Add a metastore read replica role for read-only routing

config/quickwit.yaml

@@ -115,6 +115,13 @@ version: 0.8
 # metastore_uri: s3://your-bucket/indexes
 # metastore_uri: postgres://username:password@host:port/db
 #
+# Optional PostgreSQL read replica URI. Nodes started with the
+# `metastore_read_replica` service connect to it over a read-only connection and
+# serve stale-tolerant read-only metastore requests. Searchers use those nodes
+# only when `searcher.use_metastore_read_replica` is enabled. Defaults to unset.
+#
+# metastore_read_replica_uri: postgres://username:password@read-replica-host:port/db
+#
 # When using a file-backed metastore, the state of the metastore will be cached forever.
 # If you are indexing and searching from different processes, it is possible to periodically
 # refresh the state of the metastore on the searcher using the `polling_interval` hashtag.
@@ -180,6 +187,11 @@ indexer:
 # https://quickwit.io/docs/configuration/node-config#searcher-configuration
 #
 # searcher:
+#   # If true, routes read-only metastore requests from searchers, including
+#   # DataFusion when enabled, to nodes running the `metastore_read_replica`
+#   # service. Searchers require at least one `metastore_read_replica` node at
+#   # startup and do not fall back to the primary metastore.
+#   use_metastore_read_replica: false
 #   fast_field_cache_capacity: 1G
 #   split_footer_cache_capacity: 500M
 #   partial_request_cache_capacity: 64M

docs/configuration/node-config.md

@@ -22,14 +22,15 @@ A commented example is available here: [quickwit.yaml](https://github.com/quickw
 | `version` | Config file version. `0.7` is the only available value with a retro compatibility on `0.5` and `0.4`. | | |
 | `cluster_id` | Unique identifier of the cluster the node will be joining. Clusters sharing the same network should use distinct cluster IDs.| `QW_CLUSTER_ID` | `quickwit-default-cluster` |
 | `node_id` | Unique identifier of the node. It must be distinct from the node IDs of its cluster peers. Defaults to the instance's short hostname if not set. | `QW_NODE_ID` | short hostname |
-| `enabled_services` | Enabled services (control_plane, indexer, janitor, metastore, searcher) | `QW_ENABLED_SERVICES` | all services |
+| `enabled_services` | Enabled services (control_plane, indexer, janitor, metastore, metastore_read_replica, searcher) | `QW_ENABLED_SERVICES` | all services except metastore_read_replica |
 | `listen_address` | The IP address or hostname that Quickwit service binds to for starting REST and GRPC server and connecting this node to other nodes. By default, Quickwit binds itself to 127.0.0.1 (localhost). This default is not valid when trying to form a cluster. | `QW_LISTEN_ADDRESS` | `127.0.0.1` |
 | `advertise_address` | IP address advertised by the node, i.e. the IP address that peer nodes should use to connect to the node for RPCs. | `QW_ADVERTISE_ADDRESS` | `listen_address` |
 | `gossip_listen_port` | The port which to listen for the Gossip cluster membership service (UDP). | `QW_GOSSIP_LISTEN_PORT` | `rest.listen_port` |
 | `grpc_listen_port` | The port on which gRPC services listen for traffic. | `QW_GRPC_LISTEN_PORT` | `rest.listen_port + 1` |
 | `peer_seeds` | List of IP addresses or hostnames used to bootstrap the cluster and discover the complete set of nodes. This list may contain the current node address and does not need to be exhaustive. If the list of peer seeds contains a host name, Quickwit will resolve it by querying the DNS every minute. On kubernetes for instance, it is a good practise to set it to a [headless service](https://kubernetes.io/docs/concepts/services-networking/service/#headless-services). | `QW_PEER_SEEDS` | |
 | `data_dir` | Path to directory where data (tmp data, splits kept for caching purpose) is persisted. This is mostly used in indexing. | `QW_DATA_DIR` | `./qwdata` |
 | `metastore_uri` | Metastore URI. Can be a local directory or `s3://my-bucket/indexes` or `postgres://username:password@localhost:5432/metastore`. [Learn more about the metastore configuration](metastore-config.md). | `QW_METASTORE_URI` | `{data_dir}/indexes` |
+| `metastore_read_replica_uri` | Optional PostgreSQL read replica URI. Nodes running the `metastore_read_replica` service connect to it over a read-only connection and serve stale-tolerant read-only metastore requests. Searchers use those nodes only when `searcher.use_metastore_read_replica` is enabled. | `QW_METASTORE_READ_REPLICA_URI` | |
 | `default_index_root_uri` | Default index root URI that defines the location where index data (splits) is stored. The index URI is built following the scheme: `{default_index_root_uri}/{index-id}` | `QW_DEFAULT_INDEX_ROOT_URI` | `{data_dir}/indexes` |
 | environment variable only | Log level of Quickwit. Can be a direct log level, or a comma separated list of `module_name=level` | `RUST_LOG` | `info` |
 
@@ -285,6 +286,7 @@ This section contains the configuration options for a Searcher.
 | `max_num_concurrent_split_searches` | Maximum number of concurrent split search requests running on a Searcher. | `100` |
 | `split_cache` | Searcher split cache configuration options defined in the section below. Cache disabled if unspecified. | |
 | `request_timeout_secs` | The time before a search request is cancelled. This should match the timeout of the stack calling into quickwit if there is one set.  | `30` |
+| `use_metastore_read_replica` | If true, routes read-only metastore requests from searchers, including DataFusion when enabled, to nodes running the `metastore_read_replica` service. Searchers require at least one `metastore_read_replica` node at startup and do not fall back to the primary metastore. | `false` |
 
 ### Searcher split cache configuration
 
@@ -301,6 +303,7 @@ Example:
 
 ```yaml
 searcher:
+  use_metastore_read_replica: false
   fast_field_cache_capacity: 1G
   split_footer_cache_capacity: 500M
   partial_request_cache_capacity: 64M

quickwit/quickwit-cli/src/service.rs

@@ -34,10 +34,10 @@ use crate::{config_cli_arg, get_resolvers, load_node_config, start_actor_runtime
 pub fn build_run_command() -> Command {
     Command::new("run")
         .about("Starts a Quickwit node.")
-        .long_about("Starts a Quickwit node with all services enabled by default: `indexer`, `searcher`, `metastore`, `control-plane`, and `janitor`.")
+        .long_about("Starts a Quickwit node with the default services enabled: `indexer`, `searcher`, `metastore`, `control-plane`, and `janitor`.")
         .arg(config_cli_arg())
         .args(&[
-            arg!(--"service" <SERVICE> "Services (`indexer`, `searcher`, `metastore`, `control-plane`, or `janitor`) to run. If unspecified, all the supported services are started.")
+            arg!(--"service" <SERVICE> "Services (`indexer`, `searcher`, `metastore`, `metastore-read-replica`, `control-plane`, or `janitor`) to run. If unspecified, services from the config are used.")
                 .action(ArgAction::Append)
                 .required(false),
         ])

quickwit/quickwit-cli/tests/helpers.rs

@@ -157,7 +157,7 @@ impl TestEnv {
     pub async fn start_server(&self) -> anyhow::Result<()> {
         let run_command = RunCliCommand {
             config_uri: self.resource_files.config.clone(),
-            services: Some(QuickwitService::supported_services()),
+            services: Some(QuickwitService::default_services()),
         };
         let server_handle = tokio::spawn(async move {
             if let Err(error) = run_command

quickwit/quickwit-config/Cargo.toml

@@ -46,5 +46,5 @@ quickwit-proto = { workspace = true, features = ["testsuite"] }
 
 [features]
 metrics = []
-testsuite = []
+testsuite = ["quickwit-proto/testsuite"]
 vrl = ["dep:vrl"]

quickwit/quickwit-config/resources/tests/node_config/quickwit.json

@@ -18,6 +18,7 @@
     ],
     "data_dir": "/opt/quickwit/data",
     "metastore_uri": "postgres://username:password@host:port/db",
+    "metastore_read_replica_uri": "postgres://username:replica-password@replica-host:port/db",
     "default_index_root_uri": "s3://quickwit-indexes",
     "rest": {
         "listen_port": 1111,
@@ -81,6 +82,7 @@
         "replication_factor": 2
     },
     "searcher": {
+        "use_metastore_read_replica": true,
         "aggregation_memory_limit": "1G",
         "aggregation_bucket_limit": 500000,
         "fast_field_cache_capacity": "10G",

quickwit/quickwit-config/resources/tests/node_config/quickwit.toml

@@ -11,6 +11,7 @@ grpc_listen_port = 3333
 peer_seeds = [ "quickwit-searcher-0.local", "quickwit-searcher-1.local" ]
 data_dir = "/opt/quickwit/data"
 metastore_uri = "postgres://username:password@host:port/db"
+metastore_read_replica_uri = "postgres://username:replica-password@replica-host:port/db"
 default_index_root_uri = "s3://quickwit-indexes"
 
 [rest]
@@ -71,6 +72,7 @@ parquet_merge_use_streaming_engine = true
 replication_factor = 2
 
 [searcher]
+use_metastore_read_replica = true
 aggregation_memory_limit = "1G"
 aggregation_bucket_limit = 500_000
 fast_field_cache_capacity = "10G"

quickwit/quickwit-config/resources/tests/node_config/quickwit.yaml

@@ -15,6 +15,7 @@ peer_seeds:
   - quickwit-searcher-1.local
 data_dir: /opt/quickwit/data
 metastore_uri: postgres://username:password@host:port/db
+metastore_read_replica_uri: postgres://username:replica-password@replica-host:port/db
 default_index_root_uri: s3://quickwit-indexes
 
 rest:
@@ -73,6 +74,7 @@ ingest_api:
   replication_factor: 2
 
 searcher:
+  use_metastore_read_replica: true
   aggregation_memory_limit: 1G
   aggregation_bucket_limit: 500000
   fast_field_cache_capacity: 10G

quickwit/quickwit-config/src/node_config/mod.rs

@@ -419,6 +419,10 @@ pub struct SearcherConfig {
     #[serde(default)]
     #[serde(skip_serializing_if = "Option::is_none")]
     pub storage_timeout_policy: Option<StorageTimeoutPolicy>,
+    /// Routes read-only metastore requests from searchers, including DataFusion when enabled, to
+    /// nodes running the `metastore_read_replica` service.
+    #[serde(default)]
+    pub use_metastore_read_replica: bool,
     pub warmup_memory_budget: ByteSize,
     pub warmup_single_split_initial_allocation: ByteSize,
     /// Lambda configuration for serverless leaf search execution.
@@ -642,6 +646,7 @@ impl Default for SearcherConfig {
             request_timeout_secs: Self::default_request_timeout_secs(),
             leaf_request_timeout_secs: Self::default_request_timeout_secs(),
             storage_timeout_policy: None,
+            use_metastore_read_replica: false,
             warmup_memory_budget: ByteSize::gb(100),
             warmup_single_split_initial_allocation: ByteSize::mb(300),
             lambda: None,
@@ -888,6 +893,10 @@ pub struct NodeConfig {
     pub peer_seeds: Vec<String>,
     pub data_dir_path: PathBuf,
     pub metastore_uri: Uri,
+    /// Optional PostgreSQL read replica URI. It is used as the connection URI by nodes running the
+    /// [`QuickwitService::MetastoreReadReplica`] role.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub metastore_read_replica_uri: Option<Uri>,
     pub default_index_root_uri: Uri,
     pub rest_config: RestConfig,
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -951,6 +960,9 @@ impl NodeConfig {
     pub fn redact(&mut self) {
         self.metastore_configs.redact();
         self.metastore_uri.redact();
+        if let Some(metastore_read_replica_uri) = &mut self.metastore_read_replica_uri {
+            metastore_read_replica_uri.redact();
+        }
         self.storage_configs.redact();
     }
 
@@ -983,6 +995,26 @@ mod tests {
     use super::*;
     use crate::IndexerConfig;
 
+    #[test]
+    fn test_node_config_redact_metastore_uris() {
+        let mut config = NodeConfig::for_test();
+        config.metastore_uri = Uri::for_test("postgresql://username:password@host:5432/db");
+        config.metastore_read_replica_uri = Some(Uri::for_test(
+            "postgresql://replica-user:replica-password@replica-host:5432/db",
+        ));
+
+        config.redact();
+
+        assert_eq!(
+            config.metastore_uri,
+            "postgresql://username:***redacted***@host:5432/db"
+        );
+        assert_eq!(
+            config.metastore_read_replica_uri.unwrap(),
+            "postgresql://replica-user:***redacted***@replica-host:5432/db"
+        );
+    }
+
     #[test]
     fn test_indexer_config_serialization() {
         {