fix: fresh-ISO feedback bug-bash — onboarding, status truthfulness, recovery, kiosk, logs
Fixes from real fresh-install feedback (Framework node .81) + its log bundle:
Backend:
- websocket: subscribe before initial snapshot — broadcasts in the gap were
silently lost, stranding clients on stale state until a hard refresh
(the "everything needs ctrl-r" bug: My Apps stuck Loading, App Store
stuck Checking, containers-scanned never arriving)
- crash recovery: check the crash marker BEFORE writing our own PID —
recovery had never run on any node (always saw its own PID and skipped);
PID-reuse guard via /proc cmdline
- boot status: pending-boot-starts registry (recovery, stack recovery,
reconciler, adoption) — scanner overlays queued-but-down apps as
Restarting instead of Stopped after a reboot; scanner-authored
Restarting resolves immediately on a settled scan (no transitional wedge)
- install deps: bounded wait (36x5s) when a dependency is installed but
still starting ("Waiting for Bitcoin to start…") instead of instant
rejection; dependency-gate rejections remove the optimistic entry (no
phantom Stopped tile) and surface as a notification
- seed backup: auth.setup persists the onboarding mnemonic as the
encrypted seed backup (reveal previously failed on EVERY node — nothing
ever wrote master_seed.enc); seed.restore stashes too; error sanitizer
lets seed/2FA errors through instead of "Check server logs"
- lnd: bitcoind.rpchost resolved from the running Bitcoin variant
(hardcoded bitcoin-knots broke Core nodes); manifest uses derived_env
- bitcoin status: clean human message for connection-reset/startup; raw
URLs + os-error chains no longer reach the app card
- fedimint-clientd: chown /var/lib/archipelago/fmcd to 1000:1000 (root-
created dir crash-looped the rootless container, EACCES) — first-boot
script + pre-start self-heal
- log volume (>1GB/day on a day-old node): journald caps drop-in (ISO +
bootstrap self-heal), bitcoind -printtoconsole=0 everywhere (90% of the
journal was IBD UpdateTip spam), tracing default debug→info
Frontend:
- Login: Enter advances to confirm field then submits; submit always
clickable with inline errors (was silently disabled on mismatch);
Restart Onboarding needs a confirming second click (the mismatch →
"onboarding restarted" trap)
- sync store: 30s state reconciliation + refetch on re-entrant connect;
20s containers-scanned escape hatch so Checking can never show forever;
fresh empty node reaches the real "no apps yet" state
- intro video: CRF20 re-encode (SSIM 0.988) + faststart — moov was at EOF
so playback needed the full 15MB first (the intro lag)
- backgrounds: 10 heaviest JPEGs → WebP q90 (9.4MB→6.6MB); 7 stayed JPEG
(WebP larger on noisy sources)
- Web5ConnectedNodes: drop unused template ref that failed vue-tsc -b
ISO/kiosk:
- nginx: /assets/ 404s no longer cached immutable for a year; HTTPS block
gained the missing /assets/ location (served index.html as images)
- kiosk: launcher/service spliced from configs/ at ISO build (stale
heredoc force-disabled GPU); MemoryHigh/Max 1200/1500→2200/2800M (kiosk
rode the reclaim throttle = the lag); firmware-intel-graphics +
firmware-amd-graphics (trixie split DMC blobs out of misc-nonfree)
Verified: cargo test 898/898 green, npm run build green with dist
contents confirmed (webp refs, lnd.png, faststart video, new strings).
Handover for ISO build + deploy: docs/HANDOVER-2026-07-02-iso-feedback.md
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
archipelago
co-authored by
Claude Fable 5
Claude Fable 5
parent
8256fde1a6
commit
c375ecc441
@@ -114,6 +114,31 @@ impl RpcHandler {
|
||||
Err(e) => {
|
||||
error!("package.install {} failed: {:#}", package_id_spawn, e);
|
||||
install_log(&format!("INSTALL FAIL: {} — {:#}", package_id_spawn, e)).await;
|
||||
// Dependency-gate rejections happen BEFORE any resource
|
||||
// (container/image/data dir) exists for this package, so
|
||||
// keeping the optimistic entry would leave a phantom
|
||||
// "Stopped" tile whose Start fails with `no such object`
|
||||
// (the log-confirmed LND fresh-install failure). Remove
|
||||
// the entry so the card reverts to installable, and
|
||||
// surface the reason as a notification instead.
|
||||
if let Some(gate) = e.downcast_ref::<super::dependencies::DependencyGateError>()
|
||||
{
|
||||
let (mut data, _) = handler.state_manager.get_snapshot().await;
|
||||
data.package_data.remove(&package_id_spawn);
|
||||
data.notifications.push(crate::data_model::Notification {
|
||||
id: format!("install-deps-{package_id_spawn}"),
|
||||
level: crate::data_model::NotificationLevel::Error,
|
||||
title: format!("Could not install {package_id_spawn}"),
|
||||
message: gate.to_string(),
|
||||
timestamp: chrono::Utc::now().to_rfc3339(),
|
||||
app_id: Some(package_id_spawn.clone()),
|
||||
});
|
||||
while data.notifications.len() > 20 {
|
||||
data.notifications.remove(0);
|
||||
}
|
||||
handler.state_manager.update_data(data).await;
|
||||
return;
|
||||
}
|
||||
// Don't remove the entry — that's what made the card
|
||||
// vanish from My Apps mid-install / between retry-loop
|
||||
// attempts (e.g. tailscale's entrypoint failure). Leave
|
||||
|
||||
@@ -707,12 +707,17 @@ pub(super) async fn get_app_config(
|
||||
// effectively pinned at 2 by --cpus=2 (now removed).
|
||||
// -maxconnections=125 — default but explicit, so ops can
|
||||
// tune downward on bandwidth-constrained nodes.
|
||||
// Log volume: -printtoconsole=0 — bitcoind already writes
|
||||
// debug.log in the datadir (self-shrunk on restart); echoing it
|
||||
// to stdout too pushed every IBD "UpdateTip" line through
|
||||
// conmon into journald (>1 GB/day on a fresh node). Deep
|
||||
// debugging uses /var/lib/archipelago/bitcoin/debug.log.
|
||||
Some(vec![
|
||||
"-server=1".to_string(),
|
||||
"-rpcbind=0.0.0.0".to_string(),
|
||||
"-rpcallowip=0.0.0.0/0".to_string(),
|
||||
"-rpcport=8332".to_string(),
|
||||
"-printtoconsole=1".to_string(),
|
||||
"-printtoconsole=0".to_string(),
|
||||
"-datadir=/home/bitcoin/.bitcoin".to_string(),
|
||||
format!("-dbcache={}", bitcoin_dbcache_mb()),
|
||||
"-par=0".to_string(),
|
||||
|
||||
@@ -58,6 +58,7 @@ fn archival_bitcoin_required_message(package_id: &str) -> String {
|
||||
}
|
||||
|
||||
/// Snapshot of which dependency services are currently running.
|
||||
#[derive(Debug)]
|
||||
pub(super) struct RunningDeps {
|
||||
pub has_bitcoin: bool,
|
||||
pub has_electrumx: bool,
|
||||
@@ -227,6 +228,190 @@ pub(super) fn check_install_deps(package_id: &str, deps: &RunningDeps) -> Result
|
||||
}
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Bounded dependency wait (install race fix)
|
||||
// ---------------------------------------------------------------------------
|
||||
//
|
||||
// Confirmed race on fresh nodes: the user clicks "Install LND" while
|
||||
// bitcoin-knots is itself still installing/starting. `check_install_deps`
|
||||
// rejected instantly ("LND requires a running Bitcoin node…") even though
|
||||
// Bitcoin came up 55s later. The fix: when the dependency is INSTALLED
|
||||
// (container exists in `podman ps -a`, or the package state knows about it)
|
||||
// but not Running yet, poll for up to DEP_WAIT_MAX_ATTEMPTS × DEP_WAIT_INTERVAL
|
||||
// (~3 minutes) before failing, surfacing "Waiting for X to start…" via the
|
||||
// install-progress message. If the dependency is not installed at all, fail
|
||||
// fast with the canonical `check_install_deps` message — waiting can't help.
|
||||
|
||||
/// Poll interval while waiting for an installed dependency to start.
|
||||
pub(super) const DEP_WAIT_INTERVAL: std::time::Duration = std::time::Duration::from_secs(5);
|
||||
/// 36 × 5s = 3 minutes of bounded waiting.
|
||||
pub(super) const DEP_WAIT_MAX_ATTEMPTS: u32 = 36;
|
||||
|
||||
/// Marker error: the install was rejected by the dependency gate BEFORE any
|
||||
/// resource (container, image, data dir) was created for the package. The
|
||||
/// async install wrapper (`async_lifecycle.rs`) downcasts to this to remove
|
||||
/// the optimistic `Installing` state entry instead of leaving a phantom
|
||||
/// "Stopped" tile whose Start fails with `no such object`.
|
||||
#[derive(Debug)]
|
||||
pub(in crate::api::rpc) struct DependencyGateError(pub String);
|
||||
|
||||
impl std::fmt::Display for DependencyGateError {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.write_str(&self.0)
|
||||
}
|
||||
}
|
||||
|
||||
impl std::error::Error for DependencyGateError {}
|
||||
|
||||
/// One unsatisfied install dependency: a user-facing label plus the container
|
||||
/// name variants that would satisfy it.
|
||||
struct MissingDep {
|
||||
label: &'static str,
|
||||
containers: &'static [&'static str],
|
||||
}
|
||||
|
||||
/// Which dependencies `check_install_deps` would reject `package_id` over.
|
||||
/// Must stay in lockstep with the match arms in `check_install_deps` (the
|
||||
/// wait loop re-runs `check_install_deps` for the canonical error message).
|
||||
fn missing_install_deps(package_id: &str, deps: &RunningDeps) -> Vec<MissingDep> {
|
||||
const BITCOIN: MissingDep = MissingDep {
|
||||
label: "Bitcoin",
|
||||
containers: BITCOIN_NAMES,
|
||||
};
|
||||
const ELECTRUM: MissingDep = MissingDep {
|
||||
label: "ElectrumX",
|
||||
containers: ELECTRUM_NAMES,
|
||||
};
|
||||
let mut missing = Vec::new();
|
||||
match package_id {
|
||||
"electrumx" | "mempool-electrs" | "electrs" | "lnd" | "btcpay-server" | "btcpayserver" => {
|
||||
if !deps.has_bitcoin {
|
||||
missing.push(BITCOIN);
|
||||
}
|
||||
}
|
||||
"mempool" | "mempool-web" => {
|
||||
if !deps.has_bitcoin {
|
||||
missing.push(BITCOIN);
|
||||
}
|
||||
if !deps.has_electrumx {
|
||||
missing.push(ELECTRUM);
|
||||
}
|
||||
}
|
||||
// fedimint deliberately absent: check_install_deps allows it without
|
||||
// a local Bitcoin node (remote RPC configured in guardian setup).
|
||||
_ => {}
|
||||
}
|
||||
missing
|
||||
}
|
||||
|
||||
fn join_dep_labels(missing: &[MissingDep]) -> String {
|
||||
missing
|
||||
.iter()
|
||||
.map(|d| d.label)
|
||||
.collect::<Vec<_>>()
|
||||
.join(" and ")
|
||||
}
|
||||
|
||||
/// One snapshot of the dependency world, fed to [`wait_for_install_deps`].
|
||||
pub(super) struct DepProbe {
|
||||
/// Which dependency services are currently Running.
|
||||
pub running: RunningDeps,
|
||||
/// Container/package names that EXIST in any state — installed, but
|
||||
/// possibly not running yet (`podman ps -a` ∪ package-state entries).
|
||||
pub existing: Vec<String>,
|
||||
}
|
||||
|
||||
/// All container names known to podman in any state (`podman ps -a`).
|
||||
/// Conservative on probe failure: returns an empty list, which makes the
|
||||
/// wait loop fall back to the pre-fix fail-fast behavior.
|
||||
pub(super) async fn detect_existing_containers() -> Vec<String> {
|
||||
let out = tokio::time::timeout(
|
||||
std::time::Duration::from_secs(30),
|
||||
tokio::process::Command::new("podman")
|
||||
.args(["ps", "-a", "--format", "{{.Names}}"])
|
||||
.output(),
|
||||
)
|
||||
.await;
|
||||
match out {
|
||||
Ok(Ok(o)) if o.status.success() => String::from_utf8_lossy(&o.stdout)
|
||||
.lines()
|
||||
.map(|l| l.trim().to_string())
|
||||
.filter(|l| !l.is_empty())
|
||||
.collect(),
|
||||
_ => Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Bounded dependency gate. Returns the (satisfied) `RunningDeps` snapshot,
|
||||
/// or a [`DependencyGateError`]:
|
||||
/// - immediately, when a missing dependency is not installed at all
|
||||
/// (canonical `check_install_deps` message), or
|
||||
/// - after `max_attempts × interval`, when an installed dependency never
|
||||
/// reached Running.
|
||||
///
|
||||
/// `probe` and `on_waiting` are injected so unit tests can drive the loop
|
||||
/// without a podman runtime; production wires them to
|
||||
/// `RpcHandler::dep_probe_for_install` / `set_install_message`.
|
||||
pub(super) async fn wait_for_install_deps<P, PF, L, LF>(
|
||||
package_id: &str,
|
||||
mut probe: P,
|
||||
mut on_waiting: L,
|
||||
max_attempts: u32,
|
||||
interval: std::time::Duration,
|
||||
) -> Result<RunningDeps>
|
||||
where
|
||||
P: FnMut() -> PF,
|
||||
PF: std::future::Future<Output = Result<DepProbe>>,
|
||||
L: FnMut(String) -> LF,
|
||||
LF: std::future::Future<Output = ()>,
|
||||
{
|
||||
let mut waited_attempts = 0u32;
|
||||
loop {
|
||||
let DepProbe { running, existing } = probe().await?;
|
||||
let missing = missing_install_deps(package_id, &running);
|
||||
if missing.is_empty() {
|
||||
// Keep behavior in lockstep with the canonical gate (covers any
|
||||
// future arm added there but not mirrored in missing_install_deps).
|
||||
check_install_deps(package_id, &running)?;
|
||||
return Ok(running);
|
||||
}
|
||||
|
||||
// Fail fast if any missing dependency has no installed container
|
||||
// under any name variant — waiting cannot satisfy it.
|
||||
let some_dep_not_installed = missing
|
||||
.iter()
|
||||
.any(|dep| !dep.containers.iter().any(|c| existing.iter().any(|e| e == c)));
|
||||
if some_dep_not_installed {
|
||||
let msg = match check_install_deps(package_id, &running) {
|
||||
Err(e) => e.to_string(),
|
||||
Ok(()) => format!("{package_id} dependencies are not running"),
|
||||
};
|
||||
return Err(anyhow::Error::new(DependencyGateError(msg)));
|
||||
}
|
||||
|
||||
if waited_attempts >= max_attempts {
|
||||
let labels = join_dep_labels(&missing);
|
||||
return Err(anyhow::Error::new(DependencyGateError(format!(
|
||||
"{labels} is installed but did not reach the running state within \
|
||||
{} seconds. Start {labels}, then install {package_id} again.",
|
||||
u64::from(max_attempts) * interval.as_secs()
|
||||
))));
|
||||
}
|
||||
waited_attempts += 1;
|
||||
|
||||
let labels = join_dep_labels(&missing);
|
||||
if waited_attempts == 1 {
|
||||
info!(
|
||||
"Install {package_id}: dependency {labels} installed but not running yet — \
|
||||
waiting up to {}s for it to start",
|
||||
u64::from(max_attempts) * interval.as_secs()
|
||||
);
|
||||
}
|
||||
on_waiting(format!("Waiting for {labels} to start…")).await;
|
||||
tokio::time::sleep(interval).await;
|
||||
}
|
||||
}
|
||||
|
||||
/// ElectrumX and Mempool's Electrum backend need historical blocks from an
|
||||
/// unpruned node while building their indexes. A pruned Bitcoin node can be
|
||||
/// running and RPC-reachable but still leave them stuck with closed ports.
|
||||
@@ -625,6 +810,218 @@ mod tests {
|
||||
assert!(!manifest_declares_archival_bitcoin("does-not-exist"));
|
||||
}
|
||||
|
||||
mod dep_wait {
|
||||
use super::super::{wait_for_install_deps, DepProbe, DependencyGateError, RunningDeps};
|
||||
use std::sync::atomic::{AtomicU32, Ordering};
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::Duration;
|
||||
|
||||
fn deps(has_bitcoin: bool, has_electrumx: bool) -> RunningDeps {
|
||||
RunningDeps {
|
||||
has_bitcoin,
|
||||
has_electrumx,
|
||||
has_lnd: false,
|
||||
}
|
||||
}
|
||||
|
||||
fn probe(has_bitcoin: bool, has_electrumx: bool, existing: &[&str]) -> DepProbe {
|
||||
DepProbe {
|
||||
running: deps(has_bitcoin, has_electrumx),
|
||||
existing: existing.iter().map(|s| s.to_string()).collect(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Collects "Waiting for X to start…" labels emitted during the wait.
|
||||
fn label_sink() -> (Arc<Mutex<Vec<String>>>, impl FnMut(String) -> std::future::Ready<()>)
|
||||
{
|
||||
let labels = Arc::new(Mutex::new(Vec::new()));
|
||||
let sink = {
|
||||
let labels = Arc::clone(&labels);
|
||||
move |msg: String| {
|
||||
labels.lock().unwrap().push(msg);
|
||||
std::future::ready(())
|
||||
}
|
||||
};
|
||||
(labels, sink)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn passes_immediately_when_dependency_is_running() {
|
||||
let (labels, sink) = label_sink();
|
||||
let result = wait_for_install_deps(
|
||||
"lnd",
|
||||
|| async { Ok(probe(true, false, &["bitcoin-knots"])) },
|
||||
sink,
|
||||
3,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await;
|
||||
assert!(result.is_ok());
|
||||
assert!(labels.lock().unwrap().is_empty(), "no waiting expected");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn fails_fast_when_dependency_not_installed_at_all() {
|
||||
let calls = AtomicU32::new(0);
|
||||
let (labels, sink) = label_sink();
|
||||
let err = wait_for_install_deps(
|
||||
"lnd",
|
||||
|| {
|
||||
calls.fetch_add(1, Ordering::SeqCst);
|
||||
async { Ok(probe(false, false, &["uptime-kuma"])) }
|
||||
},
|
||||
sink,
|
||||
36,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
// Single probe — no polling when waiting cannot help.
|
||||
assert_eq!(calls.load(Ordering::SeqCst), 1);
|
||||
assert!(labels.lock().unwrap().is_empty());
|
||||
// Canonical check_install_deps message, wrapped in the gate marker
|
||||
// so async_lifecycle removes the optimistic Installing entry.
|
||||
assert!(err.downcast_ref::<DependencyGateError>().is_some());
|
||||
assert!(
|
||||
err.to_string().contains("LND requires a running Bitcoin node"),
|
||||
"unexpected message: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn waits_while_installed_dependency_starts_then_passes() {
|
||||
// Bitcoin container exists (installing/starting) but only reports
|
||||
// Running from the 3rd probe onward — the log-confirmed LND race.
|
||||
let calls = Arc::new(AtomicU32::new(0));
|
||||
let (labels, sink) = label_sink();
|
||||
let probe_calls = Arc::clone(&calls);
|
||||
let result = wait_for_install_deps(
|
||||
"lnd",
|
||||
move || {
|
||||
let n = probe_calls.fetch_add(1, Ordering::SeqCst);
|
||||
async move { Ok(probe(n >= 2, false, &["bitcoin-knots"])) }
|
||||
},
|
||||
sink,
|
||||
36,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await;
|
||||
assert!(result.is_ok(), "{result:?}");
|
||||
assert_eq!(calls.load(Ordering::SeqCst), 3);
|
||||
let labels = labels.lock().unwrap();
|
||||
assert_eq!(labels.len(), 2, "one waiting label per polling attempt");
|
||||
assert!(labels.iter().all(|l| l == "Waiting for Bitcoin to start…"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn times_out_when_installed_dependency_never_runs() {
|
||||
let (labels, sink) = label_sink();
|
||||
let err = wait_for_install_deps(
|
||||
"lnd",
|
||||
|| async { Ok(probe(false, false, &["bitcoin-knots"])) },
|
||||
sink,
|
||||
4,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(err.downcast_ref::<DependencyGateError>().is_some());
|
||||
assert!(
|
||||
err.to_string()
|
||||
.contains("did not reach the running state within 0 seconds"),
|
||||
"unexpected message: {err}"
|
||||
);
|
||||
assert_eq!(labels.lock().unwrap().len(), 4);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn mempool_waits_on_both_bitcoin_and_electrumx() {
|
||||
let calls = Arc::new(AtomicU32::new(0));
|
||||
let (labels, sink) = label_sink();
|
||||
let probe_calls = Arc::clone(&calls);
|
||||
let result = wait_for_install_deps(
|
||||
"mempool",
|
||||
move || {
|
||||
let n = probe_calls.fetch_add(1, Ordering::SeqCst);
|
||||
// Bitcoin comes up on probe 2, electrumx on probe 3.
|
||||
async move { Ok(probe(n >= 1, n >= 2, &["bitcoin-knots", "electrumx"])) }
|
||||
},
|
||||
sink,
|
||||
36,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await;
|
||||
assert!(result.is_ok(), "{result:?}");
|
||||
let labels = labels.lock().unwrap();
|
||||
assert_eq!(
|
||||
labels.as_slice(),
|
||||
&[
|
||||
"Waiting for Bitcoin and ElectrumX to start…".to_string(),
|
||||
"Waiting for ElectrumX to start…".to_string(),
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn mempool_fails_fast_when_one_dep_is_not_installed() {
|
||||
// Bitcoin is installed (waiting could help) but ElectrumX is not
|
||||
// installed at all — waiting can never satisfy the gate, so fail
|
||||
// fast with the canonical message.
|
||||
let (labels, sink) = label_sink();
|
||||
let err = wait_for_install_deps(
|
||||
"mempool",
|
||||
|| async { Ok(probe(false, false, &["bitcoin-knots"])) },
|
||||
sink,
|
||||
36,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(err.downcast_ref::<DependencyGateError>().is_some());
|
||||
assert!(labels.lock().unwrap().is_empty());
|
||||
assert!(
|
||||
err.to_string().contains("Mempool requires"),
|
||||
"unexpected message: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn variant_container_names_count_as_installed() {
|
||||
// bitcoin-core (not just bitcoin-knots) satisfies the "installed"
|
||||
// check for the wait path.
|
||||
let calls = Arc::new(AtomicU32::new(0));
|
||||
let (_labels, sink) = label_sink();
|
||||
let probe_calls = Arc::clone(&calls);
|
||||
let result = wait_for_install_deps(
|
||||
"electrumx",
|
||||
move || {
|
||||
let n = probe_calls.fetch_add(1, Ordering::SeqCst);
|
||||
async move { Ok(probe(n >= 1, false, &["bitcoin-core"])) }
|
||||
},
|
||||
sink,
|
||||
36,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await;
|
||||
assert!(result.is_ok(), "{result:?}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn apps_without_dependency_gate_pass_untouched() {
|
||||
let (labels, sink) = label_sink();
|
||||
let result = wait_for_install_deps(
|
||||
"uptime-kuma",
|
||||
|| async { Ok(probe(false, false, &[])) },
|
||||
sink,
|
||||
36,
|
||||
Duration::ZERO,
|
||||
)
|
||||
.await;
|
||||
assert!(result.is_ok());
|
||||
assert!(labels.lock().unwrap().is_empty());
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mempool_api_is_directly_installable_and_covered_by_the_archival_gate() {
|
||||
// `mempool-api` is a legitimate direct `package.install` target
|
||||
|
||||
@@ -3,9 +3,10 @@ use super::config::{
|
||||
is_readonly_compatible, is_valid_docker_image,
|
||||
};
|
||||
use super::dependencies::{
|
||||
check_bitcoin_pruning_compatibility, check_install_deps, configure_fedimint_lnd,
|
||||
check_bitcoin_pruning_compatibility, configure_fedimint_lnd, detect_existing_containers,
|
||||
detect_running_deps, detect_running_deps_from_package_data, log_optional_dep_info,
|
||||
needs_archy_net, RunningDeps,
|
||||
needs_archy_net, wait_for_install_deps, DepProbe, RunningDeps, DEP_WAIT_INTERVAL,
|
||||
DEP_WAIT_MAX_ATTEMPTS,
|
||||
};
|
||||
use super::progress::parse_pull_progress;
|
||||
use super::validation::validate_app_id;
|
||||
@@ -265,8 +266,7 @@ impl RpcHandler {
|
||||
.await;
|
||||
|
||||
if matches!(package_id, "mempool" | "mempool-web") {
|
||||
let deps = self.running_deps_for_install(package_id).await?;
|
||||
check_install_deps(package_id, &deps)?;
|
||||
self.gate_install_deps(package_id).await?;
|
||||
check_bitcoin_pruning_compatibility(package_id).await?;
|
||||
}
|
||||
|
||||
@@ -289,9 +289,11 @@ impl RpcHandler {
|
||||
// Dependency checks. Prefer the scanner's cached package state so a
|
||||
// congested Podman API does not turn an already-running dependency into
|
||||
// a false install failure. Fall back to a bounded direct Podman probe
|
||||
// only when the cache does not show the dependency.
|
||||
let deps = self.running_deps_for_install(package_id).await?;
|
||||
check_install_deps(package_id, &deps)?;
|
||||
// only when the cache does not show the dependency. When the dependency
|
||||
// is installed but not Running yet (the "clicked Install LND 55s before
|
||||
// Bitcoin was up" race), wait up to ~3 minutes for it instead of
|
||||
// failing instantly.
|
||||
let deps = self.gate_install_deps(package_id).await?;
|
||||
check_bitcoin_pruning_compatibility(package_id).await?;
|
||||
log_optional_dep_info(package_id, &deps);
|
||||
let repaired_bitcoin_conf =
|
||||
@@ -945,6 +947,27 @@ impl RpcHandler {
|
||||
}
|
||||
}
|
||||
|
||||
/// Bounded dependency gate for installs: passes immediately when deps are
|
||||
/// running, fails fast (with the phantom-tile marker) when a dependency
|
||||
/// isn't installed at all, and otherwise waits up to
|
||||
/// `DEP_WAIT_MAX_ATTEMPTS × DEP_WAIT_INTERVAL` for an installed-but-
|
||||
/// starting dependency, surfacing "Waiting for X to start…" on the card.
|
||||
pub(super) async fn gate_install_deps(&self, package_id: &str) -> Result<RunningDeps> {
|
||||
wait_for_install_deps(
|
||||
package_id,
|
||||
|| async {
|
||||
Ok(DepProbe {
|
||||
running: self.running_deps_for_install(package_id).await?,
|
||||
existing: detect_existing_containers().await,
|
||||
})
|
||||
},
|
||||
|msg| async move { self.set_install_message(package_id, &msg).await },
|
||||
DEP_WAIT_MAX_ATTEMPTS,
|
||||
DEP_WAIT_INTERVAL,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
// -- Private helpers for install --
|
||||
|
||||
/// Pull the image from a registry or verify a local image exists.
|
||||
@@ -1295,6 +1318,11 @@ impl RpcHandler {
|
||||
// Default to full archive — operators with 2TB+ drives shouldn't be
|
||||
// silently pruned down to 550 MB. Users who want a pruned node can
|
||||
// set `prune=N` in bitcoin.conf themselves after install.
|
||||
//
|
||||
// printtoconsole=0: bitcoind already writes debug.log in the datadir
|
||||
// (self-shrunk on restart); duplicating it to stdout pushed every IBD
|
||||
// "UpdateTip" line through conmon into journald (>1 GB/day). Deep
|
||||
// debugging uses /var/lib/archipelago/bitcoin/debug.log.
|
||||
let bitcoin_conf = format!(
|
||||
"\
|
||||
# rpcauth: salted hash only - no plaintext password in config or CLI\n\
|
||||
@@ -1304,7 +1332,7 @@ rpcallowip=0.0.0.0/0\n\
|
||||
listen=1\n\
|
||||
rpcthreads=16\n\
|
||||
rpcworkqueue=256\n\
|
||||
printtoconsole=1\n",
|
||||
printtoconsole=0\n",
|
||||
rpcauth_line
|
||||
);
|
||||
tokio::fs::create_dir_all(bitcoin_dir)
|
||||
|
||||
@@ -61,6 +61,31 @@ impl RpcHandler {
|
||||
self.state_manager.update_data(data).await;
|
||||
}
|
||||
|
||||
/// Set a user-facing install status message (e.g. "Waiting for Bitcoin
|
||||
/// to start…") without disturbing the current phase/byte counters.
|
||||
pub(super) async fn set_install_message(&self, package_id: &str, message: &str) {
|
||||
let (mut data, _rev) = self.state_manager.get_snapshot().await;
|
||||
let entry = data
|
||||
.package_data
|
||||
.entry(package_id.to_string())
|
||||
.or_insert_with(|| create_installing_entry(package_id));
|
||||
if entry.state != PackageState::Updating {
|
||||
entry.state = PackageState::Installing;
|
||||
}
|
||||
let (size, downloaded, phase) = entry
|
||||
.install_progress
|
||||
.as_ref()
|
||||
.map(|p| (p.size, p.downloaded, p.phase))
|
||||
.unwrap_or((0, 0, None));
|
||||
entry.install_progress = Some(InstallProgress {
|
||||
size,
|
||||
downloaded,
|
||||
phase,
|
||||
message: Some(message.to_string()),
|
||||
});
|
||||
self.state_manager.update_data(data).await;
|
||||
}
|
||||
|
||||
/// Clear install progress after pull completes or fails.
|
||||
pub(super) async fn clear_install_progress(&self, package_id: &str) {
|
||||
let (mut data, _rev) = self.state_manager.get_snapshot().await;
|
||||
|
||||
@@ -1009,9 +1009,9 @@ impl RpcHandler {
|
||||
return Ok(adopted);
|
||||
}
|
||||
|
||||
// Dependency check: Bitcoin must be running
|
||||
let deps = super::dependencies::detect_running_deps().await?;
|
||||
super::dependencies::check_install_deps("btcpay-server", &deps)?;
|
||||
// Dependency check: Bitcoin must be running. Bounded wait covers the
|
||||
// "installed but still starting" race instead of failing instantly.
|
||||
self.gate_install_deps("btcpay-server").await?;
|
||||
|
||||
install_log("INSTALL START: btcpay-server (stack: postgres + nbxplorer + btcpay)").await;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user