pageserver: implement aligned io buffer

Signed-off-by: Yuchen Liang <yuchen@neon.tech>

Cargo.lock

@@ -666,34 +666,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "axum"
-version = "0.6.20"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3b829e4e32b91e643de6eafe82b1d90675f5874230191a4ffbc1b336dec4d6bf"
-dependencies = [
- "async-trait",
- "axum-core 0.3.4",
- "bitflags 1.3.2",
- "bytes",
- "futures-util",
- "http 0.2.9",
- "http-body 0.4.5",
- "hyper 0.14.30",
- "itoa",
- "matchit 0.7.0",
- "memchr",
- "mime",
- "percent-encoding",
- "pin-project-lite",
- "rustversion",
- "serde",
- "sync_wrapper 0.1.2",
- "tower",
- "tower-layer",
- "tower-service",
-]
-
 [[package]]
 name = "axum"
 version = "0.7.5"
@@ -701,7 +673,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3a6c9af12842a67734c9a2e355436e5d03b22383ed60cf13cd0c18fbfe3dcbcf"
 dependencies = [
  "async-trait",
- "axum-core 0.4.5",
+ "axum-core",
  "base64 0.21.1",
  "bytes",
  "futures-util",
@@ -731,23 +703,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "axum-core"
-version = "0.3.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "759fa577a247914fd3f7f76d62972792636412fbfd634cd452f6a385a74d2d2c"
-dependencies = [
- "async-trait",
- "bytes",
- "futures-util",
- "http 0.2.9",
- "http-body 0.4.5",
- "mime",
- "rustversion",
- "tower-layer",
- "tower-service",
-]
-
 [[package]]
 name = "axum-core"
 version = "0.4.5"
@@ -971,7 +926,7 @@ dependencies = [
  "clang-sys",
  "itertools 0.12.1",
  "log",
- "prettyplease 0.2.17",
+ "prettyplease",
  "proc-macro2",
  "quote",
  "regex",
@@ -2454,15 +2409,6 @@ dependencies = [
  "digest",
 ]
 
-[[package]]
-name = "home"
-version = "0.5.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3d1354bf6b7235cb4a0576c2619fd4ed18183f689b12b006a0ee7329eeff9a5"
-dependencies = [
- "windows-sys 0.52.0",
-]
-
 [[package]]
 name = "hostname"
 version = "0.4.0"
@@ -2657,14 +2603,15 @@ dependencies = [
 
 [[package]]
 name = "hyper-timeout"
-version = "0.4.1"
+version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bbb958482e8c7be4bc3cf272a766a2b0bf1a6755e7a6ae777f017a31d11b13b1"
+checksum = "3203a961e5c83b6f5498933e78b6b263e208c197b63e9c6c53cc82ffd3f63793"
 dependencies = [
- "hyper 0.14.30",
+ "hyper 1.4.1",
+ "hyper-util",
  "pin-project-lite",
  "tokio",
- "tokio-io-timeout",
+ "tower-service",
 ]
 
 [[package]]
@@ -3470,7 +3417,7 @@ dependencies = [
  "opentelemetry-http",
  "opentelemetry-proto",
  "opentelemetry_sdk",
- "prost 0.13.3",
+ "prost",
  "reqwest 0.12.4",
  "thiserror",
 ]
@@ -3483,8 +3430,8 @@ checksum = "30ee9f20bff9c984511a02f082dc8ede839e4a9bf15cc2487c8d6fea5ad850d9"
 dependencies = [
  "opentelemetry",
  "opentelemetry_sdk",
- "prost 0.13.3",
- "tonic 0.12.3",
+ "prost",
+ "tonic",
 ]
 
 [[package]]
@@ -4178,16 +4125,6 @@ dependencies = [
  "tokio",
 ]
 
-[[package]]
-name = "prettyplease"
-version = "0.1.25"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c8646e95016a7a6c4adea95bafa8a16baab64b583356217f2c85db4a39d9a86"
-dependencies = [
- "proc-macro2",
- "syn 1.0.109",
-]
-
 [[package]]
 name = "prettyplease"
 version = "0.2.17"
@@ -4258,16 +4195,6 @@ dependencies = [
  "thiserror",
 ]
 
-[[package]]
-name = "prost"
-version = "0.11.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b82eaa1d779e9a4bc1c3217db8ffbeabaae1dca241bf70183242128d48681cd"
-dependencies = [
- "bytes",
- "prost-derive 0.11.9",
-]
-
 [[package]]
 name = "prost"
 version = "0.13.3"
@@ -4275,42 +4202,28 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7b0487d90e047de87f984913713b85c601c05609aad5b0df4b4573fbf69aa13f"
 dependencies = [
  "bytes",
- "prost-derive 0.13.3",
+ "prost-derive",
 ]
 
 [[package]]
 name = "prost-build"
-version = "0.11.9"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "119533552c9a7ffacc21e099c24a0ac8bb19c2a2a3f363de84cd9b844feab270"
+checksum = "0c1318b19085f08681016926435853bbf7858f9c082d0999b80550ff5d9abe15"
 dependencies = [
  "bytes",
- "heck 0.4.1",
- "itertools 0.10.5",
- "lazy_static",
+ "heck 0.5.0",
+ "itertools 0.12.1",
  "log",
  "multimap",
+ "once_cell",
  "petgraph",
- "prettyplease 0.1.25",
- "prost 0.11.9",
+ "prettyplease",
+ "prost",
  "prost-types",
  "regex",
- "syn 1.0.109",
+ "syn 2.0.52",
  "tempfile",
- "which",
-]
-
-[[package]]
-name = "prost-derive"
-version = "0.11.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5d2d8d10f3c6ded6da8b05b5fb3b8a5082514344d56c9f871412d29b4e075b4"
-dependencies = [
- "anyhow",
- "itertools 0.10.5",
- "proc-macro2",
- "quote",
- "syn 1.0.109",
 ]
 
 [[package]]
@@ -4328,11 +4241,11 @@ dependencies = [
 
 [[package]]
 name = "prost-types"
-version = "0.11.9"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "213622a1460818959ac1181aaeb2dc9c7f63df720db7d788b3e24eacd1983e13"
+checksum = "4759aa0d3a6232fb8dbdb97b61de2c20047c68aca932c7ed76da9d788508d670"
 dependencies = [
- "prost 0.11.9",
+ "prost",
 ]
 
 [[package]]
@@ -5094,6 +5007,21 @@ dependencies = [
  "zeroize",
 ]
 
+[[package]]
+name = "rustls"
+version = "0.23.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebbbdb961df0ad3f2652da8f3fdc4b36122f568f968f45ad3316f26c025c677b"
+dependencies = [
+ "log",
+ "once_cell",
+ "ring",
+ "rustls-pki-types",
+ "rustls-webpki 0.102.2",
+ "subtle",
+ "zeroize",
+]
+
 [[package]]
 name = "rustls-native-certs"
 version = "0.6.2"
@@ -5119,6 +5047,19 @@ dependencies = [
  "security-framework",
 ]
 
+[[package]]
+name = "rustls-native-certs"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fcaf18a4f2be7326cd874a5fa579fae794320a0f388d365dca7e480e55f83f8a"
+dependencies = [
+ "openssl-probe",
+ "rustls-pemfile 2.1.1",
+ "rustls-pki-types",
+ "schannel",
+ "security-framework",
+]
+
 [[package]]
 name = "rustls-pemfile"
 version = "1.0.2"
@@ -5194,6 +5135,7 @@ dependencies = [
  "fail",
  "futures",
  "hex",
+ "http 1.1.0",
  "humantime",
  "hyper 0.14.30",
  "metrics",
@@ -5750,19 +5692,22 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "async-stream",
+ "bytes",
  "clap",
  "const_format",
  "futures",
  "futures-core",
  "futures-util",
+ "http-body-util",
  "humantime",
- "hyper 0.14.30",
+ "hyper 1.4.1",
+ "hyper-util",
  "metrics",
  "once_cell",
  "parking_lot 0.12.1",
- "prost 0.11.9",
+ "prost",
  "tokio",
- "tonic 0.9.2",
+ "tonic",
  "tonic-build",
  "tracing",
  "utils",
@@ -6306,6 +6251,17 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "tokio-rustls"
+version = "0.26.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c7bc40d0e5a97695bb96e27995cd3a08538541b0a846f65bba7a359f36700d4"
+dependencies = [
+ "rustls 0.23.7",
+ "rustls-pki-types",
+ "tokio",
+]
+
 [[package]]
 name = "tokio-stream"
 version = "0.1.16"
@@ -6397,29 +6353,30 @@ dependencies = [
 
 [[package]]
 name = "tonic"
-version = "0.9.2"
+version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3082666a3a6433f7f511c7192923fa1fe07c69332d3c6a2e6bb040b569199d5a"
+checksum = "877c5b330756d856ffcc4553ab34a5684481ade925ecc54bcd1bf02b1d0d4d52"
 dependencies = [
  "async-stream",
  "async-trait",
- "axum 0.6.20",
- "base64 0.21.1",
+ "axum",
+ "base64 0.22.1",
  "bytes",
- "futures-core",
- "futures-util",
- "h2 0.3.26",
- "http 0.2.9",
- "http-body 0.4.5",
- "hyper 0.14.30",
+ "h2 0.4.4",
+ "http 1.1.0",
+ "http-body 1.0.0",
+ "http-body-util",
+ "hyper 1.4.1",
  "hyper-timeout",
+ "hyper-util",
  "percent-encoding",
  "pin-project",
- "prost 0.11.9",
- "rustls-native-certs 0.6.2",
- "rustls-pemfile 1.0.2",
+ "prost",
+ "rustls-native-certs 0.8.0",
+ "rustls-pemfile 2.1.1",
+ "socket2",
  "tokio",
- "tokio-rustls 0.24.0",
+ "tokio-rustls 0.26.0",
  "tokio-stream",
  "tower",
  "tower-layer",
@@ -6428,37 +6385,17 @@ dependencies = [
 ]
 
 [[package]]
-name = "tonic"
+name = "tonic-build"
 version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "877c5b330756d856ffcc4553ab34a5684481ade925ecc54bcd1bf02b1d0d4d52"
+checksum = "9557ce109ea773b399c9b9e5dca39294110b74f1f342cb347a80d1fce8c26a11"
 dependencies = [
- "async-trait",
- "base64 0.22.1",
- "bytes",
- "http 1.1.0",
- "http-body 1.0.0",
- "http-body-util",
- "percent-encoding",
- "pin-project",
- "prost 0.13.3",
- "tokio-stream",
- "tower-layer",
- "tower-service",
- "tracing",
-]
-
-[[package]]
-name = "tonic-build"
-version = "0.9.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6fdaae4c2c638bb70fe42803a26fbd6fc6ac8c72f5c59f67ecc2a2dcabf4b07"
-dependencies = [
- "prettyplease 0.1.25",
+ "prettyplease",
  "proc-macro2",
  "prost-build",
+ "prost-types",
  "quote",
- "syn 1.0.109",
+ "syn 2.0.52",
 ]
 
 [[package]]
@@ -6864,7 +6801,7 @@ name = "vm_monitor"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "axum 0.7.5",
+ "axum",
  "cgroups-rs",
  "clap",
  "futures",
@@ -7095,18 +7032,6 @@ dependencies = [
  "rustls-pki-types",
 ]
 
-[[package]]
-name = "which"
-version = "4.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "87ba24419a2078cd2b0f2ede2691b6c66d8e47836da3b6db8265ebad47afbfc7"
-dependencies = [
- "either",
- "home",
- "once_cell",
- "rustix",
-]
-
 [[package]]
 name = "whoami"
 version = "1.5.1"
@@ -7335,9 +7260,10 @@ version = "0.1.0"
 dependencies = [
  "ahash",
  "anyhow",
+ "axum",
+ "axum-core",
  "base64 0.21.1",
  "base64ct",
- "bitflags 2.4.1",
  "bytes",
  "camino",
  "cc",
@@ -7365,7 +7291,6 @@ dependencies = [
  "hyper 1.4.1",
  "hyper-util",
  "indexmap 1.9.3",
- "itertools 0.10.5",
  "itertools 0.12.1",
  "lazy_static",
  "libc",
@@ -7377,15 +7302,15 @@ dependencies = [
  "num-traits",
  "once_cell",
  "parquet",
+ "prettyplease",
  "proc-macro2",
- "prost 0.11.9",
+ "prost",
  "quote",
  "rand 0.8.5",
  "regex",
  "regex-automata 0.4.3",
  "regex-syntax 0.8.2",
  "reqwest 0.12.4",
- "rustls 0.21.11",
  "scopeguard",
  "serde",
  "serde_json",
@@ -7401,9 +7326,10 @@ dependencies = [
  "time",
  "time-macros",
  "tokio",
- "tokio-rustls 0.24.0",
+ "tokio-stream",
  "tokio-util",
  "toml_edit",
+ "tonic",
  "tower",
  "tracing",
  "tracing-core",

Cargo.toml

@@ -130,7 +130,7 @@ pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
 pin-project-lite = "0.2"
 procfs = "0.16"
 prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
-prost = "0.11"
+prost = "0.13"
 rand = "0.8"
 redis = { version = "0.25.2", features = ["tokio-rustls-comp", "keep-alive"] }
 regex = "1.10.2"
@@ -178,7 +178,7 @@ tokio-tar = "0.3"
 tokio-util = { version = "0.7.10", features = ["io", "rt"] }
 toml = "0.8"
 toml_edit = "0.22"
-tonic = {version = "0.9", features = ["tls", "tls-roots"]}
+tonic = {version = "0.12.3", features = ["tls", "tls-roots"]}
 tower-service = "0.3.2"
 tracing = "0.1"
 tracing-error = "0.2"
@@ -246,7 +246,7 @@ criterion = "0.5.1"
 rcgen = "0.12"
 rstest = "0.18"
 camino-tempfile = "1.0.2"
-tonic-build = "0.9"
+tonic-build = "0.12"
 
 [patch.crates-io]
 

compute_tools/src/bin/compute_ctl.rs

@@ -402,8 +402,7 @@ fn start_postgres(
 ) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
     // We got all we need, update the state.
     let mut state = compute.state.lock().unwrap();
-    state.status = ComputeStatus::Init;
-    compute.state_changed.notify_all();
+    state.set_status(ComputeStatus::Init, &compute.state_changed);
 
     info!(
         "running compute with features: {:?}",

compute_tools/src/compute.rs

@@ -109,6 +109,18 @@ impl ComputeState {
             metrics: ComputeMetrics::default(),
         }
     }
+
+    pub fn set_status(&mut self, status: ComputeStatus, state_changed: &Condvar) {
+        let prev = self.status;
+        info!("Changing compute status from {} to {}", prev, status);
+        self.status = status;
+        state_changed.notify_all();
+    }
+
+    pub fn set_failed_status(&mut self, err: anyhow::Error, state_changed: &Condvar) {
+        self.error = Some(format!("{err:?}"));
+        self.set_status(ComputeStatus::Failed, state_changed);
+    }
 }
 
 impl Default for ComputeState {
@@ -303,15 +315,12 @@ impl ComputeNode {
 
     pub fn set_status(&self, status: ComputeStatus) {
         let mut state = self.state.lock().unwrap();
-        state.status = status;
-        self.state_changed.notify_all();
+        state.set_status(status, &self.state_changed);
     }
 
     pub fn set_failed_status(&self, err: anyhow::Error) {
         let mut state = self.state.lock().unwrap();
-        state.error = Some(format!("{err:?}"));
-        state.status = ComputeStatus::Failed;
-        self.state_changed.notify_all();
+        state.set_failed_status(err, &self.state_changed);
     }
 
     pub fn get_status(&self) -> ComputeStatus {

compute_tools/src/configurator.rs

@@ -24,8 +24,7 @@ fn configurator_main_loop(compute: &Arc<ComputeNode>) {
         // Re-check the status after waking up
         if state.status == ComputeStatus::ConfigurationPending {
             info!("got configuration request");
-            state.status = ComputeStatus::Configuration;
-            compute.state_changed.notify_all();
+            state.set_status(ComputeStatus::Configuration, &compute.state_changed);
             drop(state);
 
             let mut new_status = ComputeStatus::Failed;

compute_tools/src/http/api.rs

@@ -288,8 +288,7 @@ async fn handle_configure_request(
                 return Err((msg, StatusCode::PRECONDITION_FAILED));
             }
             state.pspec = Some(parsed_spec);
-            state.status = ComputeStatus::ConfigurationPending;
-            compute.state_changed.notify_all();
+            state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
             drop(state);
             info!("set new spec and notified waiters");
         }
@@ -362,15 +361,15 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
         }
         if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
             let msg = format!(
-                "invalid compute status for termination request: {:?}",
-                state.status.clone()
+                "invalid compute status for termination request: {}",
+                state.status
             );
             return Err((msg, StatusCode::PRECONDITION_FAILED));
         }
-        state.status = ComputeStatus::TerminationPending;
-        compute.state_changed.notify_all();
+        state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
         drop(state);
     }
+
     forward_termination_signal();
     info!("sent signal and notified waiters");
 
@@ -384,7 +383,8 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
         while state.status != ComputeStatus::Terminated {
             state = c.state_changed.wait(state).unwrap();
             info!(
-                "waiting for compute to become Terminated, current status: {:?}",
+                "waiting for compute to become {}, current status: {:?}",
+                ComputeStatus::Terminated,
                 state.status
             );
         }

compute_tools/src/spec.rs

@@ -1,3 +1,4 @@
+use std::collections::HashSet;
 use std::fs::File;
 use std::path::Path;
 use std::str::FromStr;
@@ -189,6 +190,15 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let mut xact = client.transaction()?;
     let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
 
+    let mut jwks_roles = HashSet::new();
+    if let Some(local_proxy) = &spec.local_proxy_config {
+        for jwks_setting in local_proxy.jwks.iter().flatten() {
+            for role_name in &jwks_setting.role_names {
+                jwks_roles.insert(role_name.clone());
+            }
+        }
+    }
+
     // Print a list of existing Postgres roles (only in debug mode)
     if span_enabled!(Level::INFO) {
         let mut vec = Vec::new();
@@ -308,6 +318,9 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
                     "CREATE ROLE {} INHERIT CREATEROLE CREATEDB BYPASSRLS REPLICATION IN ROLE neon_superuser",
                     name.pg_quote()
                 );
+                if jwks_roles.contains(name.as_str()) {
+                    query = format!("CREATE ROLE {}", name.pg_quote());
+                }
                 info!("running role create query: '{}'", &query);
                 query.push_str(&role.to_pg_options());
                 xact.execute(query.as_str(), &[])?;

libs/compute_api/src/responses.rs

@@ -1,5 +1,7 @@
 //! Structs representing the JSON formats used in the compute_ctl's HTTP API.
 
+use std::fmt::Display;
+
 use chrono::{DateTime, Utc};
 use serde::{Deserialize, Serialize, Serializer};
 
@@ -58,6 +60,21 @@ pub enum ComputeStatus {
     Terminated,
 }
 
+impl Display for ComputeStatus {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            ComputeStatus::Empty => f.write_str("empty"),
+            ComputeStatus::ConfigurationPending => f.write_str("configuration-pending"),
+            ComputeStatus::Init => f.write_str("init"),
+            ComputeStatus::Running => f.write_str("running"),
+            ComputeStatus::Configuration => f.write_str("configuration"),
+            ComputeStatus::Failed => f.write_str("failed"),
+            ComputeStatus::TerminationPending => f.write_str("termination-pending"),
+            ComputeStatus::Terminated => f.write_str("terminated"),
+        }
+    }
+}
+
 fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
 where
     S: Serializer,

libs/pageserver_api/src/config.rs

@@ -104,8 +104,7 @@ pub struct ConfigToml {
     pub image_compression: ImageCompressionAlgorithm,
     pub ephemeral_bytes_per_memory_kb: usize,
     pub l0_flush: Option<crate::models::L0FlushConfig>,
-    pub virtual_file_direct_io: crate::models::virtual_file::DirectIoMode,
-    pub io_buffer_alignment: usize,
+    pub virtual_file_io_mode: Option<crate::models::virtual_file::IoMode>,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -388,10 +387,7 @@ impl Default for ConfigToml {
             image_compression: (DEFAULT_IMAGE_COMPRESSION),
             ephemeral_bytes_per_memory_kb: (DEFAULT_EPHEMERAL_BYTES_PER_MEMORY_KB),
             l0_flush: None,
-            virtual_file_direct_io: crate::models::virtual_file::DirectIoMode::default(),
-
-            io_buffer_alignment: DEFAULT_IO_BUFFER_ALIGNMENT,
-
+            virtual_file_io_mode: None,
             tenant_config: TenantConfigToml::default(),
         }
     }

libs/pageserver_api/src/models.rs

@@ -972,8 +972,6 @@ pub struct TopTenantShardsResponse {
 }
 
 pub mod virtual_file {
-    use std::path::PathBuf;
-
     #[derive(
         Copy,
         Clone,
@@ -994,50 +992,45 @@ pub mod virtual_file {
     }
 
     /// Direct IO modes for a pageserver.
-    #[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
-    #[serde(tag = "mode", rename_all = "kebab-case", deny_unknown_fields)]
-    pub enum DirectIoMode {
-        /// Direct IO disabled (uses usual buffered IO).
-        #[default]
-        Disabled,
-        /// Direct IO disabled (performs checks and perf simulations).
-        Evaluate {
-            /// Alignment check level
-            alignment_check: DirectIoAlignmentCheckLevel,
-            /// Latency padded for performance simulation.
-            latency_padding: DirectIoLatencyPadding,
-        },
-        /// Direct IO enabled.
-        Enabled {
-            /// Actions to perform on alignment error.
-            on_alignment_error: DirectIoOnAlignmentErrorAction,
-        },
+    #[derive(
+        Copy,
+        Clone,
+        PartialEq,
+        Eq,
+        Hash,
+        strum_macros::EnumString,
+        strum_macros::Display,
+        serde_with::DeserializeFromStr,
+        serde_with::SerializeDisplay,
+        Debug,
+    )]
+    #[strum(serialize_all = "kebab-case")]
+    #[repr(u8)]
+    pub enum IoMode {
+        /// Uses buffered IO.
+        Buffered,
+        /// Uses direct IO, error out if the operation fails.
+        #[cfg(target_os = "linux")]
+        Direct,
     }
 
-    #[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
-    #[serde(rename_all = "kebab-case")]
-    pub enum DirectIoAlignmentCheckLevel {
-        #[default]
-        Error,
-        Log,
-        None,
+    impl IoMode {
+        pub const fn preferred() -> Self {
+            Self::Buffered
+        }
     }
 
-    #[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
-    #[serde(rename_all = "kebab-case")]
-    pub enum DirectIoOnAlignmentErrorAction {
-        Error,
-        #[default]
-        FallbackToBuffered,
-    }
+    impl TryFrom<u8> for IoMode {
+        type Error = u8;
 
-    #[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
-    #[serde(tag = "type", rename_all = "kebab-case")]
-    pub enum DirectIoLatencyPadding {
-        /// Pad virtual file operations with IO to a fake file.
-        FakeFileRW { path: PathBuf },
-        #[default]
-        None,
+        fn try_from(value: u8) -> Result<Self, Self::Error> {
+            Ok(match value {
+                v if v == (IoMode::Buffered as u8) => IoMode::Buffered,
+                #[cfg(target_os = "linux")]
+                v if v == (IoMode::Direct as u8) => IoMode::Direct,
+                x => return Err(x),
+            })
+        }
     }
 }
 

pageserver/benches/bench_ingest.rs

@@ -164,11 +164,7 @@ fn criterion_benchmark(c: &mut Criterion) {
     let conf: &'static PageServerConf = Box::leak(Box::new(
         pageserver::config::PageServerConf::dummy_conf(temp_dir.path().to_path_buf()),
     ));
-    virtual_file::init(
-        16384,
-        virtual_file::io_engine_for_bench(),
-        pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT,
-    );
+    virtual_file::init(16384, virtual_file::io_engine_for_bench());
     page_cache::init(conf.page_cache_size);
 
     {

pageserver/client/src/mgmt_api.rs

@@ -540,10 +540,13 @@ impl Client {
             .map_err(Error::ReceiveBody)
     }
 
-    /// Configs io buffer alignment at runtime.
-    pub async fn put_io_alignment(&self, align: usize) -> Result<()> {
-        let uri = format!("{}/v1/io_alignment", self.mgmt_api_endpoint);
-        self.request(Method::PUT, uri, align)
+    /// Configs io mode at runtime.
+    pub async fn put_io_mode(
+        &self,
+        mode: &pageserver_api::models::virtual_file::IoMode,
+    ) -> Result<()> {
+        let uri = format!("{}/v1/io_mode", self.mgmt_api_endpoint);
+        self.request(Method::PUT, uri, mode)
             .await?
             .json()
             .await

pageserver/ctl/src/layer_map_analyzer.rs

@@ -152,11 +152,7 @@ pub(crate) async fn main(cmd: &AnalyzeLayerMapCmd) -> Result<()> {
     let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);
 
     // Initialize virtual_file (file desriptor cache) and page cache which are needed to access layer persistent B-Tree.
-    pageserver::virtual_file::init(
-        10,
-        virtual_file::api::IoEngineKind::StdFs,
-        pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT,
-    );
+    pageserver::virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
     pageserver::page_cache::init(100);
 
     let mut total_delta_layers = 0usize;

pageserver/ctl/src/layers.rs

@@ -59,7 +59,7 @@ pub(crate) enum LayerCmd {
 
 async fn read_delta_file(path: impl AsRef<Path>, ctx: &RequestContext) -> Result<()> {
     let path = Utf8Path::from_path(path.as_ref()).expect("non-Unicode path");
-    virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs, 1);
+    virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
     page_cache::init(100);
     let file = VirtualFile::open(path, ctx).await?;
     let file_id = page_cache::next_file_id();
@@ -190,11 +190,7 @@ pub(crate) async fn main(cmd: &LayerCmd) -> Result<()> {
             new_tenant_id,
             new_timeline_id,
         } => {
-            pageserver::virtual_file::init(
-                10,
-                virtual_file::api::IoEngineKind::StdFs,
-                pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT,
-            );
+            pageserver::virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
             pageserver::page_cache::init(100);
 
             let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);

pageserver/ctl/src/main.rs

@@ -26,7 +26,7 @@ use pageserver::{
     tenant::{dump_layerfile_from_path, metadata::TimelineMetadata},
     virtual_file,
 };
-use pageserver_api::{config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT, shard::TenantShardId};
+use pageserver_api::shard::TenantShardId;
 use postgres_ffi::ControlFileData;
 use remote_storage::{RemotePath, RemoteStorageConfig};
 use tokio_util::sync::CancellationToken;
@@ -205,11 +205,7 @@ fn read_pg_control_file(control_file_path: &Utf8Path) -> anyhow::Result<()> {
 
 async fn print_layerfile(path: &Utf8Path) -> anyhow::Result<()> {
     // Basic initialization of things that don't change after startup
-    virtual_file::init(
-        10,
-        virtual_file::api::IoEngineKind::StdFs,
-        DEFAULT_IO_BUFFER_ALIGNMENT,
-    );
+    virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
     page_cache::init(100);
     let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);
     dump_layerfile_from_path(path, true, &ctx).await

pageserver/pagebench/src/cmd/getpage_latest_lsn.rs

@@ -59,9 +59,9 @@ pub(crate) struct Args {
     #[clap(long)]
     set_io_engine: Option<pageserver_api::models::virtual_file::IoEngineKind>,
 
-    /// Before starting the benchmark, live-reconfigure the pageserver to use specified alignment for io buffers.
+    /// Before starting the benchmark, live-reconfigure the pageserver to use specified io mode (buffered vs. direct).
     #[clap(long)]
-    set_io_alignment: Option<usize>,
+    set_io_mode: Option<pageserver_api::models::virtual_file::IoMode>,
 
     targets: Option<Vec<TenantTimelineId>>,
 }
@@ -129,8 +129,8 @@ async fn main_impl(
         mgmt_api_client.put_io_engine(engine_str).await?;
     }
 
-    if let Some(align) = args.set_io_alignment {
-        mgmt_api_client.put_io_alignment(align).await?;
+    if let Some(mode) = &args.set_io_mode {
+        mgmt_api_client.put_io_mode(mode).await?;
     }
 
     // discover targets

pageserver/src/bin/pageserver.rs

@@ -125,8 +125,7 @@ fn main() -> anyhow::Result<()> {
 
     // after setting up logging, log the effective IO engine choice and read path implementations
     info!(?conf.virtual_file_io_engine, "starting with virtual_file IO engine");
-    info!(?conf.virtual_file_direct_io, "starting with virtual_file Direct IO settings");
-    info!(?conf.io_buffer_alignment, "starting with setting for IO buffer alignment");
+    info!(?conf.virtual_file_io_mode, "starting with virtual_file IO mode");
 
     // The tenants directory contains all the pageserver local disk state.
     // Create if not exists and make sure all the contents are durable before proceeding.
@@ -168,11 +167,7 @@ fn main() -> anyhow::Result<()> {
     let scenario = failpoint_support::init();
 
     // Basic initialization of things that don't change after startup
-    virtual_file::init(
-        conf.max_file_descriptors,
-        conf.virtual_file_io_engine,
-        conf.io_buffer_alignment,
-    );
+    virtual_file::init(conf.max_file_descriptors, conf.virtual_file_io_engine);
     page_cache::init(conf.page_cache_size);
 
     start_pageserver(launch_ts, conf).context("Failed to start pageserver")?;

pageserver/src/config.rs

@@ -174,9 +174,7 @@ pub struct PageServerConf {
     pub l0_flush: crate::l0_flush::L0FlushConfig,
 
     /// Direct IO settings
-    pub virtual_file_direct_io: virtual_file::DirectIoMode,
-
-    pub io_buffer_alignment: usize,
+    pub virtual_file_io_mode: virtual_file::IoMode,
 }
 
 /// Token for authentication to safekeepers
@@ -325,11 +323,10 @@ impl PageServerConf {
             image_compression,
             ephemeral_bytes_per_memory_kb,
             l0_flush,
-            virtual_file_direct_io,
+            virtual_file_io_mode,
             concurrent_tenant_warmup,
             concurrent_tenant_size_logical_size_queries,
             virtual_file_io_engine,
-            io_buffer_alignment,
             tenant_config,
         } = config_toml;
 
@@ -368,8 +365,6 @@ impl PageServerConf {
             max_vectored_read_bytes,
             image_compression,
             ephemeral_bytes_per_memory_kb,
-            virtual_file_direct_io,
-            io_buffer_alignment,
 
             // ------------------------------------------------------------
             // fields that require additional validation or custom handling
@@ -408,6 +403,7 @@ impl PageServerConf {
             l0_flush: l0_flush
                 .map(crate::l0_flush::L0FlushConfig::from)
                 .unwrap_or_default(),
+            virtual_file_io_mode: virtual_file_io_mode.unwrap_or(virtual_file::IoMode::preferred()),
         };
 
         // ------------------------------------------------------------

pageserver/src/http/routes.rs

@@ -17,6 +17,7 @@ use hyper::header;
 use hyper::StatusCode;
 use hyper::{Body, Request, Response, Uri};
 use metrics::launch_timestamp::LaunchTimestamp;
+use pageserver_api::models::virtual_file::IoMode;
 use pageserver_api::models::AuxFilePolicy;
 use pageserver_api::models::DownloadRemoteLayersTaskSpawnRequest;
 use pageserver_api::models::IngestAuxFilesRequest;
@@ -2379,17 +2380,13 @@ async fn put_io_engine_handler(
     json_response(StatusCode::OK, ())
 }
 
-async fn put_io_alignment_handler(
+async fn put_io_mode_handler(
     mut r: Request<Body>,
     _cancel: CancellationToken,
 ) -> Result<Response<Body>, ApiError> {
     check_permission(&r, None)?;
-    let align: usize = json_request(&mut r).await?;
-    crate::virtual_file::set_io_buffer_alignment(align).map_err(|align| {
-        ApiError::PreconditionFailed(
-            format!("Requested io alignment ({align}) is not a power of two").into(),
-        )
-    })?;
+    let mode: IoMode = json_request(&mut r).await?;
+    crate::virtual_file::set_io_mode(mode);
     json_response(StatusCode::OK, ())
 }
 
@@ -3080,9 +3077,7 @@ pub fn make_router(
             |r| api_handler(r, timeline_collect_keyspace),
         )
         .put("/v1/io_engine", |r| api_handler(r, put_io_engine_handler))
-        .put("/v1/io_alignment", |r| {
-            api_handler(r, put_io_alignment_handler)
-        })
+        .put("/v1/io_mode", |r| api_handler(r, put_io_mode_handler))
         .put(
             "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/force_aux_policy_switch",
             |r| api_handler(r, force_aux_policy_switch_handler),

pageserver/src/tenant/ephemeral_file.rs

@@ -84,7 +84,7 @@ impl Drop for EphemeralFile {
     fn drop(&mut self) {
         // unlink the file
         // we are clear to do this, because we have entered a gate
-        let path = &self.buffered_writer.as_inner().as_inner().path;
+        let path = self.buffered_writer.as_inner().as_inner().path();
         let res = std::fs::remove_file(path);
         if let Err(e) = res {
             if e.kind() != std::io::ErrorKind::NotFound {
@@ -356,7 +356,7 @@ mod tests {
         }
 
         let file_contents =
-            std::fs::read(&file.buffered_writer.as_inner().as_inner().path).unwrap();
+            std::fs::read(file.buffered_writer.as_inner().as_inner().path()).unwrap();
         assert_eq!(file_contents, &content[0..cap]);
 
         let buffer_contents = file.buffered_writer.inspect_buffer();
@@ -392,7 +392,7 @@ mod tests {
             .buffered_writer
             .as_inner()
             .as_inner()
-            .path
+            .path()
             .metadata()
             .unwrap();
         assert_eq!(

pageserver/src/tenant/storage_layer/delta_layer.rs

@@ -573,7 +573,7 @@ impl DeltaLayerWriterInner {
         ensure!(
             metadata.len() <= S3_UPLOAD_LIMIT,
             "Created delta layer file at {} of size {} above limit {S3_UPLOAD_LIMIT}!",
-            file.path,
+            file.path(),
             metadata.len()
         );
 
@@ -791,7 +791,7 @@ impl DeltaLayerInner {
         max_vectored_read_bytes: Option<MaxVectoredReadBytes>,
         ctx: &RequestContext,
     ) -> anyhow::Result<Self> {
-        let file = VirtualFile::open(path, ctx)
+        let file = VirtualFile::open_v2(path, ctx)
             .await
             .context("open layer file")?;
 
@@ -1022,7 +1022,7 @@ impl DeltaLayerInner {
                             blob_meta.key,
                             PageReconstructError::Other(anyhow!(
                                 "Failed to read blobs from virtual file {}: {}",
-                                self.file.path,
+                                self.file.path(),
                                 kind
                             )),
                         );
@@ -1048,7 +1048,7 @@ impl DeltaLayerInner {
                             meta.meta.key,
                             PageReconstructError::Other(anyhow!(e).context(format!(
                                 "Failed to decompress blob from virtual file {}",
-                                self.file.path,
+                                self.file.path(),
                             ))),
                         );
 
@@ -1066,7 +1066,7 @@ impl DeltaLayerInner {
                             meta.meta.key,
                             PageReconstructError::Other(anyhow!(e).context(format!(
                                 "Failed to deserialize blob from virtual file {}",
-                                self.file.path,
+                                self.file.path(),
                             ))),
                         );
 
@@ -1198,7 +1198,6 @@ impl DeltaLayerInner {
         let mut prev: Option<(Key, Lsn, BlobRef)> = None;
 
         let mut read_builder: Option<ChunkedVectoredReadBuilder> = None;
-        let align = virtual_file::get_io_buffer_alignment();
 
         let max_read_size = self
             .max_vectored_read_bytes
@@ -1247,7 +1246,6 @@ impl DeltaLayerInner {
                         offsets.end.pos(),
                         meta,
                         max_read_size,
-                        align,
                     ))
                 }
             } else {

pageserver/src/tenant/storage_layer/image_layer.rs

@@ -389,7 +389,7 @@ impl ImageLayerInner {
         max_vectored_read_bytes: Option<MaxVectoredReadBytes>,
         ctx: &RequestContext,
     ) -> anyhow::Result<Self> {
-        let file = VirtualFile::open(path, ctx)
+        let file = VirtualFile::open_v2(path, ctx)
             .await
             .context("open layer file")?;
         let file_id = page_cache::next_file_id();
@@ -626,7 +626,7 @@ impl ImageLayerInner {
                                     meta.meta.key,
                                     PageReconstructError::Other(anyhow!(e).context(format!(
                                         "Failed to decompress blob from virtual file {}",
-                                        self.file.path,
+                                        self.file.path(),
                                     ))),
                                 );
 
@@ -647,7 +647,7 @@ impl ImageLayerInner {
                             blob_meta.key,
                             PageReconstructError::from(anyhow!(
                                 "Failed to read blobs from virtual file {}: {}",
-                                self.file.path,
+                                self.file.path(),
                                 kind
                             )),
                         );

pageserver/src/tenant/vectored_blob_io.rs

@@ -194,8 +194,6 @@ pub(crate) struct ChunkedVectoredReadBuilder {
     /// Start offset and metadata for each blob in this read
     blobs_at: VecMap<u64, BlobMeta>,
     max_read_size: Option<usize>,
-    /// Chunk size reads are coalesced into.
-    chunk_size: usize,
 }
 
 /// Computes x / d rounded up.
@@ -204,6 +202,7 @@ fn div_round_up(x: usize, d: usize) -> usize {
 }
 
 impl ChunkedVectoredReadBuilder {
+    const CHUNK_SIZE: usize = virtual_file::get_io_buffer_alignment();
     /// Start building a new vectored read.
     ///
     /// Note that by design, this does not check against reading more than `max_read_size` to
@@ -214,21 +213,19 @@ impl ChunkedVectoredReadBuilder {
         end_offset: u64,
         meta: BlobMeta,
         max_read_size: Option<usize>,
-        chunk_size: usize,
     ) -> Self {
         let mut blobs_at = VecMap::default();
         blobs_at
             .append(start_offset, meta)
             .expect("First insertion always succeeds");
 
-        let start_blk_no = start_offset as usize / chunk_size;
-        let end_blk_no = div_round_up(end_offset as usize, chunk_size);
+        let start_blk_no = start_offset as usize / Self::CHUNK_SIZE;
+        let end_blk_no = div_round_up(end_offset as usize, Self::CHUNK_SIZE);
         Self {
             start_blk_no,
             end_blk_no,
             blobs_at,
             max_read_size,
-            chunk_size,
         }
     }
 
@@ -237,18 +234,12 @@ impl ChunkedVectoredReadBuilder {
         end_offset: u64,
         meta: BlobMeta,
         max_read_size: usize,
-        align: usize,
     ) -> Self {
-        Self::new_impl(start_offset, end_offset, meta, Some(max_read_size), align)
+        Self::new_impl(start_offset, end_offset, meta, Some(max_read_size))
     }
 
-    pub(crate) fn new_streaming(
-        start_offset: u64,
-        end_offset: u64,
-        meta: BlobMeta,
-        align: usize,
-    ) -> Self {
-        Self::new_impl(start_offset, end_offset, meta, None, align)
+    pub(crate) fn new_streaming(start_offset: u64, end_offset: u64, meta: BlobMeta) -> Self {
+        Self::new_impl(start_offset, end_offset, meta, None)
     }
 
     /// Attempts to extend the current read with a new blob if the new blob resides in the same or the immediate next chunk.
@@ -256,12 +247,12 @@ impl ChunkedVectoredReadBuilder {
     /// The resulting size also must be below the max read size.
     pub(crate) fn extend(&mut self, start: u64, end: u64, meta: BlobMeta) -> VectoredReadExtended {
         tracing::trace!(start, end, "trying to extend");
-        let start_blk_no = start as usize / self.chunk_size;
-        let end_blk_no = div_round_up(end as usize, self.chunk_size);
+        let start_blk_no = start as usize / Self::CHUNK_SIZE;
+        let end_blk_no = div_round_up(end as usize, Self::CHUNK_SIZE);
 
         let not_limited_by_max_read_size = {
             if let Some(max_read_size) = self.max_read_size {
-                let coalesced_size = (end_blk_no - self.start_blk_no) * self.chunk_size;
+                let coalesced_size = (end_blk_no - self.start_blk_no) * Self::CHUNK_SIZE;
                 coalesced_size <= max_read_size
             } else {
                 true
@@ -292,12 +283,12 @@ impl ChunkedVectoredReadBuilder {
     }
 
     pub(crate) fn size(&self) -> usize {
-        (self.end_blk_no - self.start_blk_no) * self.chunk_size
+        (self.end_blk_no - self.start_blk_no) * Self::CHUNK_SIZE
     }
 
     pub(crate) fn build(self) -> VectoredRead {
-        let start = (self.start_blk_no * self.chunk_size) as u64;
-        let end = (self.end_blk_no * self.chunk_size) as u64;
+        let start = (self.start_blk_no * Self::CHUNK_SIZE) as u64;
+        let end = (self.end_blk_no * Self::CHUNK_SIZE) as u64;
         VectoredRead {
             start,
             end,
@@ -328,18 +319,14 @@ pub struct VectoredReadPlanner {
     prev: Option<(Key, Lsn, u64, BlobFlag)>,
 
     max_read_size: usize,
-
-    align: usize,
 }
 
 impl VectoredReadPlanner {
     pub fn new(max_read_size: usize) -> Self {
-        let align = virtual_file::get_io_buffer_alignment();
         Self {
             blobs: BTreeMap::new(),
             prev: None,
             max_read_size,
-            align,
         }
     }
 
@@ -418,7 +405,6 @@ impl VectoredReadPlanner {
                         end_offset,
                         BlobMeta { key, lsn },
                         self.max_read_size,
-                        self.align,
                     );
 
                     let prev_read_builder = current_read_builder.replace(next_read_builder);
@@ -472,13 +458,13 @@ impl<'a> VectoredBlobReader<'a> {
         );
 
         if cfg!(debug_assertions) {
-            let align = virtual_file::get_io_buffer_alignment() as u64;
+            const ALIGN: u64 = virtual_file::get_io_buffer_alignment() as u64;
             debug_assert_eq!(
-                read.start % align,
+                read.start % ALIGN,
                 0,
                 "Read start at {} does not satisfy the required io buffer alignment ({} bytes)",
                 read.start,
-                align
+                ALIGN
             );
         }
 
@@ -553,22 +539,18 @@ pub struct StreamingVectoredReadPlanner {
     max_cnt: usize,
     /// Size of the current batch
     cnt: usize,
-
-    align: usize,
 }
 
 impl StreamingVectoredReadPlanner {
     pub fn new(max_read_size: u64, max_cnt: usize) -> Self {
         assert!(max_cnt > 0);
         assert!(max_read_size > 0);
-        let align = virtual_file::get_io_buffer_alignment();
         Self {
             read_builder: None,
             prev: None,
             max_cnt,
             max_read_size,
             cnt: 0,
-            align,
         }
     }
 
@@ -621,7 +603,6 @@ impl StreamingVectoredReadPlanner {
                         start_offset,
                         end_offset,
                         BlobMeta { key, lsn },
-                        self.align,
                     ))
                 };
             }
@@ -656,9 +637,9 @@ mod tests {
     use super::*;
 
     fn validate_read(read: &VectoredRead, offset_range: &[(Key, Lsn, u64, BlobFlag)]) {
-        let align = virtual_file::get_io_buffer_alignment() as u64;
-        assert_eq!(read.start % align, 0);
-        assert_eq!(read.start / align, offset_range.first().unwrap().2 / align);
+        const ALIGN: u64 = virtual_file::get_io_buffer_alignment() as u64;
+        assert_eq!(read.start % ALIGN, 0);
+        assert_eq!(read.start / ALIGN, offset_range.first().unwrap().2 / ALIGN);
 
         let expected_offsets_in_read: Vec<_> = offset_range.iter().map(|o| o.2).collect();
 
@@ -676,32 +657,27 @@ mod tests {
     fn planner_chunked_coalesce_all_test() {
         use crate::virtual_file;
 
-        let chunk_size = virtual_file::get_io_buffer_alignment() as u64;
+        const CHUNK_SIZE: u64 = virtual_file::get_io_buffer_alignment() as u64;
 
-        // The test explicitly does not check chunk size < 512
-        if chunk_size < 512 {
-            return;
-        }
-
-        let max_read_size = chunk_size as usize * 8;
+        let max_read_size = CHUNK_SIZE as usize * 8;
         let key = Key::MIN;
         let lsn = Lsn(0);
 
         let blob_descriptions = [
-            (key, lsn, chunk_size / 8, BlobFlag::None), // Read 1 BEGIN
-            (key, lsn, chunk_size / 4, BlobFlag::Ignore), // Gap
-            (key, lsn, chunk_size / 2, BlobFlag::None),
-            (key, lsn, chunk_size - 2, BlobFlag::Ignore), // Gap
-            (key, lsn, chunk_size, BlobFlag::None),
-            (key, lsn, chunk_size * 2 - 1, BlobFlag::None),
-            (key, lsn, chunk_size * 2 + 1, BlobFlag::Ignore), // Gap
-            (key, lsn, chunk_size * 3 + 1, BlobFlag::None),
-            (key, lsn, chunk_size * 5 + 1, BlobFlag::None),
-            (key, lsn, chunk_size * 6 + 1, BlobFlag::Ignore), // skipped chunk size, but not a chunk: should coalesce.
-            (key, lsn, chunk_size * 7 + 1, BlobFlag::None),
-            (key, lsn, chunk_size * 8, BlobFlag::None), // Read 2 BEGIN (b/c max_read_size)
-            (key, lsn, chunk_size * 9, BlobFlag::Ignore), // ==== skipped a chunk
-            (key, lsn, chunk_size * 10, BlobFlag::None), // Read 3 BEGIN (cannot coalesce)
+            (key, lsn, CHUNK_SIZE / 8, BlobFlag::None), // Read 1 BEGIN
+            (key, lsn, CHUNK_SIZE / 4, BlobFlag::Ignore), // Gap
+            (key, lsn, CHUNK_SIZE / 2, BlobFlag::None),
+            (key, lsn, CHUNK_SIZE - 2, BlobFlag::Ignore), // Gap
+            (key, lsn, CHUNK_SIZE, BlobFlag::None),
+            (key, lsn, CHUNK_SIZE * 2 - 1, BlobFlag::None),
+            (key, lsn, CHUNK_SIZE * 2 + 1, BlobFlag::Ignore), // Gap
+            (key, lsn, CHUNK_SIZE * 3 + 1, BlobFlag::None),
+            (key, lsn, CHUNK_SIZE * 5 + 1, BlobFlag::None),
+            (key, lsn, CHUNK_SIZE * 6 + 1, BlobFlag::Ignore), // skipped chunk size, but not a chunk: should coalesce.
+            (key, lsn, CHUNK_SIZE * 7 + 1, BlobFlag::None),
+            (key, lsn, CHUNK_SIZE * 8, BlobFlag::None), // Read 2 BEGIN (b/c max_read_size)
+            (key, lsn, CHUNK_SIZE * 9, BlobFlag::Ignore), // ==== skipped a chunk
+            (key, lsn, CHUNK_SIZE * 10, BlobFlag::None), // Read 3 BEGIN (cannot coalesce)
         ];
 
         let ranges = [
@@ -780,19 +756,19 @@ mod tests {
 
     #[test]
     fn planner_replacement_test() {
-        let chunk_size = virtual_file::get_io_buffer_alignment() as u64;
-        let max_read_size = 128 * chunk_size as usize;
+        const CHUNK_SIZE: u64 = virtual_file::get_io_buffer_alignment() as u64;
+        let max_read_size = 128 * CHUNK_SIZE as usize;
         let first_key = Key::MIN;
         let second_key = first_key.next();
         let lsn = Lsn(0);
 
         let blob_descriptions = vec![
             (first_key, lsn, 0, BlobFlag::None),          // First in read 1
-            (first_key, lsn, chunk_size, BlobFlag::None), // Last in read 1
-            (second_key, lsn, 2 * chunk_size, BlobFlag::ReplaceAll),
-            (second_key, lsn, 3 * chunk_size, BlobFlag::None),
-            (second_key, lsn, 4 * chunk_size, BlobFlag::ReplaceAll), // First in read 2
-            (second_key, lsn, 5 * chunk_size, BlobFlag::None),       // Last in read 2
+            (first_key, lsn, CHUNK_SIZE, BlobFlag::None), // Last in read 1
+            (second_key, lsn, 2 * CHUNK_SIZE, BlobFlag::ReplaceAll),
+            (second_key, lsn, 3 * CHUNK_SIZE, BlobFlag::None),
+            (second_key, lsn, 4 * CHUNK_SIZE, BlobFlag::ReplaceAll), // First in read 2
+            (second_key, lsn, 5 * CHUNK_SIZE, BlobFlag::None),       // Last in read 2
         ];
 
         let ranges = [&blob_descriptions[0..2], &blob_descriptions[4..]];
@@ -802,7 +778,7 @@ mod tests {
             planner.handle(key, lsn, offset, flag);
         }
 
-        planner.handle_range_end(6 * chunk_size);
+        planner.handle_range_end(6 * CHUNK_SIZE);
 
         let reads = planner.finish();
         assert_eq!(reads.len(), 2);
@@ -947,7 +923,6 @@ mod tests {
         let reserved_bytes = blobs.iter().map(|bl| bl.len()).max().unwrap() * 2 + 16;
         let mut buf = BytesMut::with_capacity(reserved_bytes);
 
-        let align = virtual_file::get_io_buffer_alignment();
         let vectored_blob_reader = VectoredBlobReader::new(&file);
         let meta = BlobMeta {
             key: Key::MIN,
@@ -959,8 +934,7 @@ mod tests {
             if idx + 1 == offsets.len() {
                 continue;
             }
-            let read_builder =
-                ChunkedVectoredReadBuilder::new(*offset, *end, meta, 16 * 4096, align);
+            let read_builder = ChunkedVectoredReadBuilder::new(*offset, *end, meta, 16 * 4096);
             let read = read_builder.build();
             let result = vectored_blob_reader.read_blobs(&read, buf, &ctx).await?;
             assert_eq!(result.blobs.len(), 1);

pageserver/src/virtual_file.rs

@@ -23,10 +23,12 @@ use pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT;
 use pageserver_api::shard::TenantShardId;
 use std::fs::File;
 use std::io::{Error, ErrorKind, Seek, SeekFrom};
+#[cfg(target_os = "linux")]
+use std::os::unix::fs::OpenOptionsExt;
 use tokio_epoll_uring::{BoundedBuf, IoBuf, IoBufMut, Slice};
 
 use std::os::fd::{AsRawFd, FromRawFd, IntoRawFd, OwnedFd, RawFd};
-use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
+use std::sync::atomic::{AtomicBool, AtomicU8, AtomicUsize, Ordering};
 use tokio::sync::{RwLock, RwLockReadGuard, RwLockWriteGuard};
 use tokio::time::Instant;
 
@@ -38,10 +40,11 @@ pub use io_engine::FeatureTestResult as IoEngineFeatureTestResult;
 mod metadata;
 mod open_options;
 use self::owned_buffers_io::write::OwnedAsyncWriter;
-pub(crate) use api::DirectIoMode;
+pub(crate) use api::IoMode;
 pub(crate) use io_engine::IoEngineKind;
 pub(crate) use metadata::Metadata;
 pub(crate) use open_options::*;
+pub(crate) mod dio;
 
 pub(crate) mod owned_buffers_io {
     //! Abstractions for IO with owned buffers.
@@ -53,6 +56,7 @@ pub(crate) mod owned_buffers_io {
     //! but for the time being we're proving out the primitives in the neon.git repo
     //! for faster iteration.
 
+    pub(crate) mod io_buf_aligned;
     pub(crate) mod io_buf_ext;
     pub(crate) mod slice;
     pub(crate) mod write;
@@ -61,6 +65,176 @@ pub(crate) mod owned_buffers_io {
     }
 }
 
+#[derive(Debug)]
+pub enum VirtualFile {
+    Buffered(VirtualFileInner),
+    Direct(VirtualFileInner),
+}
+
+impl VirtualFile {
+    fn inner(&self) -> &VirtualFileInner {
+        match self {
+            Self::Buffered(file) => file,
+            Self::Direct(file) => file,
+        }
+    }
+
+    fn inner_mut(&mut self) -> &mut VirtualFileInner {
+        match self {
+            Self::Buffered(file) => file,
+            Self::Direct(file) => file,
+        }
+    }
+
+    fn into_inner(self) -> VirtualFileInner {
+        match self {
+            Self::Buffered(file) => file,
+            Self::Direct(file) => file,
+        }
+    }
+    /// Open a file in read-only mode. Like File::open.
+    pub async fn open<P: AsRef<Utf8Path>>(
+        path: P,
+        ctx: &RequestContext,
+    ) -> Result<Self, std::io::Error> {
+        let file = VirtualFileInner::open(path, ctx).await?;
+        Ok(Self::Buffered(file))
+    }
+
+    /// Open a file in read-only mode. Like File::open.
+    ///
+    /// `O_DIRECT` will be enabled base on `virtual_file_io_mode`.
+    pub async fn open_v2<P: AsRef<Utf8Path>>(
+        path: P,
+        ctx: &RequestContext,
+    ) -> Result<Self, std::io::Error> {
+        Self::open_with_options_v2(path.as_ref(), OpenOptions::new().read(true), ctx).await
+    }
+
+    pub async fn create<P: AsRef<Utf8Path>>(
+        path: P,
+        ctx: &RequestContext,
+    ) -> Result<Self, std::io::Error> {
+        let file = VirtualFileInner::create(path, ctx).await?;
+        Ok(Self::Buffered(file))
+    }
+
+    pub async fn create_v2<P: AsRef<Utf8Path>>(
+        path: P,
+        ctx: &RequestContext,
+    ) -> Result<Self, std::io::Error> {
+        VirtualFile::open_with_options_v2(
+            path.as_ref(),
+            OpenOptions::new().write(true).create(true).truncate(true),
+            ctx,
+        )
+        .await
+    }
+
+    pub async fn open_with_options<P: AsRef<Utf8Path>>(
+        path: P,
+        open_options: &OpenOptions,
+        ctx: &RequestContext, /* TODO: carry a pointer to the metrics in the RequestContext instead of the parsing https://github.com/neondatabase/neon/issues/6107 */
+    ) -> Result<Self, std::io::Error> {
+        let file = VirtualFileInner::open_with_options(path, open_options, ctx).await?;
+        Ok(Self::Buffered(file))
+    }
+
+    pub async fn open_with_options_v2<P: AsRef<Utf8Path>>(
+        path: P,
+        open_options: &mut OpenOptions, // Uses `&mut` here to add `O_DIRECT`.
+        ctx: &RequestContext, /* TODO: carry a pointer to the metrics in the RequestContext instead of the parsing https://github.com/neondatabase/neon/issues/6107 */
+    ) -> Result<Self, std::io::Error> {
+        let file = match get_io_mode() {
+            IoMode::Buffered => {
+                let file = VirtualFileInner::open_with_options(path, open_options, ctx).await?;
+                Self::Buffered(file)
+            }
+            #[cfg(target_os = "linux")]
+            IoMode::Direct => {
+                let file = VirtualFileInner::open_with_options(
+                    path,
+                    open_options.custom_flags(nix::libc::O_DIRECT),
+                    ctx,
+                )
+                .await?;
+                Self::Direct(file)
+            }
+        };
+        Ok(file)
+    }
+
+    pub fn path(&self) -> &Utf8Path {
+        self.inner().path.as_path()
+    }
+
+    pub async fn crashsafe_overwrite<B: BoundedBuf<Buf = Buf> + Send, Buf: IoBuf + Send>(
+        final_path: Utf8PathBuf,
+        tmp_path: Utf8PathBuf,
+        content: B,
+    ) -> std::io::Result<()> {
+        VirtualFileInner::crashsafe_overwrite(final_path, tmp_path, content).await
+    }
+
+    pub async fn sync_all(&self) -> Result<(), Error> {
+        self.inner().sync_all().await
+    }
+
+    pub async fn sync_data(&self) -> Result<(), Error> {
+        self.inner().sync_data().await
+    }
+
+    pub async fn metadata(&self) -> Result<Metadata, Error> {
+        self.inner().metadata().await
+    }
+
+    pub fn remove(self) {
+        self.into_inner().remove();
+    }
+
+    pub async fn seek(&mut self, pos: SeekFrom) -> Result<u64, Error> {
+        self.inner_mut().seek(pos).await
+    }
+
+    pub async fn read_exact_at<Buf>(
+        &self,
+        slice: Slice<Buf>,
+        offset: u64,
+        ctx: &RequestContext,
+    ) -> Result<Slice<Buf>, Error>
+    where
+        Buf: IoBufMut + Send,
+    {
+        self.inner().read_exact_at(slice, offset, ctx).await
+    }
+
+    pub async fn read_exact_at_page(
+        &self,
+        page: PageWriteGuard<'static>,
+        offset: u64,
+        ctx: &RequestContext,
+    ) -> Result<PageWriteGuard<'static>, Error> {
+        self.inner().read_exact_at_page(page, offset, ctx).await
+    }
+
+    pub async fn write_all_at<Buf: IoBuf + Send>(
+        &self,
+        buf: FullSlice<Buf>,
+        offset: u64,
+        ctx: &RequestContext,
+    ) -> (FullSlice<Buf>, Result<(), Error>) {
+        self.inner().write_all_at(buf, offset, ctx).await
+    }
+
+    pub async fn write_all<Buf: IoBuf + Send>(
+        &mut self,
+        buf: FullSlice<Buf>,
+        ctx: &RequestContext,
+    ) -> (FullSlice<Buf>, Result<usize, Error>) {
+        self.inner_mut().write_all(buf, ctx).await
+    }
+}
+
 ///
 /// A virtual file descriptor. You can use this just like std::fs::File, but internally
 /// the underlying file is closed if the system is low on file descriptors,
@@ -77,7 +251,7 @@ pub(crate) mod owned_buffers_io {
 /// 'tag' field is used to detect whether the handle still is valid or not.
 ///
 #[derive(Debug)]
-pub struct VirtualFile {
+pub struct VirtualFileInner {
     /// Lazy handle to the global file descriptor cache. The slot that this points to
     /// might contain our File, or it may be empty, or it may contain a File that
     /// belongs to a different VirtualFile.
@@ -350,12 +524,12 @@ macro_rules! with_file {
     }};
 }
 
-impl VirtualFile {
+impl VirtualFileInner {
     /// Open a file in read-only mode. Like File::open.
     pub async fn open<P: AsRef<Utf8Path>>(
         path: P,
         ctx: &RequestContext,
-    ) -> Result<VirtualFile, std::io::Error> {
+    ) -> Result<VirtualFileInner, std::io::Error> {
         Self::open_with_options(path.as_ref(), OpenOptions::new().read(true), ctx).await
     }
 
@@ -364,7 +538,7 @@ impl VirtualFile {
     pub async fn create<P: AsRef<Utf8Path>>(
         path: P,
         ctx: &RequestContext,
-    ) -> Result<VirtualFile, std::io::Error> {
+    ) -> Result<VirtualFileInner, std::io::Error> {
         Self::open_with_options(
             path.as_ref(),
             OpenOptions::new().write(true).create(true).truncate(true),
@@ -382,7 +556,7 @@ impl VirtualFile {
         path: P,
         open_options: &OpenOptions,
         _ctx: &RequestContext, /* TODO: carry a pointer to the metrics in the RequestContext instead of the parsing https://github.com/neondatabase/neon/issues/6107 */
-    ) -> Result<VirtualFile, std::io::Error> {
+    ) -> Result<VirtualFileInner, std::io::Error> {
         let path_ref = path.as_ref();
         let path_str = path_ref.to_string();
         let parts = path_str.split('/').collect::<Vec<&str>>();
@@ -423,7 +597,7 @@ impl VirtualFile {
         reopen_options.create_new(false);
         reopen_options.truncate(false);
 
-        let vfile = VirtualFile {
+        let vfile = VirtualFileInner {
             handle: RwLock::new(handle),
             pos: 0,
             path: path_ref.to_path_buf(),
@@ -1034,6 +1208,21 @@ impl tokio_epoll_uring::IoFd for FileGuard {
 
 #[cfg(test)]
 impl VirtualFile {
+    pub(crate) async fn read_blk(
+        &self,
+        blknum: u32,
+        ctx: &RequestContext,
+    ) -> Result<crate::tenant::block_io::BlockLease<'_>, std::io::Error> {
+        self.inner().read_blk(blknum, ctx).await
+    }
+
+    async fn read_to_end(&mut self, buf: &mut Vec<u8>, ctx: &RequestContext) -> Result<(), Error> {
+        self.inner_mut().read_to_end(buf, ctx).await
+    }
+}
+
+#[cfg(test)]
+impl VirtualFileInner {
     pub(crate) async fn read_blk(
         &self,
         blknum: u32,
@@ -1067,7 +1256,7 @@ impl VirtualFile {
     }
 }
 
-impl Drop for VirtualFile {
+impl Drop for VirtualFileInner {
     /// If a VirtualFile is dropped, close the underlying file if it was open.
     fn drop(&mut self) {
         let handle = self.handle.get_mut();
@@ -1143,15 +1332,10 @@ impl OpenFiles {
 /// server startup.
 ///
 #[cfg(not(test))]
-pub fn init(num_slots: usize, engine: IoEngineKind, io_buffer_alignment: usize) {
+pub fn init(num_slots: usize, engine: IoEngineKind) {
     if OPEN_FILES.set(OpenFiles::new(num_slots)).is_err() {
         panic!("virtual_file::init called twice");
     }
-    if set_io_buffer_alignment(io_buffer_alignment).is_err() {
-        panic!(
-            "IO buffer alignment needs to be a power of two and greater than 512, got {io_buffer_alignment}"
-        );
-    }
     io_engine::init(engine);
     crate::metrics::virtual_file_descriptor_cache::SIZE_MAX.set(num_slots as u64);
 }
@@ -1175,47 +1359,22 @@ fn get_open_files() -> &'static OpenFiles {
     }
 }
 
-static IO_BUFFER_ALIGNMENT: AtomicUsize = AtomicUsize::new(DEFAULT_IO_BUFFER_ALIGNMENT);
-
-/// Returns true if the alignment is a power of two and is greater or equal to 512.
-fn is_valid_io_buffer_alignment(align: usize) -> bool {
-    align.is_power_of_two() && align >= 512
-}
-
-/// Sets IO buffer alignment requirement. Returns error if the alignment requirement is
-/// not a power of two or less than 512 bytes.
-#[allow(unused)]
-pub(crate) fn set_io_buffer_alignment(align: usize) -> Result<(), usize> {
-    if is_valid_io_buffer_alignment(align) {
-        IO_BUFFER_ALIGNMENT.store(align, std::sync::atomic::Ordering::Relaxed);
-        Ok(())
-    } else {
-        Err(align)
-    }
-}
-
 /// Gets the io buffer alignment.
-///
-/// This function should be used for getting the actual alignment value to use.
-pub(crate) fn get_io_buffer_alignment() -> usize {
-    let align = IO_BUFFER_ALIGNMENT.load(std::sync::atomic::Ordering::Relaxed);
-
-    if cfg!(test) {
-        let env_var_name = "NEON_PAGESERVER_UNIT_TEST_IO_BUFFER_ALIGNMENT";
-        if let Some(test_align) = utils::env::var(env_var_name) {
-            if is_valid_io_buffer_alignment(test_align) {
-                test_align
-            } else {
-                panic!("IO buffer alignment needs to be a power of two and greater than 512, got {test_align}");
-            }
-        } else {
-            align
-        }
-    } else {
-        align
-    }
+pub(crate) const fn get_io_buffer_alignment() -> usize {
+    DEFAULT_IO_BUFFER_ALIGNMENT
 }
 
+pub(crate) type IoBufferMut = dio::AlignedBufferMut<{ get_io_buffer_alignment() }>;
+
+static IO_MODE: AtomicU8 = AtomicU8::new(IoMode::preferred() as u8);
+
+pub(crate) fn set_io_mode(mode: IoMode) {
+    IO_MODE.store(mode as u8, std::sync::atomic::Ordering::Relaxed);
+}
+
+pub(crate) fn get_io_mode() -> IoMode {
+    IoMode::try_from(IO_MODE.load(Ordering::Relaxed)).unwrap()
+}
 #[cfg(test)]
 mod tests {
     use crate::context::DownloadBehavior;
@@ -1524,7 +1683,7 @@ mod tests {
         // Open the file many times.
         let mut files = Vec::new();
         for _ in 0..VIRTUAL_FILES {
-            let f = VirtualFile::open_with_options(
+            let f = VirtualFileInner::open_with_options(
                 &test_file_path,
                 OpenOptions::new().read(true),
                 &ctx,
@@ -1576,7 +1735,7 @@ mod tests {
         let path = testdir.join("myfile");
         let tmp_path = testdir.join("myfile.tmp");
 
-        VirtualFile::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"foo".to_vec())
+        VirtualFileInner::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"foo".to_vec())
             .await
             .unwrap();
         let mut file = MaybeVirtualFile::from(VirtualFile::open(&path, &ctx).await.unwrap());
@@ -1585,7 +1744,7 @@ mod tests {
         assert!(!tmp_path.exists());
         drop(file);
 
-        VirtualFile::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"bar".to_vec())
+        VirtualFileInner::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"bar".to_vec())
             .await
             .unwrap();
         let mut file = MaybeVirtualFile::from(VirtualFile::open(&path, &ctx).await.unwrap());
@@ -1608,7 +1767,7 @@ mod tests {
         std::fs::write(&tmp_path, "some preexisting junk that should be removed").unwrap();
         assert!(tmp_path.exists());
 
-        VirtualFile::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"foo".to_vec())
+        VirtualFileInner::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"foo".to_vec())
             .await
             .unwrap();
 

pageserver/src/virtual_file/dio.rs

@@ -0,0 +1,405 @@
+#![allow(unused)]
+
+use core::slice;
+use std::{
+    alloc::{self, Layout},
+    cmp,
+    mem::{ManuallyDrop, MaybeUninit},
+    ops::{Deref, DerefMut},
+    ptr::{addr_of_mut, NonNull},
+};
+
+use bytes::buf::UninitSlice;
+
+struct IoBufferPtr(*mut u8);
+
+// SAFETY: We gurantees no one besides `IoBufferPtr` itself has the raw pointer.
+unsafe impl Send for IoBufferPtr {}
+
+/// An aligned buffer type used for I/O.
+pub struct AlignedBufferMut<const ALIGN: usize> {
+    ptr: IoBufferPtr,
+    capacity: usize,
+    len: usize,
+}
+
+impl<const ALIGN: usize> AlignedBufferMut<ALIGN> {
+    /// Constructs a new, empty `IoBufferMut` with at least the specified capacity and alignment.
+    ///
+    /// The buffer will be able to hold at most `capacity` elements and will never resize.
+    ///
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` _bytes_, or if the following alignment requirement is not met:
+    /// * `align` must not be zero,
+    ///
+    /// * `align` must be a power of two,
+    ///
+    /// * `capacity`, when rounded up to the nearest multiple of `align`,
+    ///    must not overflow isize (i.e., the rounded value must be
+    ///    less than or equal to `isize::MAX`).
+    pub fn with_capacity(capacity: usize) -> Self {
+        let layout = Layout::from_size_align(capacity, ALIGN).expect("Invalid layout");
+
+        // SAFETY:  Making an allocation with a sized and aligned layout. The memory is manually freed with the same layout.
+        let ptr = unsafe {
+            let ptr = alloc::alloc(layout);
+            if ptr.is_null() {
+                alloc::handle_alloc_error(layout);
+            }
+            IoBufferPtr(ptr)
+        };
+
+        AlignedBufferMut {
+            ptr,
+            capacity,
+            len: 0,
+        }
+    }
+
+    /// Constructs a new `IoBufferMut` with at least the specified capacity and alignment, filled with zeros.
+    pub fn with_capacity_zeroed(capacity: usize) -> Self {
+        use bytes::BufMut;
+        let mut buf = Self::with_capacity(capacity);
+        buf.put_bytes(0, capacity);
+        buf.len = capacity;
+        buf
+    }
+
+    /// Returns the total number of bytes the buffer can hold.
+    #[inline]
+    pub fn capacity(&self) -> usize {
+        self.capacity
+    }
+
+    /// Returns the alignment of the buffer.
+    #[inline]
+    pub const fn align(&self) -> usize {
+        ALIGN
+    }
+
+    /// Returns the number of bytes in the buffer, also referred to as its 'length'.
+    #[inline]
+    pub fn len(&self) -> usize {
+        self.len
+    }
+
+    /// Force the length of the buffer to `new_len`.
+    #[inline]
+    unsafe fn set_len(&mut self, new_len: usize) {
+        debug_assert!(new_len <= self.capacity());
+        self.len = new_len;
+    }
+
+    #[inline]
+    fn as_ptr(&self) -> *const u8 {
+        self.ptr.0
+    }
+
+    #[inline]
+    fn as_mut_ptr(&mut self) -> *mut u8 {
+        self.ptr.0
+    }
+
+    /// Extracts a slice containing the entire buffer.
+    ///
+    /// Equivalent to `&s[..]`.
+    #[inline]
+    fn as_slice(&self) -> &[u8] {
+        // SAFETY: The pointer is valid and `len` bytes are initialized.
+        unsafe { slice::from_raw_parts(self.as_ptr(), self.len) }
+    }
+
+    /// Extracts a mutable slice of the entire buffer.
+    ///
+    /// Equivalent to `&mut s[..]`.
+    fn as_mut_slice(&mut self) -> &mut [u8] {
+        // SAFETY: The pointer is valid and `len` bytes are initialized.
+        unsafe { slice::from_raw_parts_mut(self.as_mut_ptr(), self.len) }
+    }
+
+    /// Drops the all the contents of the buffer, setting its length to `0`.
+    #[inline]
+    pub fn clear(&mut self) {
+        self.len = 0;
+    }
+
+    /// Reserves capacity for at least `additional` more bytes to be inserted
+    /// in the given `IoBufferMut`. The collection may reserve more space to
+    /// speculatively avoid frequent reallocations. After calling `reserve`,
+    /// capacity will be greater than or equal to `self.len() + additional`.
+    /// Does nothing if capacity is already sufficient.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` _bytes_.
+    pub fn reserve(&mut self, additional: usize) {
+        if additional > self.capacity() - self.len() {
+            self.reserve_inner(additional);
+        }
+    }
+
+    fn reserve_inner(&mut self, additional: usize) {
+        let Some(required_cap) = self.len().checked_add(additional) else {
+            capacity_overflow()
+        };
+
+        let old_capacity = self.capacity();
+        let align = self.align();
+        // This guarantees exponential growth. The doubling cannot overflow
+        // because `cap <= isize::MAX` and the type of `cap` is `usize`.
+        let cap = cmp::max(old_capacity * 2, required_cap);
+
+        if !is_valid_alloc(cap) {
+            capacity_overflow()
+        }
+        let new_layout = Layout::from_size_align(cap, self.align()).expect("Invalid layout");
+
+        let old_ptr = self.as_mut_ptr();
+
+        // SAFETY: old allocation was allocated with std::alloc::alloc with the same layout,
+        // and we panics on null pointer.
+        let (ptr, cap) = unsafe {
+            let old_layout = Layout::from_size_align_unchecked(old_capacity, align);
+            let ptr = alloc::realloc(old_ptr, old_layout, new_layout.size());
+            if ptr.is_null() {
+                alloc::handle_alloc_error(new_layout);
+            }
+            (IoBufferPtr(ptr), cap)
+        };
+
+        self.ptr = ptr;
+        self.capacity = cap;
+    }
+
+    /// Consumes and leaks the `IoBufferMut`, returning a mutable reference to the contents, &'a mut [u8].
+    pub fn leak<'a>(self) -> &'a mut [u8] {
+        let mut buf = ManuallyDrop::new(self);
+        // SAFETY: leaking the buffer as intended.
+        unsafe { slice::from_raw_parts_mut(buf.as_mut_ptr(), buf.len) }
+    }
+}
+
+fn capacity_overflow() -> ! {
+    panic!("capacity overflow")
+}
+
+// We need to guarantee the following:
+// * We don't ever allocate `> isize::MAX` byte-size objects.
+// * We don't overflow `usize::MAX` and actually allocate too little.
+//
+// On 64-bit we just need to check for overflow since trying to allocate
+// `> isize::MAX` bytes will surely fail. On 32-bit and 16-bit we need to add
+// an extra guard for this in case we're running on a platform which can use
+// all 4GB in user-space, e.g., PAE or x32.
+#[inline]
+fn is_valid_alloc(alloc_size: usize) -> bool {
+    !(usize::BITS < 64 && alloc_size > isize::MAX as usize)
+}
+
+impl<const ALIGN: usize> Drop for AlignedBufferMut<ALIGN> {
+    fn drop(&mut self) {
+        // SAFETY: memory was allocated with std::alloc::alloc with the same layout.
+        unsafe {
+            alloc::dealloc(
+                self.as_mut_ptr(),
+                Layout::from_size_align_unchecked(self.capacity, ALIGN),
+            )
+        }
+    }
+}
+
+impl<const ALIGN: usize> Deref for AlignedBufferMut<ALIGN> {
+    type Target = [u8];
+
+    fn deref(&self) -> &Self::Target {
+        self.as_slice()
+    }
+}
+
+impl<const ALIGN: usize> DerefMut for AlignedBufferMut<ALIGN> {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        self.as_mut_slice()
+    }
+}
+
+/// SAFETY: When advancing the internal cursor, the caller needs to make sure the bytes advcanced past have been initialized.
+unsafe impl<const ALIGN: usize> bytes::BufMut for AlignedBufferMut<ALIGN> {
+    #[inline]
+    fn remaining_mut(&self) -> usize {
+        // Although a `Vec` can have at most isize::MAX bytes, we never want to grow `IoBufferMut`.
+        // Thus, it can have at most `self.capacity` bytes.
+        self.capacity() - self.len()
+    }
+
+    // SAFETY: Caller needs to make sure the bytes being advanced past have been initialized.
+    #[inline]
+    unsafe fn advance_mut(&mut self, cnt: usize) {
+        let len = self.len();
+        let remaining = self.remaining_mut();
+
+        if remaining < cnt {
+            panic_advance(cnt, remaining);
+        }
+
+        // Addition will not overflow since the sum is at most the capacity.
+        self.set_len(len + cnt);
+    }
+
+    #[inline]
+    fn chunk_mut(&mut self) -> &mut bytes::buf::UninitSlice {
+        let cap = self.capacity();
+        let len = self.len();
+
+        // SAFETY: Since `self.ptr` is valid for `cap` bytes, `self.ptr.add(len)` must be
+        // valid for `cap - len` bytes. The subtraction will not underflow since
+        // `len <= cap`.
+        unsafe { UninitSlice::from_raw_parts_mut(self.as_mut_ptr().add(len), cap - len) }
+    }
+}
+
+/// Panic with a nice error message.
+#[cold]
+fn panic_advance(idx: usize, len: usize) -> ! {
+    panic!(
+        "advance out of bounds: the len is {} but advancing by {}",
+        len, idx
+    );
+}
+
+/// Safety: [`IoBufferMut`] has exclusive ownership of the io buffer,
+/// and the location remains stable even if [`Self`] is moved.
+unsafe impl<const ALIGN: usize> tokio_epoll_uring::IoBuf for AlignedBufferMut<ALIGN> {
+    fn stable_ptr(&self) -> *const u8 {
+        self.as_ptr()
+    }
+
+    fn bytes_init(&self) -> usize {
+        self.len()
+    }
+
+    fn bytes_total(&self) -> usize {
+        self.capacity()
+    }
+}
+
+// SAFETY: See above.
+unsafe impl<const ALIGN: usize> tokio_epoll_uring::IoBufMut for AlignedBufferMut<ALIGN> {
+    fn stable_mut_ptr(&mut self) -> *mut u8 {
+        self.as_mut_ptr()
+    }
+
+    unsafe fn set_init(&mut self, init_len: usize) {
+        if self.len() < init_len {
+            self.set_len(init_len);
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+
+    use super::*;
+
+    const ALIGN: usize = 4 * 1024;
+    type TestIoBufferMut = AlignedBufferMut<ALIGN>;
+
+    #[test]
+    fn test_with_capacity() {
+        let v = TestIoBufferMut::with_capacity(ALIGN * 4);
+        assert_eq!(v.len(), 0);
+        assert_eq!(v.capacity(), ALIGN * 4);
+        assert_eq!(v.align(), ALIGN);
+        assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+
+        let v = TestIoBufferMut::with_capacity(ALIGN / 2);
+        assert_eq!(v.len(), 0);
+        assert_eq!(v.capacity(), ALIGN / 2);
+        assert_eq!(v.align(), ALIGN);
+        assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+    }
+
+    #[test]
+    fn test_with_capacity_zeroed() {
+        let v = TestIoBufferMut::with_capacity_zeroed(ALIGN);
+        assert_eq!(v.len(), ALIGN);
+        assert_eq!(v.capacity(), ALIGN);
+        assert_eq!(v.align(), ALIGN);
+        assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+        assert_eq!(&v[..], &[0; ALIGN])
+    }
+
+    #[test]
+    fn test_reserve() {
+        use bytes::BufMut;
+        let mut v = TestIoBufferMut::with_capacity(ALIGN);
+        let capacity = v.capacity();
+        v.reserve(capacity);
+        assert_eq!(v.capacity(), capacity);
+        let data = [b'a'; ALIGN];
+        v.put(&data[..]);
+        v.reserve(capacity);
+        assert!(v.capacity() >= capacity * 2);
+        assert_eq!(&v[..], &data[..]);
+        let capacity = v.capacity();
+        v.clear();
+        v.reserve(capacity);
+        assert_eq!(capacity, v.capacity());
+    }
+
+    #[test]
+    fn test_bytes_put() {
+        use bytes::BufMut;
+        let mut v = TestIoBufferMut::with_capacity(ALIGN * 4);
+        let x = [b'a'; ALIGN];
+
+        for _ in 0..2 {
+            for _ in 0..4 {
+                v.put(&x[..]);
+            }
+            assert_eq!(v.len(), ALIGN * 4);
+            assert_eq!(v.capacity(), ALIGN * 4);
+            assert_eq!(v.align(), ALIGN);
+            assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+            v.clear()
+        }
+        assert_eq!(v.len(), 0);
+        assert_eq!(v.capacity(), ALIGN * 4);
+        assert_eq!(v.align(), ALIGN);
+        assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+    }
+
+    #[test]
+    #[should_panic]
+    fn test_bytes_put_panic() {
+        use bytes::BufMut;
+        const ALIGN: usize = 4 * 1024;
+        let mut v = TestIoBufferMut::with_capacity(ALIGN * 4);
+        let x = [b'a'; ALIGN];
+        for _ in 0..5 {
+            v.put_slice(&x[..]);
+        }
+    }
+
+    #[test]
+    fn test_io_buf_put_slice() {
+        use tokio_epoll_uring::BoundedBufMut;
+        const ALIGN: usize = 4 * 1024;
+        let mut v = TestIoBufferMut::with_capacity(ALIGN);
+        let x = [b'a'; ALIGN];
+
+        for _ in 0..2 {
+            v.put_slice(&x[..]);
+            assert_eq!(v.len(), ALIGN);
+            assert_eq!(v.capacity(), ALIGN);
+            assert_eq!(v.align(), ALIGN);
+            assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+            v.clear()
+        }
+        assert_eq!(v.len(), 0);
+        assert_eq!(v.capacity(), ALIGN);
+        assert_eq!(v.align(), ALIGN);
+        assert_eq!(v.as_ptr().align_offset(ALIGN), 0);
+    }
+}

pageserver/src/virtual_file/owned_buffers_io/io_buf_aligned.rs

@@ -0,0 +1,9 @@
+#![allow(unused)]
+
+use tokio_epoll_uring::IoBufMut;
+
+use crate::virtual_file::IoBufferMut;
+
+pub(crate) trait IoBufAlignedMut: IoBufMut {}
+
+impl IoBufAlignedMut for IoBufferMut {}

pageserver/src/virtual_file/owned_buffers_io/io_buf_ext.rs

@@ -1,5 +1,6 @@
 //! See [`FullSlice`].
 
+use crate::virtual_file::IoBufferMut;
 use bytes::{Bytes, BytesMut};
 use std::ops::{Deref, Range};
 use tokio_epoll_uring::{BoundedBuf, IoBuf, Slice};
@@ -76,3 +77,4 @@ macro_rules! impl_io_buf_ext {
 impl_io_buf_ext!(Bytes);
 impl_io_buf_ext!(BytesMut);
 impl_io_buf_ext!(Vec<u8>);
+impl_io_buf_ext!(IoBufferMut);

pgxn/neon/neon_pgversioncompat.h

@@ -7,6 +7,7 @@
 #define NEON_PGVERSIONCOMPAT_H
 
 #include "fmgr.h"
+#include "storage/buf_internals.h"
 
 #if PG_MAJORVERSION_NUM < 17
 #define NRelFileInfoBackendIsTemp(rinfo) (rinfo.backend != InvalidBackendId)
@@ -20,11 +21,24 @@
 	NInfoGetRelNumber(a) == NInfoGetRelNumber(b) \
 )
 
-/* buftag population & RelFileNode/RelFileLocator rework */
+/* These macros were turned into static inline functions in v16 */
 #if PG_MAJORVERSION_NUM < 16
+static inline bool
+BufferTagsEqual(const BufferTag *tag1, const BufferTag *tag2)
+{
+	return BUFFERTAGS_EQUAL(*tag1, *tag2);
+}
 
-#define InitBufferTag(tag, rfn, fn, bn) INIT_BUFFERTAG(*tag, *rfn, fn, bn)
+static inline void
+InitBufferTag(BufferTag *tag, const RelFileNode *rnode,
+			  ForkNumber forkNum, BlockNumber blockNum)
+{
+	INIT_BUFFERTAG(*tag, *rnode, forkNum, blockNum);
+}
+#endif
 
+/* RelFileNode -> RelFileLocator rework */
+#if PG_MAJORVERSION_NUM < 16
 #define USE_RELFILENODE
 
 #define RELFILEINFO_HDR "storage/relfilenode.h"
@@ -73,8 +87,6 @@
 
 #define USE_RELFILELOCATOR
 
-#define BUFFERTAGS_EQUAL(a, b) BufferTagsEqual(&(a), &(b))
-
 #define RELFILEINFO_HDR "storage/relfilelocator.h"
 
 #define NRelFileInfo RelFileLocator

pgxn/neon/pagestore_smgr.c

@@ -215,7 +215,7 @@ typedef struct PrfHashEntry
 	sizeof(BufferTag) \
 )
 
-#define SH_EQUAL(tb, a, b)	(BUFFERTAGS_EQUAL((a)->buftag, (b)->buftag))
+#define SH_EQUAL(tb, a, b)	(BufferTagsEqual(&(a)->buftag, &(b)->buftag))
 #define SH_SCOPE			static inline
 #define SH_DEFINE
 #define SH_DECLARE
@@ -803,15 +803,19 @@ prefetch_register_bufferv(BufferTag tag, neon_request_lsns *frlsns,
 						  bool is_prefetch)
 {
 	uint64		min_ring_index;
-	PrefetchRequest req;
+	PrefetchRequest hashkey;
 #if USE_ASSERT_CHECKING
 	bool		any_hits = false;
 #endif
 	/* We will never read further ahead than our buffer can store. */
 	nblocks = Max(1, Min(nblocks, readahead_buffer_size));
 
-	/* use an intermediate PrefetchRequest struct to ensure correct alignment */
-	req.buftag = tag;
+	/*
+	 * Use an intermediate PrefetchRequest struct as the hash key to ensure
+	 * correct alignment and that the padding bytes are cleared.
+	 */
+	memset(&hashkey.buftag, 0, sizeof(BufferTag));
+	hashkey.buftag = tag;
 
 Retry:
 	min_ring_index = UINT64_MAX;
@@ -837,8 +841,8 @@ Retry:
 		slot = NULL;
 		entry = NULL;
 
-		req.buftag.blockNum = tag.blockNum + i;
-		entry = prfh_lookup(MyPState->prf_hash, (PrefetchRequest *) &req);
+		hashkey.buftag.blockNum = tag.blockNum + i;
+		entry = prfh_lookup(MyPState->prf_hash, &hashkey);
 
 		if (entry != NULL)
 		{
@@ -849,7 +853,7 @@ Retry:
 			Assert(slot->status != PRFS_UNUSED);
 			Assert(MyPState->ring_last <= ring_index &&
 				   ring_index < MyPState->ring_unused);
-			Assert(BUFFERTAGS_EQUAL(slot->buftag, req.buftag));
+			Assert(BufferTagsEqual(&slot->buftag, &hashkey.buftag));
 
 			/*
 			 * If the caller specified a request LSN to use, only accept
@@ -886,12 +890,19 @@ Retry:
 				{
 					min_ring_index = Min(min_ring_index, ring_index);
 					/* The buffered request is good enough, return that index */
-					pgBufferUsage.prefetch.duplicates++;
+					if (is_prefetch)
+						pgBufferUsage.prefetch.duplicates++;
+					else
+						pgBufferUsage.prefetch.hits++;
 					continue;
 				}
 			}
 		}
-
+		else if (!is_prefetch)
+		{
+			pgBufferUsage.prefetch.misses += 1;
+			MyNeonCounters->getpage_prefetch_misses_total++;
+		}
 		/*
 		 * We can only leave the block above by finding that there's
 		 * no entry that can satisfy this request, either because there
@@ -974,7 +985,7 @@ Retry:
 		 * We must update the slot data before insertion, because the hash
 		 * function reads the buffer tag from the slot.
 		 */
-		slot->buftag = req.buftag;
+		slot->buftag = hashkey.buftag;
 		slot->shard_no = get_shard_number(&tag);
 		slot->my_ring_index = ring_index;
 
@@ -2742,14 +2753,19 @@ neon_read_at_lsnv(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber base_block
 	uint64		ring_index;
 	PrfHashEntry *entry;
 	PrefetchRequest *slot;
-	BufferTag	buftag = {0};
+	PrefetchRequest hashkey;
 
 	Assert(PointerIsValid(request_lsns));
 	Assert(nblocks >= 1);
 
-	CopyNRelFileInfoToBufTag(buftag, rinfo);
-	buftag.forkNum = forkNum;
-	buftag.blockNum = base_blockno;
+	/*
+	 * Use an intermediate PrefetchRequest struct as the hash key to ensure
+	 * correct alignment and that the padding bytes are cleared.
+	 */
+	memset(&hashkey.buftag, 0, sizeof(BufferTag));
+	CopyNRelFileInfoToBufTag(hashkey.buftag, rinfo);
+	hashkey.buftag.forkNum = forkNum;
+	hashkey.buftag.blockNum = base_blockno;
 
 	/*
 	 * The redo process does not lock pages that it needs to replay but are
@@ -2767,7 +2783,7 @@ neon_read_at_lsnv(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber base_block
 	 * weren't for the behaviour of the LwLsn cache that uses the highest
 	 * value of the LwLsn cache when the entry is not found.
 	 */
-	prefetch_register_bufferv(buftag, request_lsns, nblocks, mask, false);
+	prefetch_register_bufferv(hashkey.buftag, request_lsns, nblocks, mask, false);
 
 	for (int i = 0; i < nblocks; i++)
 	{
@@ -2788,8 +2804,8 @@ neon_read_at_lsnv(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber base_block
 		 * Try to find prefetched page in the list of received pages.
 		 */
 Retry:
-		buftag.blockNum = blockno;
-		entry = prfh_lookup(MyPState->prf_hash, (PrefetchRequest *) &buftag);
+		hashkey.buftag.blockNum = blockno;
+		entry = prfh_lookup(MyPState->prf_hash, &hashkey);
 
 		if (entry != NULL)
 		{
@@ -2797,7 +2813,6 @@ Retry:
 			if (neon_prefetch_response_usable(reqlsns, slot))
 			{
 				ring_index = slot->my_ring_index;
-				pgBufferUsage.prefetch.hits += 1;
 			}
 			else
 			{
@@ -2827,10 +2842,7 @@ Retry:
 		{
 			if (entry == NULL)
 			{
-				pgBufferUsage.prefetch.misses += 1;
-				MyNeonCounters->getpage_prefetch_misses_total++;
-
-				ring_index = prefetch_register_bufferv(buftag, reqlsns, 1, NULL, false);
+				ring_index = prefetch_register_bufferv(hashkey.buftag, reqlsns, 1, NULL, false);
 				Assert(ring_index != UINT64_MAX);
 				slot = GetPrfSlot(ring_index);
 			}
@@ -2855,8 +2867,8 @@ Retry:
 		} while (!prefetch_wait_for(ring_index));
 
 		Assert(slot->status == PRFS_RECEIVED);
-		Assert(memcmp(&buftag, &slot->buftag, sizeof(BufferTag)) == 0);
-		Assert(buftag.blockNum == base_blockno + i);
+		Assert(memcmp(&hashkey.buftag, &slot->buftag, sizeof(BufferTag)) == 0);
+		Assert(hashkey.buftag.blockNum == base_blockno + i);
 
 		resp = slot->response;
 
@@ -3059,6 +3071,9 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	lfc_result = lfc_readv_select(InfoFromSMgrRel(reln), forknum, blocknum, buffers,
 								  nblocks, read);
 
+	if (lfc_result > 0)
+		MyNeonCounters->file_cache_hits_total += lfc_result;
+
 	/* Read all blocks from LFC, so we're done */
 	if (lfc_result == nblocks)
 		return;

pgxn/neon_walredo/walredoproc.c

@@ -992,7 +992,7 @@ redo_block_filter(XLogReaderState *record, uint8 block_id)
 	 * If this block isn't one we are currently restoring, then return 'true'
 	 * so that this gets ignored
 	 */
-	return !BUFFERTAGS_EQUAL(target_tag, target_redo_tag);
+	return !BufferTagsEqual(&target_tag, &target_redo_tag);
 }
 
 /*

proxy/src/auth/backend/classic.rs

@@ -3,8 +3,8 @@ use crate::{
     auth::{self, backend::ComputeCredentialKeys, AuthFlow},
     compute,
     config::AuthenticationConfig,
-    console::AuthSecret,
     context::RequestMonitoring,
+    control_plane::AuthSecret,
     sasl,
     stream::{PqStream, Stream},
 };

proxy/src/auth/backend/console_redirect.rs

@@ -1,8 +1,8 @@
 use crate::{
     auth, compute,
     config::AuthenticationConfig,
-    console::{self, provider::NodeInfo},
     context::RequestMonitoring,
+    control_plane::{self, provider::NodeInfo},
     error::{ReportableError, UserFacingError},
     stream::PqStream,
     waiters,
@@ -70,7 +70,7 @@ pub(super) async fn authenticate(
     let (psql_session_id, waiter) = loop {
         let psql_session_id = new_psql_session_id();
 
-        match console::mgmt::get_waiter(&psql_session_id) {
+        match control_plane::mgmt::get_waiter(&psql_session_id) {
             Ok(waiter) => break (psql_session_id, waiter),
             Err(_e) => continue,
         }

proxy/src/auth/backend/hacks.rs

@@ -2,8 +2,8 @@ use super::{ComputeCredentials, ComputeUserInfo, ComputeUserInfoNoEndpoint};
 use crate::{
     auth::{self, AuthFlow},
     config::AuthenticationConfig,
-    console::AuthSecret,
     context::RequestMonitoring,
+    control_plane::AuthSecret,
     intern::EndpointIdInt,
     sasl,
     stream::{self, Stream},

proxy/src/auth/backend/local.rs

@@ -5,11 +5,11 @@ use arc_swap::ArcSwapOption;
 
 use crate::{
     compute::ConnCfg,
-    console::{
+    context::RequestMonitoring,
+    control_plane::{
         messages::{ColdStartInfo, EndpointJwksResponse, MetricsAuxInfo},
         NodeInfo,
     },
-    context::RequestMonitoring,
     intern::{BranchIdTag, EndpointIdTag, InternId, ProjectIdTag},
     EndpointId,
 };

proxy/src/auth/backend/mod.rs

@@ -1,27 +1,27 @@
 mod classic;
+mod console_redirect;
 mod hacks;
 pub mod jwt;
 pub mod local;
-mod web;
 
 use std::net::IpAddr;
 use std::sync::Arc;
 use std::time::Duration;
 
+pub(crate) use console_redirect::WebAuthError;
 use ipnet::{Ipv4Net, Ipv6Net};
 use local::LocalBackend;
 use tokio::io::{AsyncRead, AsyncWrite};
 use tokio_postgres::config::AuthKeys;
 use tracing::{info, warn};
-pub(crate) use web::WebAuthError;
 
 use crate::auth::credentials::check_peer_addr_is_in_list;
 use crate::auth::{validate_password_and_exchange, AuthError};
 use crate::cache::Cached;
-use crate::console::errors::GetAuthInfoError;
-use crate::console::provider::{CachedRoleSecret, ConsoleBackend};
-use crate::console::{AuthSecret, NodeInfo};
 use crate::context::RequestMonitoring;
+use crate::control_plane::errors::GetAuthInfoError;
+use crate::control_plane::provider::{CachedRoleSecret, ControlPlaneBackend};
+use crate::control_plane::{AuthSecret, NodeInfo};
 use crate::intern::EndpointIdInt;
 use crate::metrics::Metrics;
 use crate::proxy::connect_compute::ComputeConnectBackend;
@@ -31,7 +31,7 @@ use crate::stream::Stream;
 use crate::{
     auth::{self, ComputeUserInfoMaybeEndpoint},
     config::AuthenticationConfig,
-    console::{
+    control_plane::{
         self,
         provider::{CachedAllowedIps, CachedNodeInfo},
         Api,
@@ -67,19 +67,19 @@ impl<T> std::ops::Deref for MaybeOwned<'_, T> {
 ///   backends which require them for the authentication process.
 pub enum Backend<'a, T, D> {
     /// Cloud API (V2).
-    Console(MaybeOwned<'a, ConsoleBackend>, T),
+    ControlPlane(MaybeOwned<'a, ControlPlaneBackend>, T),
     /// Authentication via a web browser.
-    Web(MaybeOwned<'a, url::ApiUrl>, D),
+    ConsoleRedirect(MaybeOwned<'a, url::ApiUrl>, D),
     /// Local proxy uses configured auth credentials and does not wake compute
     Local(MaybeOwned<'a, LocalBackend>),
 }
 
 #[cfg(test)]
 pub(crate) trait TestBackend: Send + Sync + 'static {
-    fn wake_compute(&self) -> Result<CachedNodeInfo, console::errors::WakeComputeError>;
+    fn wake_compute(&self) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError>;
     fn get_allowed_ips_and_secret(
         &self,
-    ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), console::errors::GetAuthInfoError>;
+    ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), control_plane::errors::GetAuthInfoError>;
     fn dyn_clone(&self) -> Box<dyn TestBackend>;
 }
 
@@ -93,18 +93,23 @@ impl Clone for Box<dyn TestBackend> {
 impl std::fmt::Display for Backend<'_, (), ()> {
     fn fmt(&self, fmt: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         match self {
-            Self::Console(api, ()) => match &**api {
-                ConsoleBackend::Console(endpoint) => {
-                    fmt.debug_tuple("Console").field(&endpoint.url()).finish()
-                }
+            Self::ControlPlane(api, ()) => match &**api {
+                ControlPlaneBackend::Management(endpoint) => fmt
+                    .debug_tuple("ControlPlane::Management")
+                    .field(&endpoint.url())
+                    .finish(),
                 #[cfg(any(test, feature = "testing"))]
-                ConsoleBackend::Postgres(endpoint) => {
-                    fmt.debug_tuple("Postgres").field(&endpoint.url()).finish()
-                }
+                ControlPlaneBackend::PostgresMock(endpoint) => fmt
+                    .debug_tuple("ControlPlane::PostgresMock")
+                    .field(&endpoint.url())
+                    .finish(),
                 #[cfg(test)]
-                ConsoleBackend::Test(_) => fmt.debug_tuple("Test").finish(),
+                ControlPlaneBackend::Test(_) => fmt.debug_tuple("ControlPlane::Test").finish(),
             },
-            Self::Web(url, ()) => fmt.debug_tuple("Web").field(&url.as_str()).finish(),
+            Self::ConsoleRedirect(url, ()) => fmt
+                .debug_tuple("ConsoleRedirect")
+                .field(&url.as_str())
+                .finish(),
             Self::Local(_) => fmt.debug_tuple("Local").finish(),
         }
     }
@@ -115,8 +120,8 @@ impl<T, D> Backend<'_, T, D> {
     /// This helps us pass structured config to async tasks.
     pub(crate) fn as_ref(&self) -> Backend<'_, &T, &D> {
         match self {
-            Self::Console(c, x) => Backend::Console(MaybeOwned::Borrowed(c), x),
-            Self::Web(c, x) => Backend::Web(MaybeOwned::Borrowed(c), x),
+            Self::ControlPlane(c, x) => Backend::ControlPlane(MaybeOwned::Borrowed(c), x),
+            Self::ConsoleRedirect(c, x) => Backend::ConsoleRedirect(MaybeOwned::Borrowed(c), x),
             Self::Local(l) => Backend::Local(MaybeOwned::Borrowed(l)),
         }
     }
@@ -128,8 +133,8 @@ impl<'a, T, D> Backend<'a, T, D> {
     /// a function to a contained value.
     pub(crate) fn map<R>(self, f: impl FnOnce(T) -> R) -> Backend<'a, R, D> {
         match self {
-            Self::Console(c, x) => Backend::Console(c, f(x)),
-            Self::Web(c, x) => Backend::Web(c, x),
+            Self::ControlPlane(c, x) => Backend::ControlPlane(c, f(x)),
+            Self::ConsoleRedirect(c, x) => Backend::ConsoleRedirect(c, x),
             Self::Local(l) => Backend::Local(l),
         }
     }
@@ -139,8 +144,8 @@ impl<'a, T, D, E> Backend<'a, Result<T, E>, D> {
     /// This is most useful for error handling.
     pub(crate) fn transpose(self) -> Result<Backend<'a, T, D>, E> {
         match self {
-            Self::Console(c, x) => x.map(|x| Backend::Console(c, x)),
-            Self::Web(c, x) => Ok(Backend::Web(c, x)),
+            Self::ControlPlane(c, x) => x.map(|x| Backend::ControlPlane(c, x)),
+            Self::ConsoleRedirect(c, x) => Ok(Backend::ConsoleRedirect(c, x)),
             Self::Local(l) => Ok(Backend::Local(l)),
         }
     }
@@ -290,7 +295,7 @@ impl AuthenticationConfig {
 /// All authentication flows will emit an AuthenticationOk message if successful.
 async fn auth_quirks(
     ctx: &RequestMonitoring,
-    api: &impl console::Api,
+    api: &impl control_plane::Api,
     user_info: ComputeUserInfoMaybeEndpoint,
     client: &mut stream::PqStream<Stream<impl AsyncRead + AsyncWrite + Unpin>>,
     allow_cleartext: bool,
@@ -412,8 +417,8 @@ impl<'a> Backend<'a, ComputeUserInfoMaybeEndpoint, &()> {
     /// Get username from the credentials.
     pub(crate) fn get_user(&self) -> &str {
         match self {
-            Self::Console(_, user_info) => &user_info.user,
-            Self::Web(_, ()) => "web",
+            Self::ControlPlane(_, user_info) => &user_info.user,
+            Self::ConsoleRedirect(_, ()) => "web",
             Self::Local(_) => "local",
         }
     }
@@ -429,7 +434,7 @@ impl<'a> Backend<'a, ComputeUserInfoMaybeEndpoint, &()> {
         endpoint_rate_limiter: Arc<EndpointRateLimiter>,
     ) -> auth::Result<Backend<'a, ComputeCredentials, NodeInfo>> {
         let res = match self {
-            Self::Console(api, user_info) => {
+            Self::ControlPlane(api, user_info) => {
                 info!(
                     user = &*user_info.user,
                     project = user_info.endpoint(),
@@ -446,15 +451,15 @@ impl<'a> Backend<'a, ComputeUserInfoMaybeEndpoint, &()> {
                     endpoint_rate_limiter,
                 )
                 .await?;
-                Backend::Console(api, credentials)
+                Backend::ControlPlane(api, credentials)
             }
             // NOTE: this auth backend doesn't use client credentials.
-            Self::Web(url, ()) => {
+            Self::ConsoleRedirect(url, ()) => {
                 info!("performing web authentication");
 
-                let info = web::authenticate(ctx, config, &url, client).await?;
+                let info = console_redirect::authenticate(ctx, config, &url, client).await?;
 
-                Backend::Web(url, info)
+                Backend::ConsoleRedirect(url, info)
             }
             Self::Local(_) => {
                 return Err(auth::AuthError::bad_auth_method("invalid for local proxy"))
@@ -472,8 +477,8 @@ impl Backend<'_, ComputeUserInfo, &()> {
         ctx: &RequestMonitoring,
     ) -> Result<CachedRoleSecret, GetAuthInfoError> {
         match self {
-            Self::Console(api, user_info) => api.get_role_secret(ctx, user_info).await,
-            Self::Web(_, ()) => Ok(Cached::new_uncached(None)),
+            Self::ControlPlane(api, user_info) => api.get_role_secret(ctx, user_info).await,
+            Self::ConsoleRedirect(_, ()) => Ok(Cached::new_uncached(None)),
             Self::Local(_) => Ok(Cached::new_uncached(None)),
         }
     }
@@ -483,8 +488,10 @@ impl Backend<'_, ComputeUserInfo, &()> {
         ctx: &RequestMonitoring,
     ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), GetAuthInfoError> {
         match self {
-            Self::Console(api, user_info) => api.get_allowed_ips_and_secret(ctx, user_info).await,
-            Self::Web(_, ()) => Ok((Cached::new_uncached(Arc::new(vec![])), None)),
+            Self::ControlPlane(api, user_info) => {
+                api.get_allowed_ips_and_secret(ctx, user_info).await
+            }
+            Self::ConsoleRedirect(_, ()) => Ok((Cached::new_uncached(Arc::new(vec![])), None)),
             Self::Local(_) => Ok((Cached::new_uncached(Arc::new(vec![])), None)),
         }
     }
@@ -495,18 +502,18 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials, NodeInfo> {
     async fn wake_compute(
         &self,
         ctx: &RequestMonitoring,
-    ) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
+    ) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
         match self {
-            Self::Console(api, creds) => api.wake_compute(ctx, &creds.info).await,
-            Self::Web(_, info) => Ok(Cached::new_uncached(info.clone())),
+            Self::ControlPlane(api, creds) => api.wake_compute(ctx, &creds.info).await,
+            Self::ConsoleRedirect(_, info) => Ok(Cached::new_uncached(info.clone())),
             Self::Local(local) => Ok(Cached::new_uncached(local.node_info.clone())),
         }
     }
 
     fn get_keys(&self) -> &ComputeCredentialKeys {
         match self {
-            Self::Console(_, creds) => &creds.keys,
-            Self::Web(_, _) => &ComputeCredentialKeys::None,
+            Self::ControlPlane(_, creds) => &creds.keys,
+            Self::ConsoleRedirect(_, _) => &ComputeCredentialKeys::None,
             Self::Local(_) => &ComputeCredentialKeys::None,
         }
     }
@@ -517,10 +524,10 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials, &()> {
     async fn wake_compute(
         &self,
         ctx: &RequestMonitoring,
-    ) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
+    ) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
         match self {
-            Self::Console(api, creds) => api.wake_compute(ctx, &creds.info).await,
-            Self::Web(_, ()) => {
+            Self::ControlPlane(api, creds) => api.wake_compute(ctx, &creds.info).await,
+            Self::ConsoleRedirect(_, ()) => {
                 unreachable!("web auth flow doesn't support waking the compute")
             }
             Self::Local(local) => Ok(Cached::new_uncached(local.node_info.clone())),
@@ -529,8 +536,8 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials, &()> {
 
     fn get_keys(&self) -> &ComputeCredentialKeys {
         match self {
-            Self::Console(_, creds) => &creds.keys,
-            Self::Web(_, ()) => &ComputeCredentialKeys::None,
+            Self::ControlPlane(_, creds) => &creds.keys,
+            Self::ConsoleRedirect(_, ()) => &ComputeCredentialKeys::None,
             Self::Local(_) => &ComputeCredentialKeys::None,
         }
     }
@@ -553,12 +560,12 @@ mod tests {
     use crate::{
         auth::{backend::MaskedIp, ComputeUserInfoMaybeEndpoint, IpPattern},
         config::AuthenticationConfig,
-        console::{
+        context::RequestMonitoring,
+        control_plane::{
             self,
             provider::{self, CachedAllowedIps, CachedRoleSecret},
             CachedNodeInfo,
         },
-        context::RequestMonitoring,
         proxy::NeonOptions,
         rate_limiter::{EndpointRateLimiter, RateBucketInfo},
         scram::{threadpool::ThreadPool, ServerSecret},
@@ -572,12 +579,12 @@ mod tests {
         secret: AuthSecret,
     }
 
-    impl console::Api for Auth {
+    impl control_plane::Api for Auth {
         async fn get_role_secret(
             &self,
             _ctx: &RequestMonitoring,
             _user_info: &super::ComputeUserInfo,
-        ) -> Result<CachedRoleSecret, console::errors::GetAuthInfoError> {
+        ) -> Result<CachedRoleSecret, control_plane::errors::GetAuthInfoError> {
             Ok(CachedRoleSecret::new_uncached(Some(self.secret.clone())))
         }
 
@@ -585,8 +592,10 @@ mod tests {
             &self,
             _ctx: &RequestMonitoring,
             _user_info: &super::ComputeUserInfo,
-        ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), console::errors::GetAuthInfoError>
-        {
+        ) -> Result<
+            (CachedAllowedIps, Option<CachedRoleSecret>),
+            control_plane::errors::GetAuthInfoError,
+        > {
             Ok((
                 CachedAllowedIps::new_uncached(Arc::new(self.ips.clone())),
                 Some(CachedRoleSecret::new_uncached(Some(self.secret.clone()))),
@@ -605,7 +614,7 @@ mod tests {
             &self,
             _ctx: &RequestMonitoring,
             _user_info: &super::ComputeUserInfo,
-        ) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
+        ) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
             unimplemented!()
         }
     }

proxy/src/auth/flow.rs

@@ -3,8 +3,8 @@
 use super::{backend::ComputeCredentialKeys, AuthErrorImpl, PasswordHackPayload};
 use crate::{
     config::TlsServerEndPoint,
-    console::AuthSecret,
     context::RequestMonitoring,
+    control_plane::AuthSecret,
     intern::EndpointIdInt,
     sasl,
     scram::{self, threadpool::ThreadPool},

proxy/src/auth/mod.rs

@@ -18,7 +18,7 @@ pub(crate) use flow::*;
 use tokio::time::error::Elapsed;
 
 use crate::{
-    console,
+    control_plane,
     error::{ReportableError, UserFacingError},
 };
 use std::{io, net::IpAddr};
@@ -34,7 +34,7 @@ pub(crate) enum AuthErrorImpl {
     Web(#[from] backend::WebAuthError),
 
     #[error(transparent)]
-    GetAuthInfo(#[from] console::errors::GetAuthInfoError),
+    GetAuthInfo(#[from] control_plane::errors::GetAuthInfoError),
 
     /// SASL protocol errors (includes [SCRAM](crate::scram)).
     #[error(transparent)]

proxy/src/bin/local_proxy.rs

@@ -12,7 +12,7 @@ use proxy::{
     },
     cancellation::CancellationHandlerMain,
     config::{self, AuthenticationConfig, HttpConfig, ProxyConfig, RetryConfig},
-    console::{
+    control_plane::{
         locks::ApiLocks,
         messages::{EndpointJwksResponse, JwksSettings},
     },

proxy/src/bin/proxy.rs

@@ -19,8 +19,8 @@ use proxy::config::CacheOptions;
 use proxy::config::HttpConfig;
 use proxy::config::ProjectInfoCacheOptions;
 use proxy::config::ProxyProtocolV2;
-use proxy::console;
 use proxy::context::parquet::ParquetUploadArgs;
+use proxy::control_plane;
 use proxy::http;
 use proxy::http::health_server::AppMetrics;
 use proxy::metrics::Metrics;
@@ -495,7 +495,7 @@ async fn main() -> anyhow::Result<()> {
             proxy: proxy::metrics::Metrics::get(),
         },
     ));
-    maintenance_tasks.spawn(console::mgmt::task_main(mgmt_listener));
+    maintenance_tasks.spawn(control_plane::mgmt::task_main(mgmt_listener));
 
     if let Some(metrics_config) = &config.metric_collection {
         // TODO: Add gc regardles of the metric collection being enabled.
@@ -506,8 +506,8 @@ async fn main() -> anyhow::Result<()> {
         ));
     }
 
-    if let auth::Backend::Console(api, _) = &config.auth_backend {
-        if let proxy::console::provider::ConsoleBackend::Console(api) = &**api {
+    if let auth::Backend::ControlPlane(api, _) = &config.auth_backend {
+        if let proxy::control_plane::provider::ControlPlaneBackend::Management(api) = &**api {
             match (redis_notifications_client, regional_redis_client.clone()) {
                 (None, None) => {}
                 (client1, client2) => {
@@ -623,7 +623,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
                 "Using AllowedIpsCache (wake_compute) with options={project_info_cache_config:?}"
             );
             info!("Using EndpointCacheConfig with options={endpoint_cache_config:?}");
-            let caches = Box::leak(Box::new(console::caches::ApiCaches::new(
+            let caches = Box::leak(Box::new(control_plane::caches::ApiCaches::new(
                 wake_compute_cache_config,
                 project_info_cache_config,
                 endpoint_cache_config,
@@ -636,7 +636,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
                 timeout,
             } = args.wake_compute_lock.parse()?;
             info!(?limiter, shards, ?epoch, "Using NodeLocks (wake_compute)");
-            let locks = Box::leak(Box::new(console::locks::ApiLocks::new(
+            let locks = Box::leak(Box::new(control_plane::locks::ApiLocks::new(
                 "wake_compute_lock",
                 limiter,
                 shards,
@@ -653,27 +653,27 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
             RateBucketInfo::validate(&mut wake_compute_rps_limit)?;
             let wake_compute_endpoint_rate_limiter =
                 Arc::new(WakeComputeRateLimiter::new(wake_compute_rps_limit));
-            let api = console::provider::neon::Api::new(
+            let api = control_plane::provider::neon::Api::new(
                 endpoint,
                 caches,
                 locks,
                 wake_compute_endpoint_rate_limiter,
             );
-            let api = console::provider::ConsoleBackend::Console(api);
-            auth::Backend::Console(MaybeOwned::Owned(api), ())
+            let api = control_plane::provider::ControlPlaneBackend::Management(api);
+            auth::Backend::ControlPlane(MaybeOwned::Owned(api), ())
         }
 
         AuthBackendType::Web => {
             let url = args.uri.parse()?;
-            auth::Backend::Web(MaybeOwned::Owned(url), ())
+            auth::Backend::ConsoleRedirect(MaybeOwned::Owned(url), ())
         }
 
         #[cfg(feature = "testing")]
         AuthBackendType::Postgres => {
             let url = args.auth_endpoint.parse()?;
-            let api = console::provider::mock::Api::new(url, !args.is_private_access_proxy);
-            let api = console::provider::ConsoleBackend::Postgres(api);
-            auth::Backend::Console(MaybeOwned::Owned(api), ())
+            let api = control_plane::provider::mock::Api::new(url, !args.is_private_access_proxy);
+            let api = control_plane::provider::ControlPlaneBackend::PostgresMock(api);
+            auth::Backend::ControlPlane(MaybeOwned::Owned(api), ())
         }
     };
 
@@ -689,7 +689,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
         ?epoch,
         "Using NodeLocks (connect_compute)"
     );
-    let connect_compute_locks = console::locks::ApiLocks::new(
+    let connect_compute_locks = control_plane::locks::ApiLocks::new(
         "connect_compute_lock",
         limiter,
         shards,

proxy/src/cache/project_info.rs

@@ -16,7 +16,7 @@ use tracing::{debug, info};
 use crate::{
     auth::IpPattern,
     config::ProjectInfoCacheOptions,
-    console::AuthSecret,
+    control_plane::AuthSecret,
     intern::{EndpointIdInt, ProjectIdInt, RoleNameInt},
     EndpointId, RoleName,
 };

proxy/src/compute.rs

@@ -1,8 +1,8 @@
 use crate::{
     auth::parse_endpoint_param,
     cancellation::CancelClosure,
-    console::{errors::WakeComputeError, messages::MetricsAuxInfo, provider::ApiLockError},
     context::RequestMonitoring,
+    control_plane::{errors::WakeComputeError, messages::MetricsAuxInfo, provider::ApiLockError},
     error::{ReportableError, UserFacingError},
     metrics::{Metrics, NumDbConnectionsGuard},
     proxy::neon_option,

proxy/src/config.rs

@@ -3,7 +3,7 @@ use crate::{
         self,
         backend::{jwt::JwkCache, AuthRateLimiter},
     },
-    console::locks::ApiLocks,
+    control_plane::locks::ApiLocks,
     rate_limiter::{RateBucketInfo, RateLimitAlgorithm, RateLimiterConfig},
     scram::threadpool::ThreadPool,
     serverless::{cancel_set::CancelSet, GlobalConnPoolOptions},
@@ -372,7 +372,7 @@ pub struct EndpointCacheConfig {
 }
 
 impl EndpointCacheConfig {
-    /// Default options for [`crate::console::provider::NodeInfoCache`].
+    /// Default options for [`crate::control_plane::provider::NodeInfoCache`].
     /// Notice that by default the limiter is empty, which means that cache is disabled.
     pub const CACHE_DEFAULT_OPTIONS: &'static str =
         "initial_batch_size=1000,default_batch_size=10,xread_timeout=5m,stream_name=controlPlane,disable_cache=true,limiter_info=1000@1s,retry_interval=1s";
@@ -447,7 +447,7 @@ pub struct CacheOptions {
 }
 
 impl CacheOptions {
-    /// Default options for [`crate::console::provider::NodeInfoCache`].
+    /// Default options for [`crate::control_plane::provider::NodeInfoCache`].
     pub const CACHE_DEFAULT_OPTIONS: &'static str = "size=4000,ttl=4m";
 
     /// Parse cache options passed via cmdline.
@@ -503,7 +503,7 @@ pub struct ProjectInfoCacheOptions {
 }
 
 impl ProjectInfoCacheOptions {
-    /// Default options for [`crate::console::provider::NodeInfoCache`].
+    /// Default options for [`crate::control_plane::provider::NodeInfoCache`].
     pub const CACHE_DEFAULT_OPTIONS: &'static str =
         "size=10000,ttl=4m,max_roles=10,gc_interval=60m";
 
@@ -622,9 +622,9 @@ pub struct ConcurrencyLockOptions {
 }
 
 impl ConcurrencyLockOptions {
-    /// Default options for [`crate::console::provider::ApiLocks`].
+    /// Default options for [`crate::control_plane::provider::ApiLocks`].
     pub const DEFAULT_OPTIONS_WAKE_COMPUTE_LOCK: &'static str = "permits=0";
-    /// Default options for [`crate::console::provider::ApiLocks`].
+    /// Default options for [`crate::control_plane::provider::ApiLocks`].
     pub const DEFAULT_OPTIONS_CONNECT_COMPUTE_LOCK: &'static str =
         "shards=64,permits=100,epoch=10m,timeout=10ms";
 

proxy/src/context/mod.rs

@@ -11,7 +11,7 @@ use try_lock::TryLock;
 use uuid::Uuid;
 
 use crate::{
-    console::messages::{ColdStartInfo, MetricsAuxInfo},
+    control_plane::messages::{ColdStartInfo, MetricsAuxInfo},
     error::ErrorKind,
     intern::{BranchIdInt, ProjectIdInt},
     metrics::{ConnectOutcome, InvalidEndpointsGroup, LatencyTimer, Metrics, Protocol, Waiting},

proxy/src/control_plane/messages.rs

@@ -10,14 +10,14 @@ use crate::proxy::retry::CouldRetry;
 /// Generic error response with human-readable description.
 /// Note that we can't always present it to user as is.
 #[derive(Debug, Deserialize, Clone)]
-pub(crate) struct ConsoleError {
+pub(crate) struct ControlPlaneError {
     pub(crate) error: Box<str>,
     #[serde(skip)]
     pub(crate) http_status_code: http::StatusCode,
     pub(crate) status: Option<Status>,
 }
 
-impl ConsoleError {
+impl ControlPlaneError {
     pub(crate) fn get_reason(&self) -> Reason {
         self.status
             .as_ref()
@@ -51,7 +51,7 @@ impl ConsoleError {
     }
 }
 
-impl Display for ConsoleError {
+impl Display for ControlPlaneError {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         let msg: &str = self
             .status
@@ -62,7 +62,7 @@ impl Display for ConsoleError {
     }
 }
 
-impl CouldRetry for ConsoleError {
+impl CouldRetry for ControlPlaneError {
     fn could_retry(&self) -> bool {
         // If the error message does not have a status,
         // the error is unknown and probably should not retry automatically

proxy/src/control_plane/mgmt.rs

@@ -1,5 +1,5 @@
 use crate::{
-    console::messages::{DatabaseInfo, KickSession},
+    control_plane::messages::{DatabaseInfo, KickSession},
     waiters::{self, Waiter, Waiters},
 };
 use anyhow::Context;

proxy/src/control_plane/provider/mock.rs

@@ -10,7 +10,7 @@ use crate::{
 use crate::{auth::backend::ComputeUserInfo, compute, error::io_error, scram, url::ApiUrl};
 use crate::{auth::IpPattern, cache::Cached};
 use crate::{
-    console::{
+    control_plane::{
         messages::MetricsAuxInfo,
         provider::{CachedAllowedIps, CachedRoleSecret},
     },
@@ -166,7 +166,7 @@ impl Api {
                 endpoint_id: (&EndpointId::from("endpoint")).into(),
                 project_id: (&ProjectId::from("project")).into(),
                 branch_id: (&BranchId::from("branch")).into(),
-                cold_start_info: crate::console::messages::ColdStartInfo::Warm,
+                cold_start_info: crate::control_plane::messages::ColdStartInfo::Warm,
             },
             allow_self_signed_compute: false,
         };

proxy/src/control_plane/provider/mod.rs

@@ -2,7 +2,7 @@
 pub mod mock;
 pub mod neon;
 
-use super::messages::{ConsoleError, MetricsAuxInfo};
+use super::messages::{ControlPlaneError, MetricsAuxInfo};
 use crate::{
     auth::{
         backend::{
@@ -28,7 +28,7 @@ use tracing::info;
 
 pub(crate) mod errors {
     use crate::{
-        console::messages::{self, ConsoleError, Reason},
+        control_plane::messages::{self, ControlPlaneError, Reason},
         error::{io_error, ErrorKind, ReportableError, UserFacingError},
         proxy::retry::CouldRetry,
     };
@@ -44,7 +44,7 @@ pub(crate) mod errors {
     pub(crate) enum ApiError {
         /// Error returned by the console itself.
         #[error("{REQUEST_FAILED} with {0}")]
-        Console(ConsoleError),
+        ControlPlane(ControlPlaneError),
 
         /// Various IO errors like broken pipe or malformed payload.
         #[error("{REQUEST_FAILED}: {0}")]
@@ -55,7 +55,7 @@ pub(crate) mod errors {
         /// Returns HTTP status code if it's the reason for failure.
         pub(crate) fn get_reason(&self) -> messages::Reason {
             match self {
-                ApiError::Console(e) => e.get_reason(),
+                ApiError::ControlPlane(e) => e.get_reason(),
                 ApiError::Transport(_) => messages::Reason::Unknown,
             }
         }
@@ -65,7 +65,7 @@ pub(crate) mod errors {
         fn to_string_client(&self) -> String {
             match self {
                 // To minimize risks, only select errors are forwarded to users.
-                ApiError::Console(c) => c.get_user_facing_message(),
+                ApiError::ControlPlane(c) => c.get_user_facing_message(),
                 ApiError::Transport(_) => REQUEST_FAILED.to_owned(),
             }
         }
@@ -74,7 +74,7 @@ pub(crate) mod errors {
     impl ReportableError for ApiError {
         fn get_error_kind(&self) -> crate::error::ErrorKind {
             match self {
-                ApiError::Console(e) => match e.get_reason() {
+                ApiError::ControlPlane(e) => match e.get_reason() {
                     Reason::RoleProtected => ErrorKind::User,
                     Reason::ResourceNotFound => ErrorKind::User,
                     Reason::ProjectNotFound => ErrorKind::User,
@@ -91,12 +91,12 @@ pub(crate) mod errors {
                     Reason::LockAlreadyTaken => ErrorKind::ControlPlane,
                     Reason::RunningOperations => ErrorKind::ControlPlane,
                     Reason::Unknown => match &e {
-                        ConsoleError {
+                        ControlPlaneError {
                             http_status_code:
                                 http::StatusCode::NOT_FOUND | http::StatusCode::NOT_ACCEPTABLE,
                             ..
                         } => crate::error::ErrorKind::User,
-                        ConsoleError {
+                        ControlPlaneError {
                             http_status_code: http::StatusCode::UNPROCESSABLE_ENTITY,
                             error,
                             ..
@@ -105,7 +105,7 @@ pub(crate) mod errors {
                         {
                             crate::error::ErrorKind::User
                         }
-                        ConsoleError {
+                        ControlPlaneError {
                             http_status_code: http::StatusCode::LOCKED,
                             error,
                             ..
@@ -114,11 +114,11 @@ pub(crate) mod errors {
                         {
                             crate::error::ErrorKind::User
                         }
-                        ConsoleError {
+                        ControlPlaneError {
                             http_status_code: http::StatusCode::TOO_MANY_REQUESTS,
                             ..
                         } => crate::error::ErrorKind::ServiceRateLimit,
-                        ConsoleError { .. } => crate::error::ErrorKind::ControlPlane,
+                        ControlPlaneError { .. } => crate::error::ErrorKind::ControlPlane,
                     },
                 },
                 ApiError::Transport(_) => crate::error::ErrorKind::ControlPlane,
@@ -131,7 +131,7 @@ pub(crate) mod errors {
             match self {
                 // retry some transport errors
                 Self::Transport(io) => io.could_retry(),
-                Self::Console(e) => e.could_retry(),
+                Self::ControlPlane(e) => e.could_retry(),
             }
         }
     }
@@ -314,7 +314,8 @@ impl NodeInfo {
     }
 }
 
-pub(crate) type NodeInfoCache = TimedLru<EndpointCacheKey, Result<NodeInfo, Box<ConsoleError>>>;
+pub(crate) type NodeInfoCache =
+    TimedLru<EndpointCacheKey, Result<NodeInfo, Box<ControlPlaneError>>>;
 pub(crate) type CachedNodeInfo = Cached<&'static NodeInfoCache, NodeInfo>;
 pub(crate) type CachedRoleSecret = Cached<&'static ProjectInfoCacheImpl, Option<AuthSecret>>;
 pub(crate) type CachedAllowedIps = Cached<&'static ProjectInfoCacheImpl, Arc<Vec<IpPattern>>>;
@@ -353,28 +354,28 @@ pub(crate) trait Api {
 
 #[non_exhaustive]
 #[derive(Clone)]
-pub enum ConsoleBackend {
-    /// Current Cloud API (V2).
-    Console(neon::Api),
-    /// Local mock of Cloud API (V2).
+pub enum ControlPlaneBackend {
+    /// Current Management API (V2).
+    Management(neon::Api),
+    /// Local mock control plane.
     #[cfg(any(test, feature = "testing"))]
-    Postgres(mock::Api),
+    PostgresMock(mock::Api),
     /// Internal testing
     #[cfg(test)]
     #[allow(private_interfaces)]
     Test(Box<dyn crate::auth::backend::TestBackend>),
 }
 
-impl Api for ConsoleBackend {
+impl Api for ControlPlaneBackend {
     async fn get_role_secret(
         &self,
         ctx: &RequestMonitoring,
         user_info: &ComputeUserInfo,
     ) -> Result<CachedRoleSecret, errors::GetAuthInfoError> {
         match self {
-            Self::Console(api) => api.get_role_secret(ctx, user_info).await,
+            Self::Management(api) => api.get_role_secret(ctx, user_info).await,
             #[cfg(any(test, feature = "testing"))]
-            Self::Postgres(api) => api.get_role_secret(ctx, user_info).await,
+            Self::PostgresMock(api) => api.get_role_secret(ctx, user_info).await,
             #[cfg(test)]
             Self::Test(_) => {
                 unreachable!("this function should never be called in the test backend")
@@ -388,9 +389,9 @@ impl Api for ConsoleBackend {
         user_info: &ComputeUserInfo,
     ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), errors::GetAuthInfoError> {
         match self {
-            Self::Console(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
+            Self::Management(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
             #[cfg(any(test, feature = "testing"))]
-            Self::Postgres(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
+            Self::PostgresMock(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
             #[cfg(test)]
             Self::Test(api) => api.get_allowed_ips_and_secret(),
         }
@@ -402,9 +403,9 @@ impl Api for ConsoleBackend {
         endpoint: EndpointId,
     ) -> anyhow::Result<Vec<AuthRule>> {
         match self {
-            Self::Console(api) => api.get_endpoint_jwks(ctx, endpoint).await,
+            Self::Management(api) => api.get_endpoint_jwks(ctx, endpoint).await,
             #[cfg(any(test, feature = "testing"))]
-            Self::Postgres(api) => api.get_endpoint_jwks(ctx, endpoint).await,
+            Self::PostgresMock(api) => api.get_endpoint_jwks(ctx, endpoint).await,
             #[cfg(test)]
             Self::Test(_api) => Ok(vec![]),
         }
@@ -416,16 +417,16 @@ impl Api for ConsoleBackend {
         user_info: &ComputeUserInfo,
     ) -> Result<CachedNodeInfo, errors::WakeComputeError> {
         match self {
-            Self::Console(api) => api.wake_compute(ctx, user_info).await,
+            Self::Management(api) => api.wake_compute(ctx, user_info).await,
             #[cfg(any(test, feature = "testing"))]
-            Self::Postgres(api) => api.wake_compute(ctx, user_info).await,
+            Self::PostgresMock(api) => api.wake_compute(ctx, user_info).await,
             #[cfg(test)]
             Self::Test(api) => api.wake_compute(),
         }
     }
 }
 
-/// Various caches for [`console`](super).
+/// Various caches for [`control_plane`](super).
 pub struct ApiCaches {
     /// Cache for the `wake_compute` API method.
     pub(crate) node_info: NodeInfoCache,
@@ -454,7 +455,7 @@ impl ApiCaches {
     }
 }
 
-/// Various caches for [`console`](super).
+/// Various caches for [`control_plane`](super).
 pub struct ApiLocks<K> {
     name: &'static str,
     node_locks: DashMap<K, Arc<DynamicLimiter>>,
@@ -577,7 +578,7 @@ impl WakeComputePermit {
     }
 }
 
-impl FetchAuthRules for ConsoleBackend {
+impl FetchAuthRules for ControlPlaneBackend {
     async fn fetch_auth_rules(
         &self,
         ctx: &RequestMonitoring,

proxy/src/control_plane/provider/neon.rs

@@ -1,7 +1,7 @@
 //! Production console backend.
 
 use super::{
-    super::messages::{ConsoleError, GetRoleSecret, WakeCompute},
+    super::messages::{ControlPlaneError, GetRoleSecret, WakeCompute},
     errors::{ApiError, GetAuthInfoError, WakeComputeError},
     ApiCaches, ApiLocks, AuthInfo, AuthSecret, CachedAllowedIps, CachedNodeInfo, CachedRoleSecret,
     NodeInfo,
@@ -9,7 +9,7 @@ use super::{
 use crate::{
     auth::backend::{jwt::AuthRule, ComputeUserInfo},
     compute,
-    console::messages::{ColdStartInfo, EndpointJwksResponse, Reason},
+    control_plane::messages::{ColdStartInfo, EndpointJwksResponse, Reason},
     http,
     metrics::{CacheOutcome, Metrics},
     rate_limiter::WakeComputeRateLimiter,
@@ -348,7 +348,7 @@ impl super::Api for Api {
                     let (cached, info) = cached.take_value();
                     let info = info.map_err(|c| {
                         info!(key = &*key, "found cached wake_compute error");
-                        WakeComputeError::ApiError(ApiError::Console(*c))
+                        WakeComputeError::ApiError(ApiError::ControlPlane(*c))
                     })?;
 
                     debug!(key = &*key, "found cached compute node info");
@@ -395,9 +395,9 @@ impl super::Api for Api {
                 Ok(cached.map(|()| node))
             }
             Err(err) => match err {
-                WakeComputeError::ApiError(ApiError::Console(err)) => {
+                WakeComputeError::ApiError(ApiError::ControlPlane(err)) => {
                     let Some(status) = &err.status else {
-                        return Err(WakeComputeError::ApiError(ApiError::Console(err)));
+                        return Err(WakeComputeError::ApiError(ApiError::ControlPlane(err)));
                     };
 
                     let reason = status
@@ -407,7 +407,7 @@ impl super::Api for Api {
 
                     // if we can retry this error, do not cache it.
                     if reason.can_retry() {
-                        return Err(WakeComputeError::ApiError(ApiError::Console(err)));
+                        return Err(WakeComputeError::ApiError(ApiError::ControlPlane(err)));
                     }
 
                     // at this point, we should only have quota errors.
@@ -422,7 +422,7 @@ impl super::Api for Api {
                         Duration::from_secs(30),
                     );
 
-                    Err(WakeComputeError::ApiError(ApiError::Console(err)))
+                    Err(WakeComputeError::ApiError(ApiError::ControlPlane(err)))
                 }
                 err => return Err(err),
             },
@@ -448,7 +448,7 @@ async fn parse_body<T: for<'a> serde::Deserialize<'a>>(
     // as the fact that the request itself has failed.
     let mut body = serde_json::from_slice(&s).unwrap_or_else(|e| {
         warn!("failed to parse error body: {e}");
-        ConsoleError {
+        ControlPlaneError {
             error: "reason unclear (malformed error message)".into(),
             http_status_code: status,
             status: None,
@@ -457,7 +457,7 @@ async fn parse_body<T: for<'a> serde::Deserialize<'a>>(
     body.http_status_code = status;
 
     error!("console responded with an error ({status}): {body:?}");
-    Err(ApiError::Console(body))
+    Err(ApiError::ControlPlane(body))
 }
 
 fn parse_host_port(input: &str) -> Option<(&str, u16)> {

proxy/src/lib.rs

@@ -97,8 +97,8 @@ pub mod cache;
 pub mod cancellation;
 pub mod compute;
 pub mod config;
-pub mod console;
 pub mod context;
+pub mod control_plane;
 pub mod error;
 pub mod http;
 pub mod intern;

proxy/src/metrics.rs

@@ -11,7 +11,7 @@ use metrics::{CounterPairAssoc, CounterPairVec, HyperLogLog, HyperLogLogVec};
 
 use tokio::time::{self, Instant};
 
-use crate::console::messages::ColdStartInfo;
+use crate::control_plane::messages::ColdStartInfo;
 
 #[derive(MetricGroup)]
 #[metric(new(thread_pool: Arc<ThreadPoolMetrics>))]

proxy/src/proxy/connect_compute.rs

@@ -3,8 +3,8 @@ use crate::{
     compute::COULD_NOT_CONNECT,
     compute::{self, PostgresConnection},
     config::RetryConfig,
-    console::{self, errors::WakeComputeError, locks::ApiLocks, CachedNodeInfo, NodeInfo},
     context::RequestMonitoring,
+    control_plane::{self, errors::WakeComputeError, locks::ApiLocks, CachedNodeInfo, NodeInfo},
     error::ReportableError,
     metrics::{ConnectOutcome, ConnectionFailureKind, Metrics, RetriesMetricGroup, RetryType},
     proxy::{
@@ -26,7 +26,7 @@ const CONNECT_TIMEOUT: time::Duration = time::Duration::from_secs(2);
 /// (e.g. the compute node's address might've changed at the wrong time).
 /// Invalidate the cache entry (if any) to prevent subsequent errors.
 #[tracing::instrument(name = "invalidate_cache", skip_all)]
-pub(crate) fn invalidate_cache(node_info: console::CachedNodeInfo) -> NodeInfo {
+pub(crate) fn invalidate_cache(node_info: control_plane::CachedNodeInfo) -> NodeInfo {
     let is_cached = node_info.cached();
     if is_cached {
         warn!("invalidating stalled compute node info cache entry");
@@ -49,7 +49,7 @@ pub(crate) trait ConnectMechanism {
     async fn connect_once(
         &self,
         ctx: &RequestMonitoring,
-        node_info: &console::CachedNodeInfo,
+        node_info: &control_plane::CachedNodeInfo,
         timeout: time::Duration,
     ) -> Result<Self::Connection, Self::ConnectError>;
 
@@ -61,7 +61,7 @@ pub(crate) trait ComputeConnectBackend {
     async fn wake_compute(
         &self,
         ctx: &RequestMonitoring,
-    ) -> Result<CachedNodeInfo, console::errors::WakeComputeError>;
+    ) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError>;
 
     fn get_keys(&self) -> &ComputeCredentialKeys;
 }
@@ -84,7 +84,7 @@ impl ConnectMechanism for TcpMechanism<'_> {
     async fn connect_once(
         &self,
         ctx: &RequestMonitoring,
-        node_info: &console::CachedNodeInfo,
+        node_info: &control_plane::CachedNodeInfo,
         timeout: time::Duration,
     ) -> Result<PostgresConnection, Self::Error> {
         let host = node_info.config.get_host()?;

proxy/src/proxy/passthrough.rs

@@ -1,7 +1,7 @@
 use crate::{
     cancellation,
     compute::PostgresConnection,
-    console::messages::MetricsAuxInfo,
+    control_plane::messages::MetricsAuxInfo,
     metrics::{Direction, Metrics, NumClientConnectionsGuard, NumConnectionRequestsGuard},
     stream::Stream,
     usage_metrics::{Ids, MetricCounterRecorder, USAGE_METRICS},

proxy/src/proxy/tests/mod.rs

@@ -11,9 +11,11 @@ use crate::auth::backend::{
     ComputeCredentialKeys, ComputeCredentials, ComputeUserInfo, MaybeOwned, TestBackend,
 };
 use crate::config::{CertResolver, RetryConfig};
-use crate::console::messages::{ConsoleError, Details, MetricsAuxInfo, Status};
-use crate::console::provider::{CachedAllowedIps, CachedRoleSecret, ConsoleBackend, NodeInfoCache};
-use crate::console::{self, CachedNodeInfo, NodeInfo};
+use crate::control_plane::messages::{ControlPlaneError, Details, MetricsAuxInfo, Status};
+use crate::control_plane::provider::{
+    CachedAllowedIps, CachedRoleSecret, ControlPlaneBackend, NodeInfoCache,
+};
+use crate::control_plane::{self, CachedNodeInfo, NodeInfo};
 use crate::error::ErrorKind;
 use crate::{sasl, scram, BranchId, EndpointId, ProjectId};
 use anyhow::{bail, Context};
@@ -459,7 +461,7 @@ impl ConnectMechanism for TestConnectMechanism {
     async fn connect_once(
         &self,
         _ctx: &RequestMonitoring,
-        _node_info: &console::CachedNodeInfo,
+        _node_info: &control_plane::CachedNodeInfo,
         _timeout: std::time::Duration,
     ) -> Result<Self::Connection, Self::ConnectError> {
         let mut counter = self.counter.lock().unwrap();
@@ -483,23 +485,23 @@ impl ConnectMechanism for TestConnectMechanism {
 }
 
 impl TestBackend for TestConnectMechanism {
-    fn wake_compute(&self) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
+    fn wake_compute(&self) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
         let mut counter = self.counter.lock().unwrap();
         let action = self.sequence[*counter];
         *counter += 1;
         match action {
             ConnectAction::Wake => Ok(helper_create_cached_node_info(self.cache)),
             ConnectAction::WakeFail => {
-                let err = console::errors::ApiError::Console(ConsoleError {
+                let err = control_plane::errors::ApiError::ControlPlane(ControlPlaneError {
                     http_status_code: StatusCode::BAD_REQUEST,
                     error: "TEST".into(),
                     status: None,
                 });
                 assert!(!err.could_retry());
-                Err(console::errors::WakeComputeError::ApiError(err))
+                Err(control_plane::errors::WakeComputeError::ApiError(err))
             }
             ConnectAction::WakeRetry => {
-                let err = console::errors::ApiError::Console(ConsoleError {
+                let err = control_plane::errors::ApiError::ControlPlane(ControlPlaneError {
                     http_status_code: StatusCode::BAD_REQUEST,
                     error: "TEST".into(),
                     status: Some(Status {
@@ -507,13 +509,15 @@ impl TestBackend for TestConnectMechanism {
                         message: "error".into(),
                         details: Details {
                             error_info: None,
-                            retry_info: Some(console::messages::RetryInfo { retry_delay_ms: 1 }),
+                            retry_info: Some(control_plane::messages::RetryInfo {
+                                retry_delay_ms: 1,
+                            }),
                             user_facing_message: None,
                         },
                     }),
                 });
                 assert!(err.could_retry());
-                Err(console::errors::WakeComputeError::ApiError(err))
+                Err(control_plane::errors::WakeComputeError::ApiError(err))
             }
             x => panic!("expecting action {x:?}, wake_compute is called instead"),
         }
@@ -521,7 +525,7 @@ impl TestBackend for TestConnectMechanism {
 
     fn get_allowed_ips_and_secret(
         &self,
-    ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), console::errors::GetAuthInfoError>
+    ) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), control_plane::errors::GetAuthInfoError>
     {
         unimplemented!("not used in tests")
     }
@@ -538,7 +542,7 @@ fn helper_create_cached_node_info(cache: &'static NodeInfoCache) -> CachedNodeIn
             endpoint_id: (&EndpointId::from("endpoint")).into(),
             project_id: (&ProjectId::from("project")).into(),
             branch_id: (&BranchId::from("branch")).into(),
-            cold_start_info: crate::console::messages::ColdStartInfo::Warm,
+            cold_start_info: crate::control_plane::messages::ColdStartInfo::Warm,
         },
         allow_self_signed_compute: false,
     };
@@ -549,8 +553,8 @@ fn helper_create_cached_node_info(cache: &'static NodeInfoCache) -> CachedNodeIn
 fn helper_create_connect_info(
     mechanism: &TestConnectMechanism,
 ) -> auth::Backend<'static, ComputeCredentials, &()> {
-    let user_info = auth::Backend::Console(
-        MaybeOwned::Owned(ConsoleBackend::Test(Box::new(mechanism.clone()))),
+    let user_info = auth::Backend::ControlPlane(
+        MaybeOwned::Owned(ControlPlaneBackend::Test(Box::new(mechanism.clone()))),
         ComputeCredentials {
             info: ComputeUserInfo {
                 endpoint: "endpoint".into(),

proxy/src/proxy/wake_compute.rs

@@ -1,7 +1,7 @@
 use crate::config::RetryConfig;
-use crate::console::messages::{ConsoleError, Reason};
-use crate::console::{errors::WakeComputeError, provider::CachedNodeInfo};
 use crate::context::RequestMonitoring;
+use crate::control_plane::messages::{ControlPlaneError, Reason};
+use crate::control_plane::{errors::WakeComputeError, provider::CachedNodeInfo};
 use crate::metrics::{
     ConnectOutcome, ConnectionFailuresBreakdownGroup, Metrics, RetriesMetricGroup, RetryType,
     WakeupFailureKind,
@@ -59,11 +59,11 @@ pub(crate) async fn wake_compute<B: ComputeConnectBackend>(
 }
 
 fn report_error(e: &WakeComputeError, retry: bool) {
-    use crate::console::errors::ApiError;
+    use crate::control_plane::errors::ApiError;
     let kind = match e {
         WakeComputeError::BadComputeAddress(_) => WakeupFailureKind::BadComputeAddress,
         WakeComputeError::ApiError(ApiError::Transport(_)) => WakeupFailureKind::ApiTransportError,
-        WakeComputeError::ApiError(ApiError::Console(e)) => match e.get_reason() {
+        WakeComputeError::ApiError(ApiError::ControlPlane(e)) => match e.get_reason() {
             Reason::RoleProtected => WakeupFailureKind::ApiConsoleBadRequest,
             Reason::ResourceNotFound => WakeupFailureKind::ApiConsoleBadRequest,
             Reason::ProjectNotFound => WakeupFailureKind::ApiConsoleBadRequest,
@@ -80,7 +80,7 @@ fn report_error(e: &WakeComputeError, retry: bool) {
             Reason::LockAlreadyTaken => WakeupFailureKind::ApiConsoleLocked,
             Reason::RunningOperations => WakeupFailureKind::ApiConsoleLocked,
             Reason::Unknown => match e {
-                ConsoleError {
+                ControlPlaneError {
                     http_status_code: StatusCode::LOCKED,
                     ref error,
                     ..
@@ -89,27 +89,27 @@ fn report_error(e: &WakeComputeError, retry: bool) {
                 {
                     WakeupFailureKind::QuotaExceeded
                 }
-                ConsoleError {
+                ControlPlaneError {
                     http_status_code: StatusCode::UNPROCESSABLE_ENTITY,
                     ref error,
                     ..
                 } if error.contains("compute time quota of non-primary branches is exceeded") => {
                     WakeupFailureKind::QuotaExceeded
                 }
-                ConsoleError {
+                ControlPlaneError {
                     http_status_code: StatusCode::LOCKED,
                     ..
                 } => WakeupFailureKind::ApiConsoleLocked,
-                ConsoleError {
+                ControlPlaneError {
                     http_status_code: StatusCode::BAD_REQUEST,
                     ..
                 } => WakeupFailureKind::ApiConsoleBadRequest,
-                ConsoleError {
+                ControlPlaneError {
                     http_status_code, ..
                 } if http_status_code.is_server_error() => {
                     WakeupFailureKind::ApiConsoleOtherServerError
                 }
-                ConsoleError { .. } => WakeupFailureKind::ApiConsoleOtherError,
+                ControlPlaneError { .. } => WakeupFailureKind::ApiConsoleOtherError,
             },
         },
         WakeComputeError::TooManyConnections => WakeupFailureKind::ApiConsoleLocked,

proxy/src/serverless/backend.rs

@@ -12,13 +12,13 @@ use crate::{
     },
     compute,
     config::{AuthenticationConfig, ProxyConfig},
-    console::{
+    context::RequestMonitoring,
+    control_plane::{
         errors::{GetAuthInfoError, WakeComputeError},
         locks::ApiLocks,
         provider::ApiLockError,
         CachedNodeInfo,
     },
-    context::RequestMonitoring,
     error::{ErrorKind, ReportableError, UserFacingError},
     intern::EndpointIdInt,
     proxy::{
@@ -114,7 +114,7 @@ impl PoolingBackend {
         jwt: String,
     ) -> Result<(), AuthError> {
         match &self.config.auth_backend {
-            crate::auth::Backend::Console(console, ()) => {
+            crate::auth::Backend::ControlPlane(console, ()) => {
                 config
                     .jwks_cache
                     .check_jwt(
@@ -129,7 +129,7 @@ impl PoolingBackend {
 
                 Ok(())
             }
-            crate::auth::Backend::Web(_, ()) => Err(AuthError::auth_failed(
+            crate::auth::Backend::ConsoleRedirect(_, ()) => Err(AuthError::auth_failed(
                 "JWT login over web auth proxy is not supported",
             )),
             crate::auth::Backend::Local(_) => {

proxy/src/serverless/conn_pool.rs

@@ -17,7 +17,7 @@ use tokio_postgres::tls::NoTlsStream;
 use tokio_postgres::{AsyncMessage, ReadyForQueryStatus, Socket};
 use tokio_util::sync::CancellationToken;
 
-use crate::console::messages::{ColdStartInfo, MetricsAuxInfo};
+use crate::control_plane::messages::{ColdStartInfo, MetricsAuxInfo};
 use crate::metrics::{HttpEndpointPoolsGuard, Metrics};
 use crate::usage_metrics::{Ids, MetricCounter, USAGE_METRICS};
 use crate::{
@@ -760,7 +760,7 @@ mod tests {
                 endpoint_id: (&EndpointId::from("endpoint")).into(),
                 project_id: (&ProjectId::from("project")).into(),
                 branch_id: (&BranchId::from("branch")).into(),
-                cold_start_info: crate::console::messages::ColdStartInfo::Warm,
+                cold_start_info: crate::control_plane::messages::ColdStartInfo::Warm,
             },
             conn_id: uuid::Uuid::new_v4(),
         }

proxy/src/serverless/http_conn_pool.rs

@@ -8,7 +8,7 @@ use std::sync::atomic::{self, AtomicUsize};
 use std::{sync::Arc, sync::Weak};
 use tokio::net::TcpStream;
 
-use crate::console::messages::{ColdStartInfo, MetricsAuxInfo};
+use crate::control_plane::messages::{ColdStartInfo, MetricsAuxInfo};
 use crate::metrics::{HttpEndpointPoolsGuard, Metrics};
 use crate::usage_metrics::{Ids, MetricCounter, USAGE_METRICS};
 use crate::{context::RequestMonitoring, EndpointCacheKey};

safekeeper/Cargo.toml

@@ -23,6 +23,7 @@ crc32c.workspace = true
 fail.workspace = true
 hex.workspace = true
 humantime.workspace = true
+http.workspace = true
 hyper0.workspace = true
 futures.workspace = true
 once_cell.workspace = true

safekeeper/tests/walproposer_sim/safekeeper.rs

@@ -13,7 +13,7 @@ use desim::{
     node_os::NodeOs,
     proto::{AnyMessage, NetEvent, NodeEvent},
 };
-use hyper0::Uri;
+use http::Uri;
 use safekeeper::{
     safekeeper::{ProposerAcceptorMessage, SafeKeeper, ServerInfo, UNKNOWN_SERVER_VERSION},
     state::{TimelinePersistentState, TimelineState},

storage_broker/Cargo.toml

@@ -10,13 +10,16 @@ bench = []
 [dependencies]
 anyhow.workspace = true
 async-stream.workspace = true
+bytes.workspace = true
 clap = { workspace = true, features = ["derive"] }
 const_format.workspace = true
 futures.workspace = true
 futures-core.workspace = true
 futures-util.workspace = true
 humantime.workspace = true
-hyper0 = { workspace = true, features = ["full"] }
+hyper = { workspace = true, features = ["full"] }
+http-body-util.workspace = true
+hyper-util = "0.1"
 once_cell.workspace = true
 parking_lot.workspace = true
 prost.workspace = true

storage_broker/src/bin/storage_broker.rs

@@ -10,16 +10,15 @@
 //!
 //! Only safekeeper message is supported, but it is not hard to add something
 //! else with generics.
-
-extern crate hyper0 as hyper;
-
 use clap::{command, Parser};
 use futures_core::Stream;
 use futures_util::StreamExt;
+use http_body_util::Full;
+use hyper::body::Incoming;
 use hyper::header::CONTENT_TYPE;
-use hyper::server::conn::AddrStream;
-use hyper::service::{make_service_fn, service_fn};
-use hyper::{Body, Method, StatusCode};
+use hyper::service::service_fn;
+use hyper::{Method, StatusCode};
+use hyper_util::rt::{TokioExecutor, TokioIo, TokioTimer};
 use parking_lot::RwLock;
 use std::collections::HashMap;
 use std::convert::Infallible;
@@ -27,9 +26,11 @@ use std::net::SocketAddr;
 use std::pin::Pin;
 use std::sync::Arc;
 use std::time::Duration;
+use tokio::net::TcpListener;
 use tokio::sync::broadcast;
 use tokio::sync::broadcast::error::RecvError;
 use tokio::time;
+use tonic::body::{self, empty_body, BoxBody};
 use tonic::codegen::Service;
 use tonic::transport::server::Connected;
 use tonic::Code;
@@ -48,9 +49,7 @@ use storage_broker::proto::{
     FilterTenantTimelineId, MessageType, SafekeeperDiscoveryRequest, SafekeeperDiscoveryResponse,
     SafekeeperTimelineInfo, SubscribeByFilterRequest, SubscribeSafekeeperInfoRequest, TypedMessage,
 };
-use storage_broker::{
-    parse_proto_ttid, EitherBody, DEFAULT_KEEPALIVE_INTERVAL, DEFAULT_LISTEN_ADDR,
-};
+use storage_broker::{parse_proto_ttid, DEFAULT_KEEPALIVE_INTERVAL, DEFAULT_LISTEN_ADDR};
 use utils::id::TenantTimelineId;
 use utils::logging::{self, LogFormat};
 use utils::sentry_init::init_sentry;
@@ -602,8 +601,8 @@ impl BrokerService for Broker {
 
 // We serve only metrics and healthcheck through http1.
 async fn http1_handler(
-    req: hyper::Request<hyper::body::Body>,
-) -> Result<hyper::Response<Body>, Infallible> {
+    req: hyper::Request<Incoming>,
+) -> Result<hyper::Response<BoxBody>, Infallible> {
     let resp = match (req.method(), req.uri().path()) {
         (&Method::GET, "/metrics") => {
             let mut buffer = vec![];
@@ -614,16 +613,16 @@ async fn http1_handler(
             hyper::Response::builder()
                 .status(StatusCode::OK)
                 .header(CONTENT_TYPE, encoder.format_type())
-                .body(Body::from(buffer))
+                .body(body::boxed(Full::new(bytes::Bytes::from(buffer))))
                 .unwrap()
         }
         (&Method::GET, "/status") => hyper::Response::builder()
             .status(StatusCode::OK)
-            .body(Body::empty())
+            .body(empty_body())
             .unwrap(),
         _ => hyper::Response::builder()
             .status(StatusCode::NOT_FOUND)
-            .body(Body::empty())
+            .body(empty_body())
             .unwrap(),
     };
     Ok(resp)
@@ -665,52 +664,76 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
     };
     let storage_broker_server = BrokerServiceServer::new(storage_broker_impl);
 
-    info!("listening on {}", &args.listen_addr);
-
     // grpc is served along with http1 for metrics on a single port, hence we
     // don't use tonic's Server.
-    hyper::Server::bind(&args.listen_addr)
-        .http2_keep_alive_interval(Some(args.http2_keepalive_interval))
-        .serve(make_service_fn(move |conn: &AddrStream| {
-            let storage_broker_server_cloned = storage_broker_server.clone();
-            let connect_info = conn.connect_info();
-            async move {
-                Ok::<_, Infallible>(service_fn(move |mut req| {
-                    // That's what tonic's MakeSvc.call does to pass conninfo to
-                    // the request handler (and where its request.remote_addr()
-                    // expects it to find).
-                    req.extensions_mut().insert(connect_info.clone());
-
-                    // Technically this second clone is not needed, but consume
-                    // by async block is apparently unavoidable. BTW, error
-                    // message is enigmatic, see
-                    // https://github.com/rust-lang/rust/issues/68119
-                    //
-                    // We could get away without async block at all, but then we
-                    // need to resort to futures::Either to merge the result,
-                    // which doesn't caress an eye as well.
-                    let mut storage_broker_server_svc = storage_broker_server_cloned.clone();
-                    async move {
-                        if req.headers().get("content-type").map(|x| x.as_bytes())
-                            == Some(b"application/grpc")
-                        {
-                            let res_resp = storage_broker_server_svc.call(req).await;
-                            // Grpc and http1 handlers have slightly different
-                            // Response types: it is UnsyncBoxBody for the
-                            // former one (not sure why) and plain hyper::Body
-                            // for the latter. Both implement HttpBody though,
-                            // and EitherBody is used to merge them.
-                            res_resp.map(|resp| resp.map(EitherBody::Left))
-                        } else {
-                            let res_resp = http1_handler(req).await;
-                            res_resp.map(|resp| resp.map(EitherBody::Right))
-                        }
-                    }
-                }))
+    let tcp_listener = TcpListener::bind(&args.listen_addr).await?;
+    info!("listening on {}", &args.listen_addr);
+    loop {
+        let (stream, addr) = match tcp_listener.accept().await {
+            Ok(v) => v,
+            Err(e) => {
+                info!("couldn't accept connection: {e}");
+                continue;
             }
-        }))
-        .await?;
-    Ok(())
+        };
+
+        let mut builder = hyper_util::server::conn::auto::Builder::new(TokioExecutor::new());
+        builder.http1().timer(TokioTimer::new());
+        builder
+            .http2()
+            .timer(TokioTimer::new())
+            .keep_alive_interval(Some(args.http2_keepalive_interval))
+            // This matches the tonic server default. It allows us to support production-like workloads.
+            .max_concurrent_streams(None);
+
+        let storage_broker_server_cloned = storage_broker_server.clone();
+        let connect_info = stream.connect_info();
+        let service_fn_ = async move {
+            service_fn(move |mut req| {
+                // That's what tonic's MakeSvc.call does to pass conninfo to
+                // the request handler (and where its request.remote_addr()
+                // expects it to find).
+                req.extensions_mut().insert(connect_info.clone());
+
+                // Technically this second clone is not needed, but consume
+                // by async block is apparently unavoidable. BTW, error
+                // message is enigmatic, see
+                // https://github.com/rust-lang/rust/issues/68119
+                //
+                // We could get away without async block at all, but then we
+                // need to resort to futures::Either to merge the result,
+                // which doesn't caress an eye as well.
+                let mut storage_broker_server_svc = storage_broker_server_cloned.clone();
+                async move {
+                    if req.headers().get("content-type").map(|x| x.as_bytes())
+                        == Some(b"application/grpc")
+                    {
+                        let res_resp = storage_broker_server_svc.call(req).await;
+                        // Grpc and http1 handlers have slightly different
+                        // Response types: it is UnsyncBoxBody for the
+                        // former one (not sure why) and plain hyper::Body
+                        // for the latter. Both implement HttpBody though,
+                        // and `Either` is used to merge them.
+                        res_resp.map(|resp| resp.map(http_body_util::Either::Left))
+                    } else {
+                        let res_resp = http1_handler(req).await;
+                        res_resp.map(|resp| resp.map(http_body_util::Either::Right))
+                    }
+                }
+            })
+        }
+        .await;
+
+        tokio::task::spawn(async move {
+            let res = builder
+                .serve_connection(TokioIo::new(stream), service_fn_)
+                .await;
+
+            if let Err(e) = res {
+                info!("error serving connection from {addr}: {e}");
+            }
+        });
+    }
 }
 
 #[cfg(test)]

storage_broker/src/lib.rs

@@ -1,8 +1,3 @@
-extern crate hyper0 as hyper;
-
-use hyper::body::HttpBody;
-use std::pin::Pin;
-use std::task::{Context, Poll};
 use std::time::Duration;
 use tonic::codegen::StdError;
 use tonic::transport::{ClientTlsConfig, Endpoint};
@@ -96,56 +91,3 @@ pub fn parse_proto_ttid(proto_ttid: &ProtoTenantTimelineId) -> Result<TenantTime
         timeline_id,
     })
 }
-
-// These several usages don't justify anyhow dependency, though it would work as
-// well.
-type AnyError = Box<dyn std::error::Error + Send + Sync + 'static>;
-
-// Provides impl HttpBody for two different types implementing it. Inspired by
-// https://github.com/hyperium/tonic/blob/master/examples/src/hyper_warp/server.rs
-pub enum EitherBody<A, B> {
-    Left(A),
-    Right(B),
-}
-
-impl<A, B> HttpBody for EitherBody<A, B>
-where
-    A: HttpBody + Send + Unpin,
-    B: HttpBody<Data = A::Data> + Send + Unpin,
-    A::Error: Into<AnyError>,
-    B::Error: Into<AnyError>,
-{
-    type Data = A::Data;
-    type Error = Box<dyn std::error::Error + Send + Sync + 'static>;
-
-    fn is_end_stream(&self) -> bool {
-        match self {
-            EitherBody::Left(b) => b.is_end_stream(),
-            EitherBody::Right(b) => b.is_end_stream(),
-        }
-    }
-
-    fn poll_data(
-        self: Pin<&mut Self>,
-        cx: &mut Context<'_>,
-    ) -> Poll<Option<Result<Self::Data, Self::Error>>> {
-        match self.get_mut() {
-            EitherBody::Left(b) => Pin::new(b).poll_data(cx).map(map_option_err),
-            EitherBody::Right(b) => Pin::new(b).poll_data(cx).map(map_option_err),
-        }
-    }
-
-    fn poll_trailers(
-        self: Pin<&mut Self>,
-        cx: &mut Context<'_>,
-    ) -> Poll<Result<Option<hyper::HeaderMap>, Self::Error>> {
-        match self.get_mut() {
-            EitherBody::Left(b) => Pin::new(b).poll_trailers(cx).map_err(Into::into),
-            EitherBody::Right(b) => Pin::new(b).poll_trailers(cx).map_err(Into::into),
-        }
-    }
-}
-
-fn map_option_err<T, U: Into<AnyError>>(err: Option<Result<T, U>>) -> Option<Result<T, AnyError>> {
-    err.map(|e| e.map_err(Into::into))
-}

test_runner/conftest.py

@@ -5,7 +5,6 @@ pytest_plugins = (
     "fixtures.compute_reconfigure",
     "fixtures.storage_controller_proxy",
     "fixtures.neon_fixtures",
-    "fixtures.neon_tenant",
     "fixtures.benchmark_fixture",
     "fixtures.pg_stats",
     "fixtures.compare_fixtures",

test_runner/fixtures/neon_fixtures.py

@@ -398,7 +398,7 @@ class NeonEnvBuilder:
         pageserver_default_tenant_config_compaction_algorithm: Optional[Dict[str, Any]] = None,
         safekeeper_extra_opts: Optional[list[str]] = None,
         storage_controller_port_override: Optional[int] = None,
-        pageserver_io_buffer_alignment: Optional[int] = None,
+        pageserver_virtual_file_io_mode: Optional[str] = None,
     ):
         self.repo_dir = repo_dir
         self.rust_log_override = rust_log_override
@@ -452,12 +452,11 @@ class NeonEnvBuilder:
 
         self.storage_controller_port_override = storage_controller_port_override
 
-        self.pageserver_io_buffer_alignment = pageserver_io_buffer_alignment
+        self.pageserver_virtual_file_io_mode = pageserver_virtual_file_io_mode
 
-        # FIXME
-        # assert test_name.startswith(
-        #    "test_"
-        # ), "Unexpectedly instantiated from outside a test function"
+        assert test_name.startswith(
+            "test_"
+        ), "Unexpectedly instantiated from outside a test function"
         self.test_name = test_name
 
     def init_configs(self, default_remote_storage_if_missing: bool = True) -> NeonEnv:
@@ -1042,7 +1041,7 @@ class NeonEnv:
 
         self.pageserver_virtual_file_io_engine = config.pageserver_virtual_file_io_engine
         self.pageserver_aux_file_policy = config.pageserver_aux_file_policy
-        self.pageserver_io_buffer_alignment = config.pageserver_io_buffer_alignment
+        self.pageserver_virtual_file_io_mode = config.pageserver_virtual_file_io_mode
 
         # Create the neon_local's `NeonLocalInitConf`
         cfg: Dict[str, Any] = {
@@ -1106,7 +1105,8 @@ class NeonEnv:
                         for key, value in override.items():
                             ps_cfg[key] = value
 
-            ps_cfg["io_buffer_alignment"] = self.pageserver_io_buffer_alignment
+            if self.pageserver_virtual_file_io_mode is not None:
+                ps_cfg["virtual_file_io_mode"] = self.pageserver_virtual_file_io_mode
 
             # Create a corresponding NeonPageserver object
             self.pageservers.append(
@@ -1412,7 +1412,7 @@ def neon_simple_env(
     pageserver_virtual_file_io_engine: str,
     pageserver_aux_file_policy: Optional[AuxFileStore],
     pageserver_default_tenant_config_compaction_algorithm: Optional[Dict[str, Any]],
-    pageserver_io_buffer_alignment: Optional[int],
+    pageserver_virtual_file_io_mode: Optional[str],
 ) -> Iterator[NeonEnv]:
     """
     Simple Neon environment, with no authentication and no safekeepers.
@@ -1438,7 +1438,7 @@ def neon_simple_env(
         pageserver_virtual_file_io_engine=pageserver_virtual_file_io_engine,
         pageserver_aux_file_policy=pageserver_aux_file_policy,
         pageserver_default_tenant_config_compaction_algorithm=pageserver_default_tenant_config_compaction_algorithm,
-        pageserver_io_buffer_alignment=pageserver_io_buffer_alignment,
+        pageserver_virtual_file_io_mode=pageserver_virtual_file_io_mode,
     ) as builder:
         env = builder.init_start()
 
@@ -1462,7 +1462,7 @@ def neon_env_builder(
     pageserver_default_tenant_config_compaction_algorithm: Optional[Dict[str, Any]],
     pageserver_aux_file_policy: Optional[AuxFileStore],
     record_property: Callable[[str, object], None],
-    pageserver_io_buffer_alignment: Optional[int],
+    pageserver_virtual_file_io_mode: Optional[str],
 ) -> Iterator[NeonEnvBuilder]:
     """
     Fixture to create a Neon environment for test.
@@ -1497,7 +1497,7 @@ def neon_env_builder(
         test_overlay_dir=test_overlay_dir,
         pageserver_aux_file_policy=pageserver_aux_file_policy,
         pageserver_default_tenant_config_compaction_algorithm=pageserver_default_tenant_config_compaction_algorithm,
-        pageserver_io_buffer_alignment=pageserver_io_buffer_alignment,
+        pageserver_virtual_file_io_mode=pageserver_virtual_file_io_mode,
     ) as builder:
         yield builder
         # Propogate `preserve_database_files` to make it possible to use in other fixtures,

test_runner/fixtures/neon_tenant.py

@@ -1,352 +0,0 @@
-from __future__ import annotations
-
-import random
-import string
-import threading
-import uuid
-from dataclasses import dataclass
-from pathlib import Path
-from types import TracebackType
-from typing import (
-    Any,
-    Dict,
-    Iterator,
-    List,
-    Optional,
-    Type,
-    cast,
-)
-
-import pytest
-from _pytest.config import Config
-from _pytest.fixtures import FixtureRequest
-
-from fixtures.common_types import Lsn, TenantId, TimelineId
-from fixtures.log_helper import log
-from fixtures.neon_fixtures import Endpoint, NeonEnv, NeonEnvBuilder
-from fixtures.pg_version import PgVersion
-from fixtures.port_distributor import PortDistributor
-from fixtures.remote_storage import (
-    MockS3Server,
-)
-from fixtures.utils import AuxFileStore
-
-DEFAULT_BRANCH_NAME: str = "main"
-
-
-@pytest.fixture(scope="function")
-def neon_tenant(shared_env: NeonEnv) -> Iterator[NeonTestTenant]:
-    tenant = NeonTestTenant(shared_env)
-    tenant.create()
-    yield tenant
-    # TODO:  clean up the tenant
-
-
-@dataclass(frozen=True)
-class NeonEnvDiscriminants:
-    """The options that define which environments can be shared"""
-
-    neon_binpath: Path
-    pageserver_virtual_file_io_engine: str
-    pageserver_aux_file_policy: Optional[AuxFileStore]
-    pageserver_default_tenant_config_compaction_algorithm: Optional[Dict[str, Any]]
-    pageserver_io_buffer_alignment: Optional[int]
-
-
-class NeonSharedEnvs:
-    def __init__(
-        self,
-        port_distributor: PortDistributor,
-        run_id: uuid.UUID,
-        mock_s3_server: MockS3Server,
-        pg_distrib_dir: Path,
-        top_output_dir: Path,
-        preserve_database_files: bool,
-    ):
-        self.port_distributor = port_distributor
-        self.run_id = run_id
-        self.mock_s3_server = mock_s3_server
-        self.pg_distrib_dir = pg_distrib_dir
-        self.top_output_dir = top_output_dir
-        self.preserve_database_files = preserve_database_files
-
-        self.lock = threading.Lock()
-        self.envs: Dict[NeonEnvDiscriminants, NeonEnv] = {}
-
-        self.builders: List[NeonEnvBuilder] = []
-
-    def get_repo_dir(self, disc: NeonEnvDiscriminants) -> Path:
-        # FIXME use discriminants
-        randstr = "".join(
-            random.SystemRandom().choice(string.ascii_uppercase + string.digits) for _ in range(10)
-        )
-        s = Path(f"shared-{randstr}")
-        return self.top_output_dir / s
-
-    def get_or_create(self, disc: NeonEnvDiscriminants) -> NeonEnv:
-        with self.lock:
-            env = self.envs.get(disc)
-            if env is None:
-                builder = NeonEnvBuilder(
-                    repo_dir=self.get_repo_dir(disc),
-                    port_distributor=self.port_distributor,
-                    run_id=self.run_id,
-                    mock_s3_server=self.mock_s3_server,
-                    pg_distrib_dir=self.pg_distrib_dir,
-                    preserve_database_files=self.preserve_database_files,
-                    pg_version=PgVersion("17"),  # FIXME: this should go unused. Pass None?
-                    test_name="shared",  # FIXME
-                    test_output_dir=Path("shared"),  # FIXME
-                    test_overlay_dir=None,
-                    top_output_dir=self.top_output_dir,
-                    neon_binpath=disc.neon_binpath,
-                    pageserver_virtual_file_io_engine=disc.pageserver_virtual_file_io_engine,
-                    pageserver_aux_file_policy=disc.pageserver_aux_file_policy,
-                    pageserver_default_tenant_config_compaction_algorithm=disc.pageserver_default_tenant_config_compaction_algorithm,
-                    # FIXME: only support defaults for these currently
-                    # pageserver_remote_storage
-                    # pageserver_config_override
-                    # num_safekeepers
-                    # num_pageservers
-                    # safekeepers_id_start
-                    # safekeepers_enable_fsync
-                    # auth_enabled
-                    # rust_log_override
-                    # default_branch_name
-                    initial_tenant=None,  # FIXME should go unused
-                    initial_timeline=None,  # FIXME should go unused
-                    # safekeeper_extra_opts: Optional[list[str]] = None,
-                    # storage_controller_port_override: Optional[int] = None,
-                    # pageserver_io_buffer_alignment: Optional[int] = None,
-                )
-                env = builder.init_start()
-
-                self.envs[disc] = env
-        return env
-
-    def __enter__(self) -> "NeonSharedEnvs":
-        return self
-
-    def __exit__(
-        self,
-        exc_type: Optional[Type[BaseException]],
-        exc: Optional[BaseException],
-        tb: Optional[TracebackType],
-    ):
-        for env in self.envs.values():
-            env.stop(immediate=True)
-
-
-@pytest.fixture(scope="session")
-def shared_environments(
-    # session fixtures
-    port_distributor: PortDistributor,
-    run_id: uuid.UUID,
-    mock_s3_server: MockS3Server,
-    pg_distrib_dir: Path,
-    top_output_dir: Path,
-    pytestconfig: Config,
-) -> Iterator[NeonSharedEnvs]:
-    with NeonSharedEnvs(
-        port_distributor=port_distributor,
-        run_id=run_id,
-        mock_s3_server=mock_s3_server,
-        pg_distrib_dir=pg_distrib_dir,
-        top_output_dir=top_output_dir,
-        # rust_log_override=rust_log_override, # FIXME
-        preserve_database_files=cast(bool, pytestconfig.getoption("--preserve-database-files")),
-    ) as envs:
-        yield envs
-
-
-@pytest.fixture(scope="function")
-def shared_env(
-    request: FixtureRequest,
-    # session fixture holding all the envs
-    shared_environments: NeonSharedEnvs,
-    # other session fixtures
-    port_distributor: PortDistributor,
-    mock_s3_server: MockS3Server,
-    run_id: uuid.UUID,
-    top_output_dir: Path,
-    pg_distrib_dir: Path,
-    # these define the env to use
-    neon_binpath: Path,
-    pageserver_virtual_file_io_engine: str,
-    pageserver_aux_file_policy: Optional[AuxFileStore],
-    pageserver_default_tenant_config_compaction_algorithm: Optional[Dict[str, Any]],
-    pageserver_io_buffer_alignment: Optional[int],
-) -> NeonEnv:
-    disc = NeonEnvDiscriminants(
-        neon_binpath=neon_binpath,
-        # FIXME: There's no difference in e.g. having pageserver_virtual_file_io_engine=None, and
-        # explicitly specifying whatever the default is. We could share those envs.
-        pageserver_virtual_file_io_engine=pageserver_virtual_file_io_engine,
-        pageserver_aux_file_policy=pageserver_aux_file_policy,
-        pageserver_default_tenant_config_compaction_algorithm=pageserver_default_tenant_config_compaction_algorithm,
-        pageserver_io_buffer_alignment=pageserver_io_buffer_alignment,
-    )
-    return shared_environments.get_or_create(disc)
-
-
-class NeonTestTenant:
-    """
-    An object representing a single Neon tenant, in a shared environment
-
-    Notable functions and fields:
-
-    endpoints - A factory object for creating postgres compute nodes.
-
-    tenant_id - tenant ID of the initial tenant created in the repository
-
-    initial_timeline - timeline ID of the "main" branch
-
-    create_branch() - branch a new timeline from an existing one, returns
-        the new timeline id
-
-    create_timeline() - initializes a new timeline by running initdb, returns
-        the new timeline id
-    """
-
-    def __init__(self, env: NeonEnv):
-        self.tenant_id = TenantId.generate()
-        self.initial_timeline = TimelineId.generate()
-        self.created = False
-
-        self.endpoints = TenantEndpointFactory(self)
-        self.env = env
-
-    def create(
-        self,
-        conf: Optional[Dict[str, Any]] = None,
-        shard_count: Optional[int] = None,
-        shard_stripe_size: Optional[int] = None,
-        placement_policy: Optional[str] = None,
-        aux_file_policy: Optional[AuxFileStore] = None,
-    ):
-        assert not self.created
-        self.env.create_tenant(
-            tenant_id=self.tenant_id,
-            timeline_id=self.initial_timeline,
-            conf=conf,
-            shard_count=shard_count,
-            shard_stripe_size=shard_stripe_size,
-            placement_policy=placement_policy,
-            set_default=False,
-            aux_file_policy=aux_file_policy,
-        )
-        self.created = True
-
-    # Todo: this could be imeplemented
-    # def config_tenant(self, conf: Dict[str, str]):
-
-    def create_branch(
-        self,
-        new_branch_name: str = DEFAULT_BRANCH_NAME,
-        ancestor_branch_name: Optional[str] = None,
-        ancestor_start_lsn: Optional[Lsn] = None,
-        new_timeline_id: Optional[TimelineId] = None,
-    ) -> TimelineId:
-        return self.env.create_branch(
-            new_branch_name=new_branch_name,
-            tenant_id=self.tenant_id,
-            ancestor_branch_name=ancestor_branch_name,
-            ancestor_start_lsn=ancestor_start_lsn,
-            new_timeline_id=new_timeline_id,
-        )
-
-    def create_timeline(
-        self,
-        new_branch_name: str,
-        timeline_id: Optional[TimelineId] = None,
-    ) -> TimelineId:
-        return self.env.create_timeline(new_branch_name=new_branch_name, timeline_id=timeline_id)
-
-
-class TenantEndpointFactory:
-    """An object representing multiple compute endpoints of a single tenant."""
-
-    def __init__(self, tenant: NeonTestTenant):
-        self.tenant = tenant
-        self.num_instances: int = 0
-        self.endpoints: List[Endpoint] = []
-
-    def create(
-        self,
-        branch_name: str,
-        endpoint_id: Optional[str] = None,
-        lsn: Optional[Lsn] = None,
-        hot_standby: bool = False,
-        config_lines: Optional[List[str]] = None,
-    ) -> Endpoint:
-        ep = Endpoint(
-            self.tenant.env,
-            tenant_id=self.tenant.tenant_id,
-            pg_port=self.tenant.env.port_distributor.get_port(),
-            http_port=self.tenant.env.port_distributor.get_port(),
-        )
-
-        endpoint_id = endpoint_id or self.tenant.env.generate_endpoint_id()
-
-        self.num_instances += 1
-        self.endpoints.append(ep)
-
-        return ep.create(
-            branch_name=branch_name,
-            endpoint_id=endpoint_id,
-            lsn=lsn,
-            hot_standby=hot_standby,
-            config_lines=config_lines,
-        )
-
-    # FIXME: extra args for start
-    # remote_ext_config: Optional[str] = None,
-    # basebackup_request_tries: Optional[int] = None,
-    def create_start(self, *args, **kwargs):
-        ep = self.create(*args, **kwargs)
-        ep.start()
-        return ep
-
-    def stop_all(self, fail_on_error=True) -> "TenantEndpointFactory":
-        exception = None
-        for ep in self.endpoints:
-            try:
-                ep.stop()
-            except Exception as e:
-                log.error(f"Failed to stop endpoint {ep.endpoint_id}: {e}")
-                exception = e
-
-        if fail_on_error and exception is not None:
-            raise exception
-
-        return self
-
-    def new_replica(
-        self, origin: Endpoint, endpoint_id: str, config_lines: Optional[List[str]] = None
-    ):
-        branch_name = origin.branch_name
-        assert origin in self.endpoints
-        assert branch_name is not None
-
-        return self.create(
-            branch_name=branch_name,
-            endpoint_id=endpoint_id,
-            lsn=None,
-            hot_standby=True,
-            config_lines=config_lines,
-        )
-
-    def new_replica_start(
-        self, origin: Endpoint, endpoint_id: str, config_lines: Optional[List[str]] = None
-    ):
-        branch_name = origin.branch_name
-        assert origin in self.endpoints
-        assert branch_name is not None
-
-        return self.create_start(
-            branch_name=branch_name,
-            endpoint_id=endpoint_id,
-            lsn=None,
-            hot_standby=True,
-            config_lines=config_lines,
-        )

test_runner/fixtures/parametrize.py

@@ -35,8 +35,8 @@ def pageserver_virtual_file_io_engine() -> Optional[str]:
 
 
 @pytest.fixture(scope="function", autouse=True)
-def pageserver_io_buffer_alignment() -> Optional[int]:
-    return None
+def pageserver_virtual_file_io_mode() -> Optional[str]:
+    return os.getenv("PAGESERVER_VIRTUAL_FILE_IO_MODE")
 
 
 @pytest.fixture(scope="function", autouse=True)

test_runner/regress/test_clog_truncate.py

@@ -2,14 +2,16 @@ import os
 import time
 
 from fixtures.log_helper import log
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv
 from fixtures.utils import query_scalar
 
 
 #
 # Test compute node start after clog truncation
 #
-def test_clog_truncate(neon_tenant: NeonTestTenant):
+def test_clog_truncate(neon_simple_env: NeonEnv):
+    env = neon_simple_env
+
     # set aggressive autovacuum to make sure that truncation will happen
     config = [
         "autovacuum_max_workers=10",
@@ -21,7 +23,7 @@ def test_clog_truncate(neon_tenant: NeonTestTenant):
         "autovacuum_freeze_max_age=100000",
     ]
 
-    endpoint = neon_tenant.endpoints.create_start("main", config_lines=config)
+    endpoint = env.endpoints.create_start("main", config_lines=config)
 
     # Install extension containing function needed for test
     endpoint.safe_psql("CREATE EXTENSION neon_test_utils")
@@ -54,12 +56,12 @@ def test_clog_truncate(neon_tenant: NeonTestTenant):
 
     # create new branch after clog truncation and start a compute node on it
     log.info(f"create branch at lsn_after_truncation {lsn_after_truncation}")
-    neon_tenant.create_branch(
+    env.create_branch(
         "test_clog_truncate_new",
         ancestor_branch_name="main",
         ancestor_start_lsn=lsn_after_truncation,
     )
-    endpoint2 = neon_tenant.endpoints.create_start("test_clog_truncate_new")
+    endpoint2 = env.endpoints.create_start("test_clog_truncate_new")
 
     # check that new node doesn't contain truncated segment
     pg_xact_0000_path_new = os.path.join(endpoint2.pg_xact_dir_path(), "0000")

test_runner/regress/test_compute_catalog.py

@@ -1,9 +1,11 @@
 import requests
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv
 
 
-def test_compute_catalog(neon_tenant: NeonTestTenant):
-    endpoint = neon_tenant.endpoints.create_start("main", config_lines=["log_min_messages=debug1"])
+def test_compute_catalog(neon_simple_env: NeonEnv):
+    env = neon_simple_env
+
+    endpoint = env.endpoints.create_start("main", config_lines=["log_min_messages=debug1"])
     client = endpoint.http_client()
 
     objects = client.dbs_and_roles()

test_runner/regress/test_createdropdb.py

@@ -4,7 +4,6 @@ import pathlib
 import pytest
 from fixtures.log_helper import log
 from fixtures.neon_fixtures import NeonEnv, check_restored_datadir_content
-from fixtures.neon_tenant import NeonTestTenant
 from fixtures.pg_version import PgVersion
 from fixtures.utils import query_scalar
 
@@ -13,17 +12,18 @@ from fixtures.utils import query_scalar
 # Test CREATE DATABASE when there have been relmapper changes
 #
 @pytest.mark.parametrize("strategy", ["file_copy", "wal_log"])
-def test_createdb(neon_tenant: NeonTestTenant, strategy: str, pg_version: PgVersion):
-    if pg_version == PgVersion.V14 and strategy == "wal_log":
+def test_createdb(neon_simple_env: NeonEnv, strategy: str):
+    env = neon_simple_env
+    if env.pg_version == PgVersion.V14 and strategy == "wal_log":
         pytest.skip("wal_log strategy not supported on PostgreSQL 14")
 
-    endpoint = neon_tenant.endpoints.create_start("main")
+    endpoint = env.endpoints.create_start("main")
 
     with endpoint.cursor() as cur:
         # Cause a 'relmapper' change in the original branch
         cur.execute("VACUUM FULL pg_class")
 
-        if pg_version == PgVersion.V14:
+        if env.pg_version == PgVersion.V14:
             cur.execute("CREATE DATABASE foodb")
         else:
             cur.execute(f"CREATE DATABASE foodb STRATEGY={strategy}")
@@ -31,8 +31,8 @@ def test_createdb(neon_tenant: NeonTestTenant, strategy: str, pg_version: PgVers
         lsn = query_scalar(cur, "SELECT pg_current_wal_insert_lsn()")
 
     # Create a branch
-    neon_tenant.create_branch("test_createdb2", ancestor_branch_name="main", ancestor_start_lsn=lsn)
-    endpoint2 = neon_tenant.endpoints.create_start("test_createdb2")
+    env.create_branch("test_createdb2", ancestor_branch_name="main", ancestor_start_lsn=lsn)
+    endpoint2 = env.endpoints.create_start("test_createdb2")
 
     # Test that you can connect to the new database on both branches
     for db in (endpoint, endpoint2):

test_runner/regress/test_createuser.py

@@ -1,12 +1,13 @@
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv
 from fixtures.utils import query_scalar
 
 
 #
 # Test CREATE USER to check shared catalog restore
 #
-def test_createuser(neon_tenant: NeonTestTenant):
-    endpoint = neon_tenant.endpoints.create_start("main")
+def test_createuser(neon_simple_env: NeonEnv):
+    env = neon_simple_env
+    endpoint = env.endpoints.create_start("main")
 
     with endpoint.cursor() as cur:
         # Cause a 'relmapper' change in the original branch
@@ -17,10 +18,8 @@ def test_createuser(neon_tenant: NeonTestTenant):
         lsn = query_scalar(cur, "SELECT pg_current_wal_insert_lsn()")
 
     # Create a branch
-    neon_tenant.create_branch(
-        "test_createuser2", ancestor_branch_name="main", ancestor_start_lsn=lsn
-    )
-    endpoint2 = neon_tenant.endpoints.create_start("test_createuser2")
+    env.create_branch("test_createuser2", ancestor_branch_name="main", ancestor_start_lsn=lsn)
+    endpoint2 = env.endpoints.create_start("test_createuser2")
 
     # Test that you can connect to new branch as a new user
     assert endpoint2.safe_psql("select current_user", user="testuser") == [("testuser",)]

test_runner/regress/test_ddl_forwarding.py

@@ -4,8 +4,7 @@ from typing import Any, Dict, List, Optional, Tuple, Type
 import psycopg2
 import pytest
 from fixtures.log_helper import log
-from fixtures.neon_fixtures import VanillaPostgres
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv, VanillaPostgres
 from pytest_httpserver import HTTPServer
 from werkzeug.wrappers.request import Request
 from werkzeug.wrappers.response import Response
@@ -289,8 +288,9 @@ def assert_db_connlimit(endpoint: Any, db_name: str, connlimit: int, msg: str):
 # 2. User can ignore, then compute_ctl will drop invalid databases
 #    automatically during full configuration
 # Here we test the latter. The first one is tested in test_ddl_forwarding
-def test_ddl_forwarding_invalid_db(neon_tenant: NeonTestTenant):
-    endpoint = neon_tenant.endpoints.create_start(
+def test_ddl_forwarding_invalid_db(neon_simple_env: NeonEnv):
+    env = neon_simple_env
+    endpoint = env.endpoints.create_start(
         "main",
         # Some non-existent url
         config_lines=["neon.console_url=http://localhost:9999/unknown/api/v0/roles_and_databases"],

test_runner/regress/test_endpoint_crash.py

@@ -1,5 +1,5 @@
 import pytest
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnvBuilder
 
 
 @pytest.mark.parametrize(
@@ -10,12 +10,13 @@ from fixtures.neon_tenant import NeonTestTenant
         "💣",  # calls `trigger_segfault` internally
     ],
 )
-def test_endpoint_crash(neon_tenant: NeonTestTenant, sql_func: str):
+def test_endpoint_crash(neon_env_builder: NeonEnvBuilder, sql_func: str):
     """
     Test that triggering crash from neon_test_utils crashes the endpoint
     """
-    neon_tenant.create_branch("test_endpoint_crash")
-    endpoint = neon_tenant.endpoints.create_start("test_endpoint_crash")
+    env = neon_env_builder.init_start()
+    env.create_branch("test_endpoint_crash")
+    endpoint = env.endpoints.create_start("test_endpoint_crash")
 
     endpoint.safe_psql("CREATE EXTENSION neon_test_utils;")
     with pytest.raises(Exception, match="This probably means the server terminated abnormally"):

test_runner/regress/test_fsm_truncate.py

@@ -1,9 +1,10 @@
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnvBuilder
 
 
-def test_fsm_truncate(neon_tenant: NeonTestTenant):
-    neon_tenant.create_branch("test_fsm_truncate")
-    endpoint = neon_tenant.endpoints.create_start("test_fsm_truncate")
+def test_fsm_truncate(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init_start()
+    env.create_branch("test_fsm_truncate")
+    endpoint = env.endpoints.create_start("test_fsm_truncate")
     endpoint.safe_psql(
         "CREATE TABLE t1(key int); CREATE TABLE t2(key int); TRUNCATE TABLE t1; TRUNCATE TABLE t2;"
     )

test_runner/regress/test_gin_redo.py

@@ -1,16 +1,17 @@
 import time
 
-from fixtures.neon_fixtures import wait_replica_caughtup
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv, wait_replica_caughtup
 
 
 #
 # Test that redo of XLOG_GIN_VACUUM_PAGE doesn't produce error
 #
-def test_gin_redo(neon_tenant: NeonTestTenant):
-    primary = neon_tenant.endpoints.create_start(branch_name="main", endpoint_id="primary")
+def test_gin_redo(neon_simple_env: NeonEnv):
+    env = neon_simple_env
+
+    primary = env.endpoints.create_start(branch_name="main", endpoint_id="primary")
     time.sleep(1)
-    secondary = neon_tenant.endpoints.new_replica_start(origin=primary, endpoint_id="secondary")
+    secondary = env.endpoints.new_replica_start(origin=primary, endpoint_id="secondary")
     con = primary.connect()
     cur = con.cursor()
     cur.execute("create table gin_test_tbl(id integer, i int4[])")

test_runner/regress/test_lfc_resize.py

@@ -7,16 +7,16 @@ import time
 
 import pytest
 from fixtures.log_helper import log
-from fixtures.neon_fixtures import PgBin
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv, PgBin
 
 
 @pytest.mark.timeout(600)
-def test_lfc_resize(neon_tenant: NeonTestTenant, pg_bin: PgBin):
+def test_lfc_resize(neon_simple_env: NeonEnv, pg_bin: PgBin):
     """
     Test resizing the Local File Cache
     """
-    endpoint = neon_tenant.endpoints.create_start(
+    env = neon_simple_env
+    endpoint = env.endpoints.create_start(
         "main",
         config_lines=[
             "neon.file_cache_path='file.cache'",

test_runner/regress/test_local_file_cache.py

@@ -3,18 +3,19 @@ import queue
 import random
 import threading
 import time
-from pathlib import Path
 from typing import List
 
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnvBuilder
 from fixtures.utils import query_scalar
 
 
-def test_local_file_cache_unlink(neon_tenant: NeonTestTenant, test_output_dir: Path):
-    cache_dir = test_output_dir / Path("file_cache")
+def test_local_file_cache_unlink(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init_start()
+
+    cache_dir = os.path.join(env.repo_dir, "file_cache")
     os.mkdir(cache_dir)
 
-    endpoint = neon_tenant.endpoints.create_start(
+    endpoint = env.endpoints.create_start(
         "main",
         config_lines=[
             "shared_buffers='1MB'",
@@ -65,7 +66,7 @@ def test_local_file_cache_unlink(neon_tenant: NeonTestTenant, test_output_dir: P
     time.sleep(5)
 
     # unlink, this is what we're actually testing
-    new_cache_dir = test_output_dir / Path("file_cache_new")
+    new_cache_dir = os.path.join(env.repo_dir, "file_cache_new")
     os.rename(cache_dir, new_cache_dir)
 
     time.sleep(10)

test_runner/regress/test_logical_replication.py

@@ -14,7 +14,6 @@ from fixtures.neon_fixtures import (
     logical_replication_sync,
     wait_for_last_flush_lsn,
 )
-from fixtures.neon_tenant import NeonTestTenant
 from fixtures.utils import wait_until
 
 
@@ -395,9 +394,11 @@ def test_restart_endpoint(neon_simple_env: NeonEnv, vanilla_pg):
 # records passed ot the WAL redo process are never large enough to hit
 # the bug.
 @pytest.mark.parametrize("pageserver_aux_file_policy", [AuxFileStore.CrossValidation])
-def test_large_records(neon_tenant: NeonTestTenant, vanilla_pg):
-    neon_tenant.create_branch("init")
-    endpoint = neon_tenant.endpoints.create_start("init")
+def test_large_records(neon_simple_env: NeonEnv, vanilla_pg):
+    env = neon_simple_env
+
+    env.create_branch("init")
+    endpoint = env.endpoints.create_start("init")
 
     cur = endpoint.connect().cursor()
     cur.execute("CREATE TABLE reptbl(id int, largeval text);")
@@ -465,13 +466,14 @@ def test_slots_and_branching(neon_simple_env: NeonEnv):
 
 
 @pytest.mark.parametrize("pageserver_aux_file_policy", [AuxFileStore.CrossValidation])
-def test_replication_shutdown(neon_tenant: NeonTestTenant):
+def test_replication_shutdown(neon_simple_env: NeonEnv):
     # Ensure Postgres can exit without stuck when a replication job is active + neon extension installed
-    neon_tenant.create_branch("test_replication_shutdown_publisher", ancestor_branch_name="main")
-    pub = neon_tenant.endpoints.create("test_replication_shutdown_publisher")
+    env = neon_simple_env
+    env.create_branch("test_replication_shutdown_publisher", ancestor_branch_name="main")
+    pub = env.endpoints.create("test_replication_shutdown_publisher")
 
-    neon_tenant.create_branch("test_replication_shutdown_subscriber")
-    sub = neon_tenant.endpoints.create("test_replication_shutdown_subscriber")
+    env.create_branch("test_replication_shutdown_subscriber")
+    sub = env.endpoints.create("test_replication_shutdown_subscriber")
 
     pub.respec(skip_pg_catalog_updates=False)
     pub.start()

test_runner/regress/test_neon_extension.py

@@ -2,14 +2,15 @@ import time
 from contextlib import closing
 
 from fixtures.log_helper import log
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnvBuilder
 
 
 # Verify that the neon extension is installed and has the correct version.
-def test_neon_extension(neon_tenant: NeonTestTenant):
-    neon_tenant.create_branch("test_create_extension_neon")
+def test_neon_extension(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init_start()
+    env.create_branch("test_create_extension_neon")
 
-    endpoint_main = neon_tenant.endpoints.create("test_create_extension_neon")
+    endpoint_main = env.endpoints.create("test_create_extension_neon")
     # don't skip pg_catalog updates - it runs CREATE EXTENSION neon
     endpoint_main.respec(skip_pg_catalog_updates=False)
     endpoint_main.start()
@@ -32,10 +33,11 @@ def test_neon_extension(neon_tenant: NeonTestTenant):
 
 
 # Verify that the neon extension can be upgraded/downgraded.
-def test_neon_extension_compatibility(neon_tenant: NeonTestTenant):
-    neon_tenant.create_branch("test_neon_extension_compatibility")
+def test_neon_extension_compatibility(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init_start()
+    env.create_branch("test_neon_extension_compatibility")
 
-    endpoint_main = neon_tenant.endpoints.create("test_neon_extension_compatibility")
+    endpoint_main = env.endpoints.create("test_neon_extension_compatibility")
     # don't skip pg_catalog updates - it runs CREATE EXTENSION neon
     endpoint_main.respec(skip_pg_catalog_updates=False)
     endpoint_main.start()
@@ -68,10 +70,11 @@ def test_neon_extension_compatibility(neon_tenant: NeonTestTenant):
 
 
 # Verify that the neon extension can be auto-upgraded to the latest version.
-def test_neon_extension_auto_upgrade(neon_tenant: NeonTestTenant):
-    neon_tenant.create_branch("test_neon_extension_auto_upgrade")
+def test_neon_extension_auto_upgrade(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init_start()
+    env.create_branch("test_neon_extension_auto_upgrade")
 
-    endpoint_main = neon_tenant.endpoints.create("test_neon_extension_auto_upgrade")
+    endpoint_main = env.endpoints.create("test_neon_extension_auto_upgrade")
     # don't skip pg_catalog updates - it runs CREATE EXTENSION neon
     endpoint_main.respec(skip_pg_catalog_updates=False)
     endpoint_main.start()

test_runner/regress/test_neon_superuser.py

@@ -1,15 +1,16 @@
 from fixtures.log_helper import log
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnv
 from fixtures.pg_version import PgVersion
 from fixtures.utils import wait_until
 
 
-def test_neon_superuser(neon_tenant: NeonTestTenant, pg_version: PgVersion):
-    neon_tenant.create_branch("test_neon_superuser_publisher", ancestor_branch_name="main")
-    pub = neon_tenant.endpoints.create("test_neon_superuser_publisher")
+def test_neon_superuser(neon_simple_env: NeonEnv, pg_version: PgVersion):
+    env = neon_simple_env
+    env.create_branch("test_neon_superuser_publisher", ancestor_branch_name="main")
+    pub = env.endpoints.create("test_neon_superuser_publisher")
 
-    neon_tenant.create_branch("test_neon_superuser_subscriber")
-    sub = neon_tenant.endpoints.create("test_neon_superuser_subscriber")
+    env.create_branch("test_neon_superuser_subscriber")
+    sub = env.endpoints.create("test_neon_superuser_subscriber")
 
     pub.respec(skip_pg_catalog_updates=False)
     pub.start()

test_runner/regress/test_oid_overflow.py

@@ -1,9 +1,11 @@
 from fixtures.log_helper import log
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import NeonEnvBuilder
 
 
-def test_oid_overflow(neon_tenant: NeonTestTenant):
-    endpoint = neon_tenant.endpoints.create_start("main")
+def test_oid_overflow(neon_env_builder: NeonEnvBuilder):
+    env = neon_env_builder.init_start()
+
+    endpoint = env.endpoints.create_start("main")
 
     conn = endpoint.connect()
     cur = conn.cursor()

test_runner/regress/test_parallel_copy.py

@@ -1,8 +1,7 @@
 import asyncio
 from io import BytesIO
 
-from fixtures.neon_fixtures import Endpoint
-from fixtures.neon_tenant import NeonTestTenant
+from fixtures.neon_fixtures import Endpoint, NeonEnv
 
 
 async def repeat_bytes(buf, repetitions: int):
@@ -40,8 +39,9 @@ async def parallel_load_same_table(endpoint: Endpoint, n_parallel: int):
 
 
 # Load data into one table with COPY TO from 5 parallel connections
-def test_parallel_copy(neon_tenant: NeonTestTenant, n_parallel=5):
-    endpoint = neon_tenant.endpoints.create_start("main")
+def test_parallel_copy(neon_simple_env: NeonEnv, n_parallel=5):
+    env = neon_simple_env
+    endpoint = env.endpoints.create_start("main")
 
     # Create test table
     conn = endpoint.connect()

test_runner/regress/test_vm_bits.py

@@ -3,7 +3,6 @@ from contextlib import closing
 
 from fixtures.log_helper import log
 from fixtures.neon_fixtures import NeonEnv, NeonEnvBuilder, fork_at_current_lsn
-from fixtures.neon_tenant import NeonTestTenant
 from fixtures.utils import query_scalar
 
 
@@ -115,13 +114,14 @@ def test_vm_bit_clear(neon_simple_env: NeonEnv):
     assert cur_new.fetchall() == []
 
 
-def test_vm_bit_clear_on_heap_lock_whitebox(neon_tenant: NeonTestTenant):
+def test_vm_bit_clear_on_heap_lock_whitebox(neon_env_builder: NeonEnvBuilder):
     """
     Test that the ALL_FROZEN VM bit is cleared correctly at a HEAP_LOCK record.
 
     This is a repro for the bug fixed in commit 66fa176cc8.
     """
-    endpoint = neon_tenant.endpoints.create_start(
+    env = neon_env_builder.init_start()
+    endpoint = env.endpoints.create_start(
         "main",
         config_lines=[
             # If auto-analyze runs at the same time that we run VACUUM FREEZE, it

workspace_hack/Cargo.toml

@@ -17,9 +17,10 @@ license.workspace = true
 [dependencies]
 ahash = { version = "0.8" }
 anyhow = { version = "1", features = ["backtrace"] }
+axum = { version = "0.7", features = ["ws"] }
+axum-core = { version = "0.4", default-features = false, features = ["tracing"] }
 base64 = { version = "0.21", features = ["alloc"] }
 base64ct = { version = "1", default-features = false, features = ["std"] }
-bitflags = { version = "2", default-features = false, features = ["std"] }
 bytes = { version = "1", features = ["serde"] }
 camino = { version = "1", default-features = false, features = ["serde1"] }
 chrono = { version = "0.4", default-features = false, features = ["clock", "serde", "wasmbind"] }
@@ -43,11 +44,10 @@ hashbrown = { version = "0.14", features = ["raw"] }
 hex = { version = "0.4", features = ["serde"] }
 hmac = { version = "0.12", default-features = false, features = ["reset"] }
 hyper-582f2526e08bb6a0 = { package = "hyper", version = "0.14", features = ["full"] }
-hyper-dff4ba8e3ae991db = { package = "hyper", version = "1", features = ["http1", "http2", "server"] }
-hyper-util = { version = "0.1", features = ["http1", "http2", "server", "tokio"] }
+hyper-dff4ba8e3ae991db = { package = "hyper", version = "1", features = ["full"] }
+hyper-util = { version = "0.1", features = ["client-legacy", "server-auto", "service"] }
 indexmap = { version = "1", default-features = false, features = ["std"] }
-itertools-5ef9efb8ec2df382 = { package = "itertools", version = "0.12" }
-itertools-93f6ce9d446188ac = { package = "itertools", version = "0.10" }
+itertools = { version = "0.12" }
 lazy_static = { version = "1", default-features = false, features = ["spin_no_std"] }
 libc = { version = "0.2", features = ["extra_traits", "use_std"] }
 log = { version = "0.4", default-features = false, features = ["std"] }
@@ -58,13 +58,12 @@ num-integer = { version = "0.1", features = ["i128"] }
 num-traits = { version = "0.2", features = ["i128", "libm"] }
 once_cell = { version = "1" }
 parquet = { version = "53", default-features = false, features = ["zstd"] }
-prost = { version = "0.11" }
+prost = { version = "0.13", features = ["prost-derive"] }
 rand = { version = "0.8", features = ["small_rng"] }
 regex = { version = "1" }
 regex-automata = { version = "0.4", default-features = false, features = ["dfa-onepass", "hybrid", "meta", "nfa-backtrack", "perf-inline", "perf-literal", "unicode"] }
 regex-syntax = { version = "0.8" }
 reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls", "stream"] }
-rustls = { version = "0.21", features = ["dangerous_configuration"] }
 scopeguard = { version = "1" }
 serde = { version = "1", features = ["alloc", "derive"] }
 serde_json = { version = "1", features = ["raw_value"] }
@@ -77,10 +76,11 @@ sync_wrapper = { version = "0.1", default-features = false, features = ["futures
 tikv-jemalloc-sys = { version = "0.5" }
 time = { version = "0.3", features = ["macros", "serde-well-known"] }
 tokio = { version = "1", features = ["fs", "io-std", "io-util", "macros", "net", "process", "rt-multi-thread", "signal", "test-util"] }
-tokio-rustls = { version = "0.24" }
+tokio-stream = { version = "0.1", features = ["net"] }
 tokio-util = { version = "0.7", features = ["codec", "compat", "io", "rt"] }
 toml_edit = { version = "0.22", features = ["serde"] }
-tower = { version = "0.4", default-features = false, features = ["balance", "buffer", "limit", "log", "timeout", "util"] }
+tonic = { version = "0.12", features = ["tls-roots"] }
+tower = { version = "0.4", default-features = false, features = ["balance", "buffer", "limit", "log", "util"] }
 tracing = { version = "0.1", features = ["log"] }
 tracing-core = { version = "0.1" }
 url = { version = "2", features = ["serde"] }
@@ -92,7 +92,6 @@ zstd-sys = { version = "2", default-features = false, features = ["legacy", "std
 [build-dependencies]
 ahash = { version = "0.8" }
 anyhow = { version = "1", features = ["backtrace"] }
-bitflags = { version = "2", default-features = false, features = ["std"] }
 bytes = { version = "1", features = ["serde"] }
 cc = { version = "1", default-features = false, features = ["parallel"] }
 chrono = { version = "0.4", default-features = false, features = ["clock", "serde", "wasmbind"] }
@@ -101,9 +100,7 @@ getrandom = { version = "0.2", default-features = false, features = ["std"] }
 half = { version = "2", default-features = false, features = ["num-traits"] }
 hashbrown = { version = "0.14", features = ["raw"] }
 indexmap = { version = "1", default-features = false, features = ["std"] }
-itertools-5ef9efb8ec2df382 = { package = "itertools", version = "0.12" }
-itertools-93f6ce9d446188ac = { package = "itertools", version = "0.10" }
-lazy_static = { version = "1", default-features = false, features = ["spin_no_std"] }
+itertools = { version = "0.12" }
 libc = { version = "0.2", features = ["extra_traits", "use_std"] }
 log = { version = "0.4", default-features = false, features = ["std"] }
 memchr = { version = "2" }
@@ -113,8 +110,9 @@ num-integer = { version = "0.1", features = ["i128"] }
 num-traits = { version = "0.2", features = ["i128", "libm"] }
 once_cell = { version = "1" }
 parquet = { version = "53", default-features = false, features = ["zstd"] }
+prettyplease = { version = "0.2", default-features = false, features = ["verbatim"] }
 proc-macro2 = { version = "1" }
-prost = { version = "0.11" }
+prost = { version = "0.13", features = ["prost-derive"] }
 quote = { version = "1" }
 regex = { version = "1" }
 regex-automata = { version = "0.4", default-features = false, features = ["dfa-onepass", "hybrid", "meta", "nfa-backtrack", "perf-inline", "perf-literal", "unicode"] }