ReadItem - [x] Test with several Insert/Read/DeleteItem + ReadIndex - [x] Test all combinations of return formats for ReadItem - [x] Test with ReadBatch, InsertBatch, DeleteBatch - [x] Test with PollItem - [x] Test error codes - [ ] Fix most broken stuff - [x] test PollItem broken randomly - [x] when invalid causality tokens are given, errors should be 4xx not 5xx **Improvements:** - [x] Descending range queries - [x] Specify - [x] Implement - [x] Add test - [x] Batch updates to index counter - [x] Put K2V behind `k2v` feature flag Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/293 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-05-10 11:16:57 +00:00
pub struct S3ApiConfig {
/// Address and port to bind for api serving
2022-09-07 15:54:16 +00:00
pub api_bind_addr: Option<SocketAddr>,
/// S3 region to use
2020-04-24 17:46:52 +00:00
pub s3_region: String,
2021-11-11 10:26:02 +00:00
/// Suffix to remove from domain name to find bucket. If None,
/// vhost-style S3 request are disabled
pub root_domain: Option<String>,
2020-04-24 17:46:52 +00:00
}
First implementation of K2V (#293) **Specification:** View spec at [this URL](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/k2v/doc/drafts/k2v-spec.md) - [x] Specify the structure of K2V triples - [x] Specify the DVVS format used for causality detection - [x] Specify the K2V index (just a counter of number of values per partition key) - [x] Specify single-item endpoints: ReadItem, InsertItem, DeleteItem - [x] Specify index endpoint: ReadIndex - [x] Specify multi-item endpoints: InsertBatch, ReadBatch, DeleteBatch - [x] Move to JSON objects instead of tuples - [x] Specify endpoints for polling for updates on single values (PollItem) **Implementation:** - [x] Table for K2V items, causal contexts - [x] Indexing mechanism and table for K2V index - [x] Make API handlers a bit more generic - [x] K2V API endpoint - [x] K2V API router - [x] ReadItem - [x] InsertItem - [x] DeleteItem - [x] PollItem - [x] ReadIndex - [x] InsertBatch - [x] ReadBatch - [x] DeleteBatch **Testing:** - [x] Just a simple Python script that does some requests to check visually that things are going right (does not contain parsing of results or assertions on returned values) - [x] Actual tests: - [x] Adapt testing framework - [x] Simple test with InsertItem + ReadItem - [x] Test with several Insert/Read/DeleteItem + ReadIndex - [x] Test all combinations of return formats for ReadItem - [x] Test with ReadBatch, InsertBatch, DeleteBatch - [x] Test with PollItem - [x] Test error codes - [ ] Fix most broken stuff - [x] test PollItem broken randomly - [x] when invalid causality tokens are given, errors should be 4xx not 5xx **Improvements:** - [x] Descending range queries - [x] Specify - [x] Implement - [x] Add test - [x] Batch updates to index counter - [x] Put K2V behind `k2v` feature flag Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/293 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-05-10 11:16:57 +00:00
/// Configuration for K2V api
#[derive(Deserialize, Debug, Clone)]
pub struct K2VApiConfig {
/// Address and port to bind for api serving
pub api_bind_addr: SocketAddr,
}
2021-03-20 19:38:44 +00:00
/// Configuration for serving files as normal web server
2020-10-31 16:28:56 +00:00
#[derive(Deserialize, Debug, Clone)]
pub struct WebConfig {
/// Address and port to bind for web serving
2020-11-10 08:57:07 +00:00
pub bind_addr: SocketAddr,
/// Suffix to remove from domain name to find bucket
2020-11-10 08:57:07 +00:00
pub root_domain: String,
2020-10-31 16:28:56 +00:00
}
/// Configuration for the admin and monitoring HTTP API
2022-03-10 09:51:40 +00:00
#[derive(Deserialize, Debug, Clone, Default)]
pub struct AdminConfig {
/// Address and port to bind for admin API serving
2022-03-10 09:51:40 +00:00
pub api_bind_addr: Option<SocketAddr>,
First version of admin API (#298) **Spec:** - [x] Start writing - [x] Specify all layout endpoints - [x] Specify all endpoints for operations on keys - [x] Specify all endpoints for operations on key/bucket permissions - [x] Specify all endpoints for operations on buckets - [x] Specify all endpoints for operations on bucket aliases View rendered spec at <https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/admin-api/doc/drafts/admin-api.md> **Code:** - [x] Refactor code for admin api to use common api code that was created for K2V **General endpoints:** - [x] Metrics - [x] GetClusterStatus - [x] ConnectClusterNodes - [x] GetClusterLayout - [x] UpdateClusterLayout - [x] ApplyClusterLayout - [x] RevertClusterLayout **Key-related endpoints:** - [x] ListKeys - [x] CreateKey - [x] ImportKey - [x] GetKeyInfo - [x] UpdateKey - [x] DeleteKey **Bucket-related endpoints:** - [x] ListBuckets - [x] CreateBucket - [x] GetBucketInfo - [x] DeleteBucket - [x] PutBucketWebsite - [x] DeleteBucketWebsite **Operations on key/bucket permissions:** - [x] BucketAllowKey - [x] BucketDenyKey **Operations on bucket aliases:** - [x] GlobalAliasBucket - [x] GlobalUnaliasBucket - [x] LocalAliasBucket - [x] LocalUnaliasBucket **And also:** - [x] Separate error type for the admin API (this PR includes a quite big refactoring of error handling) - [x] Add management of website access - [ ] Check that nothing is missing wrt what can be done using the CLI - [ ] Improve formatting of the spec - [x] Make sure everyone is cool with the API design Fix #231 Fix #295 Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/298 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-05-24 10:16:39 +00:00
/// Bearer token to use to scrape metrics
pub metrics_token: Option<String>,
/// Bearer token to use to access Admin API endpoints
pub admin_token: Option<String>,
/// OTLP server to where to export traces
pub trace_sink: Option<String>,
}
Abstract database behind generic interface and implement alternative drivers (#322) - [x] Design interface - [x] Implement Sled backend - [x] Re-implement the SledCountedTree hack ~~on Sled backend~~ on all backends (i.e. over the abstraction) - [x] Convert Garage code to use generic interface - [x] Proof-read converted Garage code - [ ] Test everything well - [x] Implement sqlite backend - [x] Implement LMDB backend - [ ] (Implement Persy backend?) - [ ] (Implement other backends? (like RocksDB, ...)) - [x] Implement backend choice in config file and garage server module - [x] Add CLI for converting between DB formats - Exploit the new interface to put more things in transactions - [x] `.updated()` trigger on Garage tables Fix #284 **Bugs** - [x] When exporting sqlite, trees iterate empty?? - [x] LMDB doesn't work **Known issues for various back-ends** - Sled: - Eats all my RAM and also all my disk space - `.len()` has to traverse the whole table - Is actually quite slow on some operations - And is actually pretty bad code... - Sqlite: - Requires a lock to be taken on all operations. The lock is also taken when iterating on a table with `.iter()`, and the lock isn't released until the iterator is dropped. This means that we must be VERY carefull to not do anything else inside a `.iter()` loop or else we will have a deadlock! Most such cases have been eliminated from the Garage codebase, but there might still be some that remain. If your Garage-over-Sqlite seems to hang/freeze, this is the reason. - (adapter uses a bunch of unsafe code) - Heed (LMDB): - Not suited for 32-bit machines as it has to map the whole DB in memory. - (adpater uses a tiny bit of unsafe code) **My recommendation:** avoid 32-bit machines and use LMDB as much as possible. **Converting databases** is actually quite easy. For example from Sled to LMDB: ```bash cd src/db cargo run --features cli --bin convert -- -i path/to/garage/meta/db -a sled -o path/to/garage/meta/db.lmdb -b lmdb ``` Then, just add this to your `config.toml`: ```toml db_engine = "lmdb" ``` Co-authored-by: Alex Auvolat <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/322 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-06-08 08:01:44 +00:00
fn default_db_engine() -> String {
"sled".into()
}
fn default_sled_cache_capacity() -> u64 {
128 * 1024 * 1024
}
fn default_sled_flush_every_ms() -> u64 {
2000
}
2020-04-23 17:05:46 +00:00
fn default_block_size() -> usize {
1048576
}
2021-03-20 19:38:44 +00:00
/// Read and parse configuration
2020-04-23 17:05:46 +00:00
pub fn read_config(config_file: PathBuf) -> Result<Config, Error> {
let mut file = std::fs::OpenOptions::new()
.read(true)
.open(config_file.as_path())?;
let mut config = String::new();
file.read_to_string(&mut config)?;
Ok(toml::from_str(&config)?)
}
2021-10-14 09:50:12 +00:00
fn deserialize_vec_addr<'de, D>(deserializer: D) -> Result<Vec<(NodeID, SocketAddr)>, D::Error>
where
D: de::Deserializer<'de>,
{
2021-10-14 09:50:12 +00:00
let mut ret = vec![];
for peer in <Vec<&str>>::deserialize(deserializer)? {
let (pubkey, addrs) = parse_and_resolve_peer_addr(peer).ok_or_else(|| {
D::Error::custom(format!("Unable to parse or resolve peer: {}", peer))
})?;
for ip in addrs {
ret.push((pubkey, ip));
2021-10-14 09:50:12 +00:00
}
}
Ok(ret)
}
fn default_compression() -> Option<i32> {
Some(1)
}
fn deserialize_compression<'de, D>(deserializer: D) -> Result<Option<i32>, D::Error>
where
D: de::Deserializer<'de>,
{
use std::convert::TryFrom;
struct OptionVisitor;
impl<'de> serde::de::Visitor<'de> for OptionVisitor {
type Value = Option<i32>;
fn expecting(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
formatter.write_str("int or 'none'")
}
fn visit_str<E>(self, value: &str) -> Result<Self::Value, E>
where
E: de::Error,
{
if value.eq_ignore_ascii_case("none") {
Ok(None)
} else {
Err(E::custom(format!(
"Invalid compression level: '{}', should be a number, or 'none'",
value
)))
}
}
fn visit_i64<E>(self, v: i64) -> Result<Self::Value, E>
where
E: de::Error,
{
i32::try_from(v)
.map(Some)
.map_err(|_| E::custom("Compression level out of bound".to_owned()))
}
fn visit_u64<E>(self, v: u64) -> Result<Self::Value, E>
where
E: de::Error,
{
i32::try_from(v)
.map(Some)
.map_err(|_| E::custom("Compression level out of bound".to_owned()))
}
}
deserializer.deserialize_any(OptionVisitor)
}