perf: speed up startup from ~15s to ~2s (#280)

Three high-impact changes eliminate most startup latency:

1. Enable wasmtime persistent compilation cache — call
   cache_config_load_default() so compiled native code is serialized to
   disk (~/.cache/wasmtime). Subsequent startups deserialize instead of
   recompiling, dropping the WASM phase from ~13s to <1s.

2. Cache compiled Component in PreparedModule — store the compiled
   wasmtime::component::Component directly instead of raw bytes.
   Eliminates ~2.6s recompilation on every first tool/channel execution.

3. Move blocking housekeeping to background tasks — embedding backfill
   (~1.3s of failing HTTP calls) and stale job cleanup are fire-and-forget
   work that no longer blocks the critical startup path.

Also: deduplicate Workspace creation in main.rs (two identical instances
reduced to one), and replace leftover println! in session validation with
tracing calls.

Co-authored-by: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Illia Polosukhin
2026-02-21 02:30:57 +00:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 2cdd1acb1e
commit 98ee648fcb
8 changed files with 130 additions and 81 deletions
+18 -11
View File
@@ -200,9 +200,13 @@ impl AppBuilder {
self.session.attach_store(db.clone(), "default").await;
if let Err(e) = db.cleanup_stale_sandbox_jobs().await {
tracing::warn!("Failed to cleanup stale sandbox jobs: {}", e);
}
// Fire-and-forget housekeeping — no need to block startup.
let db_cleanup = db.clone();
tokio::spawn(async move {
if let Err(e) = db_cleanup.cleanup_stale_sandbox_jobs().await {
tracing::warn!("Failed to cleanup stale sandbox jobs: {}", e);
}
});
self.db = Some(db);
Ok(())
@@ -715,15 +719,18 @@ impl AppBuilder {
}
if embeddings.is_some() {
match ws.backfill_embeddings().await {
Ok(count) if count > 0 => {
tracing::info!("Backfilled embeddings for {} chunks", count);
let ws_bg = Arc::clone(ws);
tokio::spawn(async move {
match ws_bg.backfill_embeddings().await {
Ok(count) if count > 0 => {
tracing::info!("Backfilled embeddings for {} chunks", count);
}
Ok(_) => {}
Err(e) => {
tracing::warn!("Failed to backfill embeddings: {}", e);
}
}
Ok(_) => {}
Err(e) => {
tracing::warn!("Failed to backfill embeddings: {}", e);
}
}
});
}
}
+1 -1
View File
@@ -488,7 +488,7 @@ mod tests {
let prepared = Arc::new(PreparedChannelModule {
name: name.to_string(),
description: format!("Test channel: {}", name),
component_bytes: Vec::new(),
component: None,
limits: ResourceLimits::default(),
});
+30 -10
View File
@@ -68,38 +68,51 @@ impl WasmChannelRuntimeConfig {
}
/// A compiled WASM channel component ready for instantiation.
#[derive(Debug)]
///
/// Stores the pre-compiled `Component` directly so instantiation
/// doesn't require recompilation.
pub struct PreparedChannelModule {
/// Channel name.
pub name: String,
/// Channel description.
pub description: String,
/// Compiled component bytes (public for testing, otherwise use component_bytes()).
pub(crate) component_bytes: Vec<u8>,
/// Pre-compiled component (cheaply cloneable via internal Arc).
pub(crate) component: Option<wasmtime::component::Component>,
/// Resource limits for this channel.
pub limits: ResourceLimits,
}
impl PreparedChannelModule {
/// Get the compiled component bytes.
pub fn component_bytes(&self) -> &[u8] {
&self.component_bytes
/// Get the pre-compiled component for instantiation.
pub fn component(&self) -> Option<&wasmtime::component::Component> {
self.component.as_ref()
}
/// Create a PreparedChannelModule for testing purposes.
///
/// Creates a module with no actual WASM bytes, suitable for testing
/// Creates a module with no actual WASM component, suitable for testing
/// channel infrastructure without requiring a real WASM component.
pub fn for_testing(name: impl Into<String>, description: impl Into<String>) -> Self {
Self {
name: name.into(),
description: description.into(),
component_bytes: Vec::new(),
component: None,
limits: ResourceLimits::default(),
}
}
}
impl std::fmt::Debug for PreparedChannelModule {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("PreparedChannelModule")
.field("name", &self.name)
.field("description", &self.description)
.field("has_component", &self.component.is_some())
.field("limits", &self.limits)
.finish()
}
}
/// WASM channel runtime.
///
/// Manages the Wasmtime engine and a cache of prepared channel modules.
@@ -137,6 +150,13 @@ impl WasmChannelRuntime {
// Disable debug info in production
wasmtime_config.debug_info(false);
// Enable persistent compilation cache. Wasmtime serializes compiled native
// code to disk (~/.cache/wasmtime by default), so subsequent startups
// deserialize instead of recompiling — typically 10-50x faster.
if let Err(e) = wasmtime_config.cache_config_load_default() {
tracing::warn!("Failed to enable wasmtime compilation cache: {}", e);
}
let engine = Engine::new(&wasmtime_config).map_err(|e| {
WasmChannelError::Config(format!("Failed to create Wasmtime engine: {}", e))
})?;
@@ -183,13 +203,13 @@ impl WasmChannelRuntime {
// Compile in blocking task (Wasmtime compilation is synchronous)
let prepared = tokio::task::spawn_blocking(move || {
// Validate and compile the component
let _component = wasmtime::component::Component::new(&engine, &wasm_bytes)
let component = wasmtime::component::Component::new(&engine, &wasm_bytes)
.map_err(|e| WasmChannelError::Compilation(e.to_string()))?;
Ok::<_, WasmChannelError>(PreparedChannelModule {
name: name.clone(),
description: desc,
component_bytes: wasm_bytes,
component: Some(component),
limits: limits.unwrap_or(default_limits),
})
})
+19 -15
View File
@@ -37,7 +37,7 @@ use tokio::sync::{RwLock, mpsc, oneshot};
use tokio_stream::wrappers::ReceiverStream;
use uuid::Uuid;
use wasmtime::Store;
use wasmtime::component::{Component, Linker};
use wasmtime::component::Linker;
use wasmtime_wasi::{ResourceTable, WasiCtx, WasiCtxBuilder, WasiView};
use crate::channels::wasm::capabilities::ChannelCapabilities;
@@ -725,9 +725,13 @@ impl WasmChannel {
) -> Result<SandboxedChannel, WasmChannelError> {
let engine = runtime.engine();
// Compile the component (uses cached bytes)
let component = Component::new(engine, prepared.component_bytes())
.map_err(|e| WasmChannelError::Compilation(e.to_string()))?;
// Use the pre-compiled component (no recompilation needed)
let component = prepared
.component()
.ok_or_else(|| {
WasmChannelError::Compilation("No compiled component available".to_string())
})?
.clone();
// Create linker and add host functions
let mut linker = Linker::new(engine);
@@ -778,7 +782,7 @@ impl WasmChannel {
/// Returns the channel configuration for HTTP endpoint registration.
async fn call_on_start(&self) -> Result<ChannelConfig, WasmChannelError> {
// If no WASM bytes, return default config (for testing)
if self.prepared.component_bytes.is_empty() {
if self.prepared.component().is_none() {
tracing::info!(
channel = %self.name,
"WASM channel on_start called (no WASM module, returning defaults)"
@@ -918,7 +922,7 @@ impl WasmChannel {
);
// If no WASM bytes, return 200 OK (for testing)
if self.prepared.component_bytes.is_empty() {
if self.prepared.component().is_none() {
tracing::debug!(
channel = %self.name,
method = method,
@@ -1018,7 +1022,7 @@ impl WasmChannel {
/// Called periodically if polling is configured.
pub async fn call_on_poll(&self) -> Result<(), WasmChannelError> {
// If no WASM bytes, do nothing (for testing)
if self.prepared.component_bytes.is_empty() {
if self.prepared.component().is_none() {
tracing::debug!(
channel = %self.name,
"WASM channel on_poll called (no WASM module)"
@@ -1118,7 +1122,7 @@ impl WasmChannel {
);
// If no WASM bytes, do nothing (for testing)
if self.prepared.component_bytes.is_empty() {
if self.prepared.component().is_none() {
tracing::debug!(
channel = %self.name,
message_id = %message_id,
@@ -1236,7 +1240,7 @@ impl WasmChannel {
metadata: &serde_json::Value,
) -> Result<(), WasmChannelError> {
// If no WASM bytes, do nothing (for testing)
if self.prepared.component_bytes.is_empty() {
if self.prepared.component().is_none() {
return Ok(());
}
@@ -1307,7 +1311,7 @@ impl WasmChannel {
timeout: Duration,
wit_update: wit_channel::StatusUpdate,
) -> Result<(), WasmChannelError> {
if prepared.component_bytes.is_empty() {
if prepared.component().is_none() {
return Ok(());
}
@@ -1627,7 +1631,7 @@ impl WasmChannel {
workspace_store: &Arc<ChannelWorkspaceStore>,
) -> Result<Vec<EmittedMessage>, WasmChannelError> {
// Skip if no WASM bytes (testing mode)
if prepared.component_bytes.is_empty() {
if prepared.component().is_none() {
tracing::debug!(
channel = %channel_name,
"WASM channel on_poll called (no WASM module)"
@@ -2206,7 +2210,7 @@ mod tests {
let prepared = Arc::new(PreparedChannelModule {
name: "test".to_string(),
description: "Test channel".to_string(),
component_bytes: Vec::new(),
component: None,
limits: ResourceLimits::default(),
});
@@ -2271,7 +2275,7 @@ mod tests {
#[tokio::test]
async fn test_execute_poll_no_wasm_returns_empty() {
// When there's no WASM module (empty component_bytes), execute_poll
// When there's no WASM module (None component), execute_poll
// should return an empty vector of messages
let config = WasmChannelRuntimeConfig::for_testing();
let runtime = Arc::new(WasmChannelRuntime::new(config).unwrap());
@@ -2279,7 +2283,7 @@ mod tests {
let prepared = Arc::new(PreparedChannelModule {
name: "poll-test".to_string(),
description: "Test channel".to_string(),
component_bytes: Vec::new(), // No WASM bytes
component: None, // No WASM module
limits: ResourceLimits::default(),
});
@@ -2381,7 +2385,7 @@ mod tests {
let prepared = Arc::new(PreparedChannelModule {
name: "poll-channel".to_string(),
description: "Polling test channel".to_string(),
component_bytes: Vec::new(),
component: None,
limits: ResourceLimits::default(),
});
+3 -3
View File
@@ -157,14 +157,14 @@ impl SessionManager {
}
// Token exists, validate it by calling /v1/users/me
println!("Validating session...");
tracing::debug!("Validating session...");
match self.validate_token().await {
Ok(()) => {
println!("Session valid.");
tracing::debug!("Session valid");
Ok(())
}
Err(e) => {
println!("Session expired or invalid: {}", e);
tracing::info!("Session expired or invalid: {}", e);
self.initiate_login().await
}
}
+31 -29
View File
@@ -487,9 +487,13 @@ async fn main() -> anyhow::Result<()> {
session.attach_store(Arc::clone(db), "default").await;
// Mark any jobs left in "running" or "creating" state as "interrupted".
if let Err(e) = db.cleanup_stale_sandbox_jobs().await {
tracing::warn!("Failed to cleanup stale sandbox jobs: {}", e);
}
// Fire-and-forget housekeeping — no need to block startup.
let db_cleanup = Arc::clone(db);
tokio::spawn(async move {
if let Err(e) = db_cleanup.cleanup_stale_sandbox_jobs().await {
tracing::warn!("Failed to cleanup stale sandbox jobs: {}", e);
}
});
}
// Create secrets store early: needed for injecting LLM API keys from encrypted
@@ -800,14 +804,20 @@ async fn main() -> anyhow::Result<()> {
);
}
// Register memory tools if database is available
if let Some(ref db) = db {
let mut workspace = Workspace::new_with_db("default", Arc::clone(db));
// Create workspace once, reused for memory tools and agent
let workspace: Option<Arc<Workspace>> = if let Some(ref db) = db {
let mut ws = Workspace::new_with_db("default", Arc::clone(db));
if let Some(ref emb) = embeddings {
workspace = workspace.with_embeddings(emb.clone());
ws = ws.with_embeddings(emb.clone());
}
let workspace = Arc::new(workspace);
tools.register_memory_tools(workspace);
Some(Arc::new(ws))
} else {
None
};
// Register memory tools if workspace is available
if let Some(ref ws) = workspace {
tools.register_memory_tools(Arc::clone(ws));
}
// Register builder tool if enabled.
@@ -1322,17 +1332,6 @@ async fn main() -> anyhow::Result<()> {
None
};
// Create workspace for agent (shared with memory tools)
let workspace = if let Some(ref db_ref) = db {
let mut ws = Workspace::new_with_db("default", Arc::clone(db_ref));
if let Some(ref emb) = embeddings {
ws = ws.with_embeddings(emb.clone());
}
Some(Arc::new(ws))
} else {
None
};
// Seed workspace with core identity files on first boot
if let Some(ref ws) = workspace {
match ws.seed_if_empty().await {
@@ -1343,17 +1342,20 @@ async fn main() -> anyhow::Result<()> {
}
}
// Backfill embeddings if we just enabled the provider
// Backfill embeddings in background (fire-and-forget housekeeping)
if let (Some(ws), Some(_)) = (&workspace, &embeddings) {
match ws.backfill_embeddings().await {
Ok(count) if count > 0 => {
tracing::info!("Backfilled embeddings for {} chunks", count);
let ws_bg = Arc::clone(ws);
tokio::spawn(async move {
match ws_bg.backfill_embeddings().await {
Ok(count) if count > 0 => {
tracing::info!("Backfilled embeddings for {} chunks", count);
}
Ok(_) => {}
Err(e) => {
tracing::warn!("Failed to backfill embeddings: {}", e);
}
}
Ok(_) => {}
Err(e) => {
tracing::warn!("Failed to backfill embeddings: {}", e);
}
}
});
}
// Create context manager (shared between job tools and agent)
+25 -8
View File
@@ -64,8 +64,8 @@ impl WasmRuntimeConfig {
/// A compiled WASM component ready for instantiation.
///
/// Contains the pre-compiled component plus cached metadata extracted
/// from the component during preparation.
#[derive(Debug)]
/// from the component during preparation. Stores the compiled `Component`
/// directly so instantiation doesn't require recompilation.
pub struct PreparedModule {
/// Tool name.
pub name: String,
@@ -73,16 +73,26 @@ pub struct PreparedModule {
pub description: String,
/// Parameter schema JSON (cached from component).
pub schema: serde_json::Value,
/// Compiled component bytes (can be serialized for caching).
component_bytes: Vec<u8>,
/// Pre-compiled component (cheaply cloneable via internal Arc).
component: wasmtime::component::Component,
/// Resource limits for this tool.
pub limits: ResourceLimits,
}
impl PreparedModule {
/// Get the compiled component bytes.
pub fn component_bytes(&self) -> &[u8] {
&self.component_bytes
/// Get the pre-compiled component for instantiation.
pub fn component(&self) -> &wasmtime::component::Component {
&self.component
}
}
impl std::fmt::Debug for PreparedModule {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("PreparedModule")
.field("name", &self.name)
.field("description", &self.description)
.field("limits", &self.limits)
.finish()
}
}
@@ -123,6 +133,13 @@ impl WasmToolRuntime {
// Disable debug info in production for smaller modules
wasmtime_config.debug_info(false);
// Enable persistent compilation cache. Wasmtime serializes compiled native
// code to disk (~/.cache/wasmtime by default), so subsequent startups
// deserialize instead of recompiling — typically 10-50x faster.
if let Err(e) = wasmtime_config.cache_config_load_default() {
tracing::warn!("Failed to enable wasmtime compilation cache: {}", e);
}
let engine = Engine::new(&wasmtime_config).map_err(|e| {
WasmError::EngineCreationFailed(format!("Failed to create Wasmtime engine: {}", e))
})?;
@@ -199,7 +216,7 @@ impl WasmToolRuntime {
name: name.clone(),
description,
schema,
component_bytes: wasm_bytes,
component,
limits: limits.unwrap_or(default_limits),
})
})
+3 -4
View File
@@ -13,7 +13,7 @@ use std::time::{Duration, Instant};
use async_trait::async_trait;
use wasmtime::Store;
use wasmtime::component::{Component, Linker};
use wasmtime::component::Linker;
use wasmtime_wasi::{ResourceTable, WasiCtx, WasiCtxBuilder, WasiView};
use crate::context::JobContext;
@@ -581,9 +581,8 @@ impl WasmToolWrapper {
// Set up resource limiter
store.limiter(|data| &mut data.limiter);
// Compile the component (uses cached bytes)
let component = Component::new(engine, self.prepared.component_bytes())
.map_err(|e| WasmError::CompilationFailed(e.to_string()))?;
// Use the pre-compiled component (no recompilation needed)
let component = self.prepared.component().clone();
// Create linker with all host functions properly namespaced
let mut linker = Linker::new(engine);