refactor(firmware): run git on a dedicated large-stack thread
libgit2's init→push chain is deeply stack-hungry (~67 KB measured for a trivial config write; the push is deeper). Spike 7 sized the shared main task stack at 96 KB for it, which forced the editor build to over-reserve ~80 KB. Move git_publish onto its own std::thread (GIT_STACK = 96 KB via Builder::stack_size) and join it from main. This lets CONFIG_ESP_MAIN_TASK_STACK_SIZE drop back to 12288 — the Spike-6 value proven to run the editor plus a TLS-on-main handshake — so the editor no longer pays for git's stack. Hardware-verified: the push ran off-main (mbedTLS + FATFS) with no panic, no stack overflow, and no ENOMEM on the 96 KB spawn. This retires the earlier "time() only works on the main task" misdiagnosis for good — it was always the default 4 KB pthread stack overflowing, never thread-vs-main.
This commit is contained in:
@@ -1,20 +1,21 @@
|
||||
# Rust often needs a bit of an extra main task stack size compared to C (the default is 3K)
|
||||
# You might have to increase this further if you allocate large stack variables in the main task.
|
||||
# Bumped for the TLS handshake (Spike 6): mbedtls runs on the calling task and
|
||||
# wants several KB of stack on top of the app's own usage.
|
||||
# Bumped hard for Spike 7: libgit2's call chain is stack-hungry. Nearly every
|
||||
# function puts a `char path[GIT_PATH_MAX]` (4 KB) buffer on the stack, and the
|
||||
# repository_init → config-write → FATFS → wear-leveling chain nests ~10 of them
|
||||
# deep — a trivial config write measured ~67 KB of stack on hardware, overflowing
|
||||
# the previous 48 KB and smashing an adjacent newlib lock handle (LoadProhibited
|
||||
# in xQueueGenericSend). The push (smart-HTTP + pack + mbedTLS) is deeper still.
|
||||
# NOTE: this earlier looked like "time() only works on the main task" — but that
|
||||
# iteration ran git on a std::thread with the default 4 KB stack; the same chain
|
||||
# just overflowed sooner. It's stack depth, not thread-vs-main.
|
||||
# CAVEAT: this sdkconfig is shared with the editor build, so the editor also
|
||||
# reserves this stack for nothing. Once the push is proven, git should move to a
|
||||
# dedicated large-stack task and this can drop back to ~16 KB.
|
||||
CONFIG_ESP_MAIN_TASK_STACK_SIZE=98304
|
||||
# wants several KB of stack on top of the app's own usage. 12 KB ran the editor
|
||||
# AND a full TLS-on-main handshake on hardware — the last-known-good value for
|
||||
# this shared stack.
|
||||
#
|
||||
# Spike 7 briefly bumped this to 96 KB because libgit2's push chain is far deeper
|
||||
# (~67 KB measured for a trivial config write: nearly every function puts a 4 KB
|
||||
# `char path[GIT_PATH_MAX]` on the stack and init→config→FATFS→wear-leveling
|
||||
# nests ~10 deep). But this sdkconfig is SHARED with the editor build, so that
|
||||
# forced the editor to over-reserve ~80 KB for nothing. Git now runs on its own
|
||||
# large-stack thread instead (git_push.rs — GIT_STACK via
|
||||
# std::thread::Builder::stack_size), so this drops back to the Spike-6 value.
|
||||
# (The "time() only works on the main task" theory was a misdiagnosis: that
|
||||
# iteration ran git on a std::thread with the DEFAULT 4 KB stack and just
|
||||
# overflowed sooner — it was always stack depth, never thread-vs-main.)
|
||||
CONFIG_ESP_MAIN_TASK_STACK_SIZE=12288
|
||||
|
||||
# Increase a bit these stack sizes as they are also a bit too small by default
|
||||
CONFIG_ESP_SYSTEM_EVENT_TASK_STACK_SIZE=4096
|
||||
|
||||
@@ -93,6 +93,13 @@ const CA_BUNDLE_PATH: &str = "/spiflash/ca.pem";
|
||||
/// SNTP first-sync budget (same as Spike 6).
|
||||
const SNTP_TIMEOUT: Duration = Duration::from_secs(20);
|
||||
|
||||
/// Stack for the dedicated git thread (see run()). libgit2's init→push chain
|
||||
/// measured ~67 KB on hardware and the push is deeper; 96 KB is the value proven
|
||||
/// on the main task before git moved off it. Sizing the thread — not the shared
|
||||
/// main-task stack — is the whole point of this task: the editor build no longer
|
||||
/// reserves it. Allocated from internal DRAM only while a push is running.
|
||||
const GIT_STACK: usize = 96 * 1024;
|
||||
|
||||
fn main() -> Result<()> {
|
||||
// Required once before any esp-idf-svc call; some runtime patches only link
|
||||
// if this symbol is referenced. See esp-idf-template#71.
|
||||
@@ -143,15 +150,30 @@ fn run() -> Result<()> {
|
||||
mount_fat().context("mounting flash-FAT")?;
|
||||
install_tls_trust_store().context("installing TLS trust store")?;
|
||||
|
||||
// Git work runs on the MAIN task, not a spawned thread. libgit2 (via mbedTLS
|
||||
// cert validation and FATFS timestamping) calls time()/gettimeofday, whose
|
||||
// newlib lock asserts when taken from a Rust std::thread but works on main
|
||||
// (Spike 6 ran TLS on main fine). The main stack is sized for it in
|
||||
// sdkconfig.defaults (CONFIG_ESP_MAIN_TASK_STACK_SIZE). Errors are LOGGED,
|
||||
// not propagated, so the radio stays up and the monitor shows the result.
|
||||
match git_publish() {
|
||||
Ok(summary) => log::info!("✅ Spike 7 complete — {summary}"),
|
||||
Err(e) => log::error!("❌ git_publish failed: {e:?}"),
|
||||
// Git runs on a DEDICATED large-stack thread, not the main task. libgit2's
|
||||
// call chain is deeply stack-hungry (see GIT_STACK), and sizing the *shared*
|
||||
// main-task stack for it made the editor build over-reserve ~80 KB. Its own
|
||||
// thread lets the main task stay small (sdkconfig.defaults, back to 12 KB).
|
||||
//
|
||||
// NB: an earlier iteration ran git on a std::thread and appeared to fail,
|
||||
// which we wrongly blamed on a "newlib time() lock that only works on main".
|
||||
// The real cause was the default 4 KB pthread stack overflowing — the same
|
||||
// chain just smashed the stack sooner. An explicit stack_size fixes it; there
|
||||
// is no thread-vs-main limitation. (Verified: the push below runs mbedTLS +
|
||||
// FATFS timestamping off-main.)
|
||||
//
|
||||
// Errors are LOGGED, not propagated, so the radio stays up (_wifi is held on
|
||||
// this task) and the monitor shows the result. join() blocks main until git
|
||||
// finishes; a panic almost certainly means GIT_STACK is too small.
|
||||
let git = std::thread::Builder::new()
|
||||
.name("git".into())
|
||||
.stack_size(GIT_STACK)
|
||||
.spawn(git_publish)
|
||||
.context("spawning git thread")?;
|
||||
match git.join() {
|
||||
Ok(Ok(summary)) => log::info!("✅ Spike 7 complete — {summary}"),
|
||||
Ok(Err(e)) => log::error!("❌ git_publish failed: {e:?}"),
|
||||
Err(_) => log::error!("❌ git thread panicked — likely stack overflow, raise GIT_STACK"),
|
||||
}
|
||||
|
||||
log::info!("idling with Wi-Fi up — press reset to re-run");
|
||||
@@ -251,8 +273,9 @@ fn install_tls_trust_store() -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// The whole publish (on the main task): init a fresh working copy, write a
|
||||
/// file, commit, and push to a fresh remote branch. Returns a one-line summary.
|
||||
/// The whole publish (runs on the dedicated git thread — see run()): init a fresh
|
||||
/// working copy, write a file, commit, and push to a fresh remote branch. Returns
|
||||
/// a one-line summary.
|
||||
fn git_publish() -> Result<String> {
|
||||
log::info!("git_publish started — free heap {}", free_heap());
|
||||
let unix = now_unix();
|
||||
|
||||
Reference in New Issue
Block a user