Replace etcd with storage_broker.

This is the replacement itself, the binary landed earlier. See
docs/storage_broker.md.

ref
https://github.com/neondatabase/neon/pull/2466
https://github.com/neondatabase/neon/issues/2394

control_plane/Cargo.toml

@@ -25,5 +25,7 @@ url = "2.2.2"
 pageserver_api = { path = "../libs/pageserver_api" }
 postgres_connection = { path = "../libs/postgres_connection" }
 safekeeper_api = { path = "../libs/safekeeper_api" }
+# Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
+storage_broker = { version = "0.1", path = "../storage_broker" }
 utils = { path = "../libs/utils" }
 workspace_hack = { version = "0.1", path = "../workspace_hack" }

control_plane/simple.conf

@@ -10,5 +10,5 @@ id = 1
 pg_port = 5454
 http_port = 7676
 
-[etcd_broker]
-broker_endpoints = ['http://127.0.0.1:2379']
+[broker]
+listen_addr = '127.0.0.1:50051'

control_plane/src/bin/neon_local.rs

@@ -8,10 +8,10 @@
 use anyhow::{anyhow, bail, Context, Result};
 use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
 use control_plane::compute::ComputeControlPlane;
-use control_plane::local_env::{EtcdBroker, LocalEnv};
+use control_plane::local_env::LocalEnv;
 use control_plane::pageserver::PageServerNode;
 use control_plane::safekeeper::SafekeeperNode;
-use control_plane::{etcd, local_env};
+use control_plane::{broker, local_env};
 use pageserver_api::models::TimelineInfo;
 use pageserver_api::{
     DEFAULT_HTTP_LISTEN_ADDR as DEFAULT_PAGESERVER_HTTP_ADDR,
@@ -22,9 +22,10 @@ use safekeeper_api::{
     DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
 };
 use std::collections::{BTreeSet, HashMap};
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
 use std::process::exit;
 use std::str::FromStr;
+use storage_broker::DEFAULT_LISTEN_ADDR as DEFAULT_BROKER_ADDR;
 use utils::{
     auth::{Claims, Scope},
     id::{NodeId, TenantId, TenantTimelineId, TimelineId},
@@ -41,13 +42,12 @@ project_git_version!(GIT_VERSION);
 
 const DEFAULT_PG_VERSION: &str = "14";
 
-fn default_conf(etcd_binary_path: &Path) -> String {
+fn default_conf() -> String {
     format!(
         r#"
 # Default built-in configuration, defined in main.rs
-[etcd_broker]
-broker_endpoints = ['http://localhost:2379']
-etcd_binary_path = '{etcd_binary_path}'
+[broker]
+listen_addr = '{DEFAULT_BROKER_ADDR}'
 
 [pageserver]
 id = {DEFAULT_PAGESERVER_ID}
@@ -60,7 +60,6 @@ id = {DEFAULT_SAFEKEEPER_ID}
 pg_port = {DEFAULT_SAFEKEEPER_PG_PORT}
 http_port = {DEFAULT_SAFEKEEPER_HTTP_PORT}
 "#,
-        etcd_binary_path = etcd_binary_path.display(),
         pageserver_auth_type = AuthType::Trust,
     )
 }
@@ -298,7 +297,7 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
         })?
     } else {
         // Built-in default config
-        default_conf(&EtcdBroker::locate_etcd()?)
+        default_conf()
     };
 
     let pg_version = init_match
@@ -807,14 +806,14 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
 }
 
 fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    etcd::start_etcd_process(env)?;
+    broker::start_broker_process(env)?;
     let pageserver = PageServerNode::from_env(env);
 
     // Postgres nodes are not started automatically
 
     if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
         eprintln!("pageserver start failed: {e}");
-        try_stop_etcd_process(env);
+        try_stop_storage_broker_process(env);
         exit(1);
     }
 
@@ -822,7 +821,7 @@ fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.start() {
             eprintln!("safekeeper '{}' start failed: {e}", safekeeper.id);
-            try_stop_etcd_process(env);
+            try_stop_storage_broker_process(env);
             exit(1);
         }
     }
@@ -854,14 +853,14 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
         }
     }
 
-    try_stop_etcd_process(env);
+    try_stop_storage_broker_process(env);
 
     Ok(())
 }
 
-fn try_stop_etcd_process(env: &local_env::LocalEnv) {
-    if let Err(e) = etcd::stop_etcd_process(env) {
-        eprintln!("etcd stop failed: {e}");
+fn try_stop_storage_broker_process(env: &local_env::LocalEnv) {
+    if let Err(e) = broker::stop_broker_process(env) {
+        eprintln!("neon broker stop failed: {e}");
     }
 }
 

control_plane/src/broker.rs

@@ -0,0 +1,48 @@
+use anyhow::Context;
+
+use std::path::PathBuf;
+
+use crate::{background_process, local_env};
+
+pub fn start_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    let broker = &env.broker;
+    let listen_addr = &broker.listen_addr;
+
+    print!("Starting neon broker at {}", listen_addr);
+
+    let args = [format!("--listen-addr={listen_addr}")];
+
+    let client = reqwest::blocking::Client::new();
+    background_process::start_process(
+        "storage_broker",
+        &env.base_data_dir,
+        &env.storage_broker_bin(),
+        &args,
+        [],
+        background_process::InitialPidFile::Create(&storage_broker_pid_file_path(env)),
+        || {
+            let url = broker.client_url();
+            let status_url = url.join("status").with_context(|| {
+                format!("Failed to append /status path to broker endpoint {url}",)
+            })?;
+            let request = client
+                .get(status_url)
+                .build()
+                .with_context(|| format!("Failed to construct request to broker endpoint {url}"))?;
+            match client.execute(request) {
+                Ok(resp) => Ok(resp.status().is_success()),
+                Err(_) => Ok(false),
+            }
+        },
+    )
+    .context("Failed to spawn storage_broker subprocess")?;
+    Ok(())
+}
+
+pub fn stop_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    background_process::stop_process(true, "storage_broker", &storage_broker_pid_file_path(env))
+}
+
+fn storage_broker_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
+    env.base_data_dir.join("storage_broker.pid")
+}

control_plane/src/etcd.rs

@@ -1,78 +0,0 @@
-use std::{fs, path::PathBuf};
-
-use anyhow::Context;
-
-use crate::{background_process, local_env};
-
-pub fn start_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    let etcd_broker = &env.etcd_broker;
-    print!(
-        "Starting etcd broker using {:?}",
-        etcd_broker.etcd_binary_path
-    );
-
-    let etcd_data_dir = env.base_data_dir.join("etcd");
-    fs::create_dir_all(&etcd_data_dir)
-        .with_context(|| format!("Failed to create etcd data dir {etcd_data_dir:?}"))?;
-
-    let client_urls = etcd_broker.comma_separated_endpoints();
-    let args = [
-        format!("--data-dir={}", etcd_data_dir.display()),
-        format!("--listen-client-urls={client_urls}"),
-        format!("--advertise-client-urls={client_urls}"),
-        // Set --quota-backend-bytes to keep the etcd virtual memory
-        // size smaller. Our test etcd clusters are very small.
-        // See https://github.com/etcd-io/etcd/issues/7910
-        "--quota-backend-bytes=100000000".to_string(),
-        // etcd doesn't compact (vacuum) with default settings,
-        // enable it to prevent space exhaustion.
-        "--auto-compaction-mode=revision".to_string(),
-        "--auto-compaction-retention=1".to_string(),
-    ];
-
-    let pid_file_path = etcd_pid_file_path(env);
-
-    let client = reqwest::blocking::Client::new();
-
-    background_process::start_process(
-        "etcd",
-        &etcd_data_dir,
-        &etcd_broker.etcd_binary_path,
-        &args,
-        [],
-        background_process::InitialPidFile::Create(&pid_file_path),
-        || {
-            for broker_endpoint in &etcd_broker.broker_endpoints {
-                let request = broker_endpoint
-                    .join("health")
-                    .with_context(|| {
-                        format!(
-                            "Failed to append /health path to broker endopint {}",
-                            broker_endpoint
-                        )
-                    })
-                    .and_then(|url| {
-                        client.get(&url.to_string()).build().with_context(|| {
-                            format!("Failed to construct request to etcd endpoint {url}")
-                        })
-                    })?;
-                if client.execute(request).is_ok() {
-                    return Ok(true);
-                }
-            }
-
-            Ok(false)
-        },
-    )
-    .context("Failed to spawn etcd subprocess")?;
-
-    Ok(())
-}
-
-pub fn stop_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    background_process::stop_process(true, "etcd", &etcd_pid_file_path(env))
-}
-
-fn etcd_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
-    env.base_data_dir.join("etcd.pid")
-}

control_plane/src/lib.rs

@@ -8,8 +8,8 @@
 //
 
 mod background_process;
+pub mod broker;
 pub mod compute;
-pub mod etcd;
 pub mod local_env;
 pub mod pageserver;
 pub mod postgresql_conf;

control_plane/src/local_env.rs

@@ -4,12 +4,16 @@
 //! script which will use local paths.
 
 use anyhow::{bail, ensure, Context};
+
 use reqwest::Url;
 use serde::{Deserialize, Serialize};
 use serde_with::{serde_as, DisplayFromStr};
 use std::collections::HashMap;
 use std::env;
 use std::fs;
+use std::net::IpAddr;
+use std::net::Ipv4Addr;
+use std::net::SocketAddr;
 use std::path::{Path, PathBuf};
 use std::process::{Command, Stdio};
 use utils::{
@@ -62,7 +66,7 @@ pub struct LocalEnv {
     #[serde(default)]
     pub private_key_path: PathBuf,
 
-    pub etcd_broker: EtcdBroker,
+    pub broker: NeonBroker,
 
     pub pageserver: PageServerConf,
 
@@ -78,67 +82,26 @@ pub struct LocalEnv {
     branch_name_mappings: HashMap<String, Vec<(TenantId, TimelineId)>>,
 }
 
-/// Etcd broker config for cluster internal communication.
-#[serde_as]
+/// Broker config for cluster internal communication.
 #[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
-pub struct EtcdBroker {
-    /// A prefix to all to any key when pushing/polling etcd from a node.
-    #[serde(default)]
-    pub broker_etcd_prefix: Option<String>,
-
-    /// Broker (etcd) endpoints for storage nodes coordination, e.g. 'http://127.0.0.1:2379'.
-    #[serde(default)]
-    #[serde_as(as = "Vec<DisplayFromStr>")]
-    pub broker_endpoints: Vec<Url>,
-
-    /// Etcd binary path to use.
-    #[serde(default)]
-    pub etcd_binary_path: PathBuf,
+#[serde(default)]
+pub struct NeonBroker {
+    /// Broker listen address for storage nodes coordination, e.g. '127.0.0.1:50051'.
+    pub listen_addr: SocketAddr,
 }
 
-impl EtcdBroker {
-    pub fn locate_etcd() -> anyhow::Result<PathBuf> {
-        let which_output = Command::new("which")
-            .arg("etcd")
-            .output()
-            .context("Failed to run 'which etcd' command")?;
-        let stdout = String::from_utf8_lossy(&which_output.stdout);
-        ensure!(
-            which_output.status.success(),
-            "'which etcd' invocation failed. Status: {}, stdout: {stdout}, stderr: {}",
-            which_output.status,
-            String::from_utf8_lossy(&which_output.stderr)
-        );
-
-        let etcd_path = PathBuf::from(stdout.trim());
-        ensure!(
-            etcd_path.is_file(),
-            "'which etcd' invocation was successful, but the path it returned is not a file or does not exist: {}",
-            etcd_path.display()
-        );
-
-        Ok(etcd_path)
+// Dummy Default impl to satisfy Deserialize derive.
+impl Default for NeonBroker {
+    fn default() -> Self {
+        NeonBroker {
+            listen_addr: SocketAddr::new(IpAddr::V4(Ipv4Addr::new(0, 0, 0, 0)), 0),
+        }
     }
+}
 
-    pub fn comma_separated_endpoints(&self) -> String {
-        self.broker_endpoints
-            .iter()
-            .map(|url| {
-                // URL by default adds a '/' path at the end, which is not what etcd CLI wants.
-                let url_string = url.as_str();
-                if url_string.ends_with('/') {
-                    &url_string[0..url_string.len() - 1]
-                } else {
-                    url_string
-                }
-            })
-            .fold(String::new(), |mut comma_separated_urls, url| {
-                if !comma_separated_urls.is_empty() {
-                    comma_separated_urls.push(',');
-                }
-                comma_separated_urls.push_str(url);
-                comma_separated_urls
-            })
+impl NeonBroker {
+    pub fn client_url(&self) -> Url {
+        Url::parse(&format!("http://{}", self.listen_addr)).expect("failed to construct url")
     }
 }
 
@@ -234,6 +197,10 @@ impl LocalEnv {
         self.neon_distrib_dir.join("safekeeper")
     }
 
+    pub fn storage_broker_bin(&self) -> PathBuf {
+        self.neon_distrib_dir.join("storage_broker")
+    }
+
     pub fn pg_data_dirs_path(&self) -> PathBuf {
         self.base_data_dir.join("pgdatadirs").join("tenants")
     }
@@ -511,8 +478,8 @@ mod tests {
             "failed to parse simple config {simple_conf_toml}, reason: {simple_conf_parse_result:?}"
         );
 
-        let string_to_replace = "broker_endpoints = ['http://127.0.0.1:2379']";
-        let spoiled_url_str = "broker_endpoints = ['!@$XOXO%^&']";
+        let string_to_replace = "listen_addr = '127.0.0.1:50051'";
+        let spoiled_url_str = "listen_addr = '!@$XOXO%^&'";
         let spoiled_url_toml = simple_conf_toml.replace(string_to_replace, spoiled_url_str);
         assert!(
             spoiled_url_toml.contains(spoiled_url_str),

control_plane/src/pageserver.rs

@@ -96,13 +96,8 @@ impl PageServerNode {
         }
     }
 
-    pub fn initialize(
-        &self,
-        create_tenant: Option<TenantId>,
-        initial_timeline_id: Option<TimelineId>,
-        config_overrides: &[&str],
-        pg_version: u32,
-    ) -> anyhow::Result<TimelineId> {
+    // pageserver conf overrides defined by neon_local configuration.
+    fn neon_local_overrides(&self) -> Vec<String> {
         let id = format!("id={}", self.env.pageserver.id);
         // FIXME: the paths should be shell-escaped to handle paths with spaces, quotas etc.
         let pg_distrib_dir_param = format!(
@@ -117,41 +112,32 @@ impl PageServerNode {
         );
         let listen_pg_addr_param =
             format!("listen_pg_addr='{}'", self.env.pageserver.listen_pg_addr);
-        let broker_endpoints_param = format!(
-            "broker_endpoints=[{}]",
-            self.env
-                .etcd_broker
-                .broker_endpoints
-                .iter()
-                .map(|url| format!("'{url}'"))
-                .collect::<Vec<_>>()
-                .join(",")
-        );
-        let broker_etcd_prefix_param = self
-            .env
-            .etcd_broker
-            .broker_etcd_prefix
-            .as_ref()
-            .map(|prefix| format!("broker_etcd_prefix='{prefix}'"));
+        let broker_endpoint_param = format!("broker_endpoint='{}'", self.env.broker.client_url());
 
-        let mut init_config_overrides = config_overrides.to_vec();
-        init_config_overrides.push(&id);
-        init_config_overrides.push(&pg_distrib_dir_param);
-        init_config_overrides.push(&authg_type_param);
-        init_config_overrides.push(&listen_http_addr_param);
-        init_config_overrides.push(&listen_pg_addr_param);
-        init_config_overrides.push(&broker_endpoints_param);
-
-        if let Some(broker_etcd_prefix_param) = broker_etcd_prefix_param.as_deref() {
-            init_config_overrides.push(broker_etcd_prefix_param);
-        }
+        let mut overrides = vec![
+            id,
+            pg_distrib_dir_param,
+            authg_type_param,
+            listen_http_addr_param,
+            listen_pg_addr_param,
+            broker_endpoint_param,
+        ];
 
         if self.env.pageserver.auth_type != AuthType::Trust {
-            init_config_overrides.push("auth_validation_public_key_path='auth_public_key.pem'");
+            overrides.push("auth_validation_public_key_path='auth_public_key.pem'".to_owned());
         }
+        overrides
+    }
 
+    pub fn initialize(
+        &self,
+        create_tenant: Option<TenantId>,
+        initial_timeline_id: Option<TimelineId>,
+        config_overrides: &[&str],
+        pg_version: u32,
+    ) -> anyhow::Result<TimelineId> {
         let mut pageserver_process = self
-            .start_node(&init_config_overrides, &self.env.base_data_dir, true)
+            .start_node(config_overrides, &self.env.base_data_dir, true)
             .with_context(|| {
                 format!(
                     "Failed to start a process for pageserver {}",
@@ -224,6 +210,9 @@ impl PageServerNode {
         datadir: &Path,
         update_config: bool,
     ) -> anyhow::Result<Child> {
+        let mut overrides = self.neon_local_overrides();
+        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
+
         print!(
             "Starting pageserver at '{}' in '{}'",
             self.pg_connection_config.raw_address(),
@@ -242,7 +231,7 @@ impl PageServerNode {
             args.push("--update-config");
         }
 
-        for config_override in config_overrides {
+        for config_override in &overrides {
             args.extend(["-c", config_override]);
         }
 

control_plane/src/safekeeper.rs

@@ -131,13 +131,8 @@ impl SafekeeperNode {
             args.push("--no-sync");
         }
 
-        let comma_separated_endpoints = self.env.etcd_broker.comma_separated_endpoints();
-        if !comma_separated_endpoints.is_empty() {
-            args.extend(["--broker-endpoints", &comma_separated_endpoints]);
-        }
-        if let Some(prefix) = self.env.etcd_broker.broker_etcd_prefix.as_deref() {
-            args.extend(["--broker-etcd-prefix", prefix]);
-        }
+        let broker_endpoint = format!("{}", self.env.broker.client_url());
+        args.extend(["--broker-endpoint", &broker_endpoint]);
 
         let mut backup_threads = String::new();
         if let Some(threads) = self.conf.backup_threads {