fix(startup): thread-exhaustion resilience — cap workers, never panic
Port of upstream grok-build 0.2.113/0.2.114 fixes, extended to Kigi's startup order. - kigi-tty-utils runtime module: worker-cap policy (8 max) — tokio's per-core default pins 100+ thread slots on many-core shared hosts against RLIMIT_NPROC / pids.max, and later spawns die with EAGAIN. - kigi-bin builds the main runtime with capped workers and reports an out-of-threads host with a diagnostic + exit(1) instead of a panic. - The pre-runtime optimization threads (HTTP warmup, early model prefetch) spawn recoverably and degrade — their panic would have preempted the runtime's own diagnostic. - The per-session actor thread and its runtime report spawn/build failure through the existing acp::Error / AgentBuildError boundaries (new RuntimeBuild variant) instead of panicking the agent host. - fsnotify's watcher thread spawn maps into FsNotifyError::WatcherStart so callers degrade instead of crashing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KSy9S31pZNWXtRZNVJ1sDf
This commit is contained in:
1 parent
bf93091416
commit
97de661554
8 files changed
+144
-17
No files matched your search
@@ -1221,10 +1221,26 @@ fn main() {
|
||||
"Found crashed sessions from a previous run"
|
||||
);
|
||||
}
|
||||
let runtime = tokio::runtime::Builder::new_multi_thread()
|
||||
// Capped workers: tokio's per-core default pins 100+ thread slots on
|
||||
// many-core shared hosts and later spawns die with EAGAIN.
|
||||
let runtime = match tokio::runtime::Builder::new_multi_thread()
|
||||
.worker_threads(kigi_tty_utils::runtime::capped_worker_threads().get())
|
||||
.enable_all()
|
||||
.build()
|
||||
.unwrap_or_else(|e| panic!("failed to start tokio runtime: {e}"));
|
||||
{
|
||||
Ok(runtime) => runtime,
|
||||
Err(e) => {
|
||||
// A host out of threads (RLIMIT_NPROC / pids.max) is an
|
||||
// environment problem, not a bug — report it, don't panic.
|
||||
kigi_tty_utils::restore_native_stderr();
|
||||
eprintln!("Error: failed to start the async runtime: {e}");
|
||||
eprintln!(
|
||||
"The host may be out of threads (RLIMIT_NPROC or the cgroup pids ceiling); \
|
||||
close other processes or raise the limit, then retry."
|
||||
);
|
||||
std::process::exit(1);
|
||||
}
|
||||
};
|
||||
let result = run_and_shutdown(runtime, async_main(), RUNTIME_SHUTDOWN_GRACE);
|
||||
kigi_log::debug_log::flush();
|
||||
if let Err(e) = result {
|
||||
|
||||
Reference in new issue
Block a user