Installing /etc/fips/fips.yaml as a live dpkg conf-file collides with a
configuration-management-rendered or operator-edited config on upgrade:
dpkg either prompts interactively (keep/replace), stalling unattended
upgrades, or clobbers the local file. Ship the default config as
/usr/share/doc/fips/fips.yaml.example (mode 644) and drop it from
conf-files. postinst now seeds /etc/fips/fips.yaml from the example only
when it does not already exist (mode 600), yielding to any existing
config without a prompt or clobber. Add ConditionPathExists for the
config to the service unit so a missing config skips the unit cleanly
rather than crash-looping.
A busy node opens roughly three file descriptors per established UDP peer
(a connect()-ed socket plus a 2-FD drain self-pipe), so the default 1024
soft RLIMIT_NOFILE is exhausted near 320 peers and further peer admission,
handshakes, and discovery fail with EMFILE. Document the FD budget, the
symptom, and the systemd (LimitNOFILE drop-in) and OpenWrt (procd nofile)
procedures to raise it, plus how to verify the per-peer ratio is bounded.
Link the new guide from the how-to index.
Bring the local runner (testing/ci-local.sh) and GitHub CI into agreement
on two axes.
Suite coverage: the admission-cap integration suite ran only locally, so a
regression in it could never turn the GitHub gate red. Add an admission-cap
leg to the integration matrix, add testing/check-ci-parity.sh (wired as
'ci-local.sh --check-parity') to diff the two suite sets and fail on
unexpected drift, and document the deliberate local-only (live-Tor) and
granularity-only differences in a comment block atop both runners.
Toolchain selection: every CI and packaging job installed its toolchain
with dtolnay/rust-toolchain@stable, but the rust-toolchain.toml channel pin
overrode it for all compilation, wasting an install and printing a
misleading rustc version. Switch the stable call sites to
actions-rust-lang/setup-rust-toolchain, which reads rust-toolchain.toml as
the single source of truth. Keep the explicit cache steps (cache: false on
the new action), set rustflags empty so the action does not impose a global
-D warnings the previous setup never applied, fold the macOS cross-compile
target into the action input, and leave the OpenWrt nightly Tier-3 leg on
dtolnay/rust-toolchain@nightly.
When two peers each auto_connect to the other, each runs both an
initiator and a responder NAT-traversal session and binds a separate
UDP socket per session. Each side adopts only the first Established
event and drops the loser session's socket; when the two sides adopt
mismatched sessions, each sends its Noise msg1 to a peer port the peer
has already stopped draining, and both handshakes stall.
Deterministically keep the session initiated by the smaller NodeAddr,
decided on the responder path: decline an incoming offer only when we
also have an in-flight outbound initiator for the same peer and our
NodeAddr is smaller. The peer's redundant initiator then times out,
leaving a single matching socket pair on both ends. Asymmetric
(one-sided) auto_connect has no co-active initiator and is never
suppressed, so connectivity is preserved; an undecidable NodeAddr falls
through to answering.
Reuses the NodeAddr tie-breaker convention already used by the
cross-connection and rekey dual-init paths. Adds a unit test for the
election helper.
Add wait_until_connected to the shared convergence helpers: it polls a
suite's own pairwise pings (the signal it actually asserts on), returns
as soon as every pair is reachable, extends its deadline while the
reachable-pair count is still climbing, and gives up only when progress
stalls.
Use it in the rekey, static-mesh, and sidecar suites in place of the
fixed wall-clock baseline timeout and the blind sleep, which timed out
under concurrent CI load while the mesh was still converging.
Add a Loopback variant to TransportHandle backed by an unbounded
in-process channel and a shared address-to-receiver registry, so
node-level multi-node tests deliver packets directly between nodes
instead of over real localhost UDP sockets. This removes the kernel
UDP receive-buffer overflow that dropped handshake packets when many
tests ran in parallel under CPU contention, and lets the large-network
convergence tests run reliably in the default suite again (their
parallel-load ignore markers are removed).
The new transport and its enum variant are cfg(test)-gated, so the
daemon build is unaffected.
The FMP rekey msg1 resend driver retransmitted indefinitely with no cap
and no abandon, so a rekey that never completed kept resending msg1
forever. Give it a retransmission budget: cap resends at
handshake_max_resends with exponential backoff and abandon the rekey
cycle cleanly once the budget is exhausted, mirroring the FSP session
rekey msg3 driver.
With the cap in place the link-dead heartbeat can safely become
rekey-aware: check_link_heartbeats now suppresses teardown while a rekey
is in progress with msg1 budget remaining, instead of reaping a link
that is still actively carrying rekey-handshake traffic. The suppression
terminates deterministically (the budget abandons on exhaustion, cutover
clears the in-progress flag), so a genuinely dead link is still reaped on
the next cycle.
Adds a rekey_msg1_resend_count counter on ActivePeer reset at every
rekey-clear and cutover site, msg1 resend-budget unit tests, and two-node
heartbeat suppression/resume/regression integration tests.
Remove the duplicated immutable fields (config, identity, startup_epoch,
started_at, is_leaf_only, max_connections/peers/links) from the Node
struct so the Arc<NodeContext> bundle is the single source of truth.
Previously Node owned these fields and a parallel context copy, kept in
lockstep by rebuild_context() at every mutation site — pure overhead that
existed only because of the duplication.
- Replace rebuild_context() with replace_context(): a clone-edit-swap of
the whole Arc. The per-instance context stays immutable; mutation swaps
the Arc. This is the sole runtime mutation path (constructors, leaf_only,
update_peers).
- Add Copy-returning accessors startup_epoch() and max_connections()/
max_peers()/max_links(); migrate the remaining direct field readers onto
the accessors. node_addr()/npub()/Debug now read identity/is_leaf_only
from the context.
- update_peers reads the pre-update peer set from the live context Arc
before building a fresh Config + context and swapping — preserving the
read-before-write ordering its mutation-window test depends on.
- Remove the test-only set_max_* setters; tests set the limits on Config at
construction instead (new make_node_with_max_peers/links helpers).
- Add a ci-local guard that fails if the Node struct re-declares a bundled
field, so the single-store invariant can't silently regress.
cargo test --lib 1291/0; clippy -D warnings and release build clean.
Store node counters in an atomic metric registry read through &self, and
introduce a shared NodeContext bundle holding the effectively-immutable
fields (config, identity, startup epoch, capability limits). Source the
immutable config and identity reads across the receive hot path, the
handshake/session/mmp/encrypted state machines, and the discovery, tree,
bloom, retry, and lifecycle modules through the context accessors rather
than direct field reads. The Node fields and the context are rebuilt in
lockstep at every mutation site.
PeerRecvDrain::drop previously called std::thread::join on the worker
thread synchronously. The worker uses packet_tx.blocking_send on a
tokio mpsc Sender, which internally parks the worker via
tokio::block_on on the same current_thread runtime that drives
rx_loop. Calling join from inside remove_active_peer (which runs on
the runtime thread, the runtime's sole driver) created a circular
wait:
- rx_loop blocks in libc futex via Thread::join
- the worker being joined cannot observe the stop flag because the
runtime that polls it is the very thread now blocked joining it
- all other PeerRecvDrain workers park on the same runtime via
block_on, so a single peer's removal wedges every worker on the
daemon
The /proc snapshot from a production wedge showed exactly this
shape: 107 of 108 threads in futex_do_wait, 101 of them named
fips-peer-drain. fipsctl became unresponsive (EAGAIN on control
socket), SIGTERM was ignored, and Docker SIGKILLed the container
after the 10 s grace period. Two confirmed wedges on the public
test deployment (52 min and 23 min uptime), plus a third on the
admission-gate-Msg2-silent-drop build at 2 min 21 sec — all ending
with the identical "Peer removed and state cleaned up
tree_changed=false" final log line preceding total silence.
Fix: detach the std::thread instead of joining. The stop flag plus
self-pipe write already signal the worker to exit; the worker's
kernel-level libc::poll inside the drain loop sees the wake, checks
the flag, exits, and the OS reclaims the thread state independently
of the JoinHandle being dropped.
The trigger was statistically amplified by aggressive multi-npub-
from-one-NAT peer reconnect patterns at the moment of the 30 s
link-dead-timeout peer-removal, but not bounded to them. Any
peer whose disconnect happens with the per-peer drain worker
parked in block_on can fire the bug. The admission-gate work
that landed earlier in this branch line compressed more handshake
work per rx_loop tick, increasing the rate at which workers are
parked in block_on and so reducing time-to-wedge — but the
underlying bug pre-dated the admission gate and pre-dated this
fix branch.
The deployed wedged daemon is mitigated operationally by blocking
the trigger IP at the host firewall; this commit removes the bug
class entirely.
Bring the refactor-hotpath integration branch into master: explicit
RejectReason counters for previously-silent receive-path drop sites
across the tree, discovery, and handshake handlers, plus the Reloadable
trait and ArcSwap-backed hot-reload consolidation for the host map and
peer ACL. Includes the new discovery dedup-cache-full reject counter.
The discovery request dedup cache (recent_requests) silently dropped
LookupRequests once it reached MAX_RECENT_DISCOVERY_REQUESTS, with no
counter to surface the condition. Add a DiscoveryReject::ReqDedupCacheFull
reject reason backed by a req_dedup_cache_full counter on DiscoveryStats,
mirroring the existing duplicate-request counter, and record it at the
drop site so the rejection is visible in show_routing.
Bring the runtime peer-list refresh and opt-in mDNS LAN discovery work
on master into the receive-path RejectReason / reloadable-config
integration branch. Code files auto-merge clean; the only conflict is
the CHANGELOG Unreleased section, resolved as the union of both sets of
entries.
Add scoped mDNS / DNS-SD discovery for peers on the same local link,
giving sub-second pairing without a relay or NAT-traversal roundtrip.
A node advertises its npub, protocol version, and an optional network
scope over link-local multicast, and browses for matching adverts to
initiate Noise handshakes against same-LAN peers.
LAN discovery is disabled by default; operators enable it with
node.discovery.lan.enabled: true. Default-off avoids reintroducing a
per-LAN identity broadcast on nodes that have deliberately disabled
other discovery channels, and avoids any multicast surprise on upgrade.
The startup advertised-port picker now excludes bootstrap transports
and selects a non-bootstrap operational UDP transport with a stable
lowest-id selector, so the advertised port is deterministic across
restarts rather than dependent on HashMap iteration order. This
matches the per-dial transport selection used for discovered peers.
Co-authored-by: Johnathan Corgan <johnathan@corganlabs.com>
Add Node::update_peers for runtime peer-list refresh. It re-derives the
active peer connections from a new peer configuration, adding newly
configured peers and removing those no longer present, while keeping
links to peers that remain in the set rather than tearing every
connection down. The call returns an UpdatePeersOutcome summarizing the
added, removed, and retained peers.
PeerAddress gains a seen_at_ms recency field (with_seen_at_ms). Active
path selection now sorts address candidates by recency so the most
recently observed address wins when concurrent path probes race.
complete_rekey_msg2 now returns the remote peer's startup epoch
alongside the new Noise session, letting the rekey path detect a peer
restart and clear stale session state. A stale FSP session is cleared
when a peer restart is detected during FMP rekey or cross-connection
promotion, so the session-layer map no longer lingers out of sync with
the freshly promoted peer.
Per-tick work budgets bound the connection churn in a single node tick
(MAX_DISCOVERY_CONNECTS_PER_TICK, MAX_RETRY_CONNECTIONS_PER_TICK,
MAX_PARALLEL_PATH_CANDIDATES_PER_PEER); work beyond a tick's budget is
deferred to the next tick rather than discarded.
Co-authored-by: Johnathan Corgan <johnathan@corganlabs.com>
Move PeerAclReloader onto the Reloadable trait: its ACL snapshot is now
published through an arc_swap::ArcSwap so the authorization hot path reads
it without locking, and the former check_reload becomes the trait's
reload(). The node tick calls self.peer_acl.reload().await.
Wire the host map into the tick as well. The host map snapshot was
previously taken once at construction and never polled; it now hot-reloads
on /etc/fips/hosts mtime changes once per tick, alongside the ACL, so
hostname display reflects edits without a restart.
The path_mtu_lookup cache (event-driven, populated from observed traffic)
and the nostr_discovery subsystem (an async spawned task) are deliberately
left off the trait: neither reloads from a backing file, so a no-op reload()
would be misleading. The rationale is documented on the trait module.
The host map and the ACL's embedded alias reloader still stat /etc/fips/hosts
independently each tick. A single small-file stat per tick is cheap, so the
duplicate is left in place; sharing one mtime observation between the two is
a possible future cleanup.
Tests: a node-level test exercises the host-map tick reload end to end
through peer_display_name; the ACL reloader tests are updated to drive the
async reload().
Add a `Reloadable` trait that normalizes the node's reloadable
configuration/resource pattern onto a single contract built around an
`arc_swap::ArcSwap` snapshot: a lock-free `load()` for the hot read path
and an async `reload()` that re-reads the backing source and atomically
swaps in a fresh snapshot. The trait carries the canonical Arc-wrapper
template documentation (single-writer node tick, many-reader hot path,
whole-snapshot swap so readers never observe a partial update).
Migrate the host map to this trait via a new `HostMapReloadable` that
reuses the existing load/merge/mtime helpers in upper::hosts. The Node
`host_map` field changes from `Arc<HostMap>` to `HostMapReloadable`, and
`peer_display_name` reads through a lock-free guard. The initial snapshot
is byte-identical to the previous construction, so behavior is unchanged.
The host map is still snapshotted once at construction and not polled;
`reload()` is exercised only by unit tests for now. Wiring the periodic
poll into the node tick, and deduplicating the hosts-file stat against
the ACL reloader's embedded copy, is left as a follow-up.
Add `arc-swap` as a dependency. Unit tests cover initial load (base +
file, base only), change/no-change/deletion/creation detection,
base-preserved-on-reload, and equivalence of the initial snapshot to the
pre-migration construction.
Introduce a typed RejectReason enum and a NodeStats::record_reject
dispatch so every receive-path rejection-and-return site bumps a
machine-readable per-subsystem counter while keeping its operator-facing
log line. The top-level variants mirror the existing NodeStats subsystem
split (Tree, Bloom, Discovery, Forwarding) and add Handshake, Session,
Mmp, and Transport categories; HandshakeStats, SessionStats, and MmpStats
are new sub-stats.
Wired clusters: tree and MMP outbound sign-failure; the FSP session
unknown-session and state-machine cluster; the Noise IK handshake
state-machine cluster (msg1/msg2); and the decode / crypto / cap /
semantic tail across bloom, discovery, forwarding, mmp, and tree. The
TreeStats::ancestry_invalid counter, present since the scaffold but never
incremented, is now bumped from the validate_semantics ancestry rejection.
Several handshake, MMP, tree, and discovery paths that previously had no
counter at all are now counted, including the send_lookup_response
no-route drop (DiscoveryStats::resp_no_route).
Existing direct counters at the bloom / discovery / forwarding sites are
retained alongside the new dispatch while the rollout is in progress (the
bloom_poison tests expect the transitional +2 delta); a later change
collapses the duplicate increment.
Raise the in-process backpressure headroom in make_test_node_with_mtu
(request an 8 MiB recv_buf_size on UdpConfig and grow packet_channel from
256 to 8192) to reduce localhost-UDP receive overflow under parallel-CPU
scheduler contention, and mark the large-network convergence tests
#[ignore] so cargo test --lib stays green by default. The ignored tests
remain runnable on demand with --ignored or --test-threads=1.
Add per-direction pool_inbound/pool_outbound counters to TcpStats and
TorStats, updated at every pool-insert, receive-loop-exit, transport-stop,
and send-failure removal site. Compare the max_inbound_connections cap
against pool_inbound rather than the combined pool length, so outbound
connect-on-send connections no longer consume the operator-facing inbound
budget. The configuration field name and operator semantics are preserved;
only the cap-check comparison and accounting change.
New integration scenario verifying the early-gate silent-drop behavior
of the inbound max_peers admission check at sustained scale, using the
existing 5-node mesh topology with one node's node.limits.max_peers
lowered to 1. This forces 2 of the cap'd node's 3 configured peers
into a sustained denied state, and asserts via tcpdump that no Msg2
responses go back to those denied peers across a 60s capture window.
A background load-driver restarts the denied peer containers every 15s
to reset their auto-reconnect exponential backoff (5s base / 300s cap),
producing fresh Msg1 bursts each cycle. Without this loop the gate
fires ~3-4 times per denied peer in a 60s window; with restarts the
observed rate is 15 per denied peer (~30 total firings), high enough
that any Msg2 leakage would be caught with strong statistical
confidence.
Local run on this branch: cap'd node-c converged to peer_count=1 with
node-b admitted; nodes d and e sustained-retried as denied; tcpdump
captured 30 inbound Msg1 (len 84) packets from the denied pair and 0
outbound Msg2 (len 104) packets, with final peer_count unchanged.
Files:
testing/static/scripts/admission-cap-test.sh — new test script with
inject-config subcommand (sets node.limits.max_peers) and a
3-phase test driver (converge, capture-with-load, per-peer assert)
testing/ci-local.sh — register admission-cap as a new suite category
(ADMISSION_SUITES), wire run_admission_cap function, add to
run_suite dispatch, list_suites, and the default integration sweep
Together with the existing unit-level coverage in src/node/tests/unit.rs
(handle_msg1_silent_drops_at_cap_for_new_peer with mock-transport Msg2
discriminator, and handle_msg1_admits_existing_peer_at_cap as the
bypass regression guard), the gate's silent-drop behavior is now
verified both at single-firing wire-observable resolution and at
sustained multi-firing cross-process scale.
Move the max_peers cap check in handle_msg1 forward, from the late
check inside promote_connection (which fires after Msg2 has already
been built and put on the wire) to an early position after identity
verification but before index allocation and the Msg2 send. When the
gate fires for a net-new identity, the Msg1 is silent-dropped — no
response goes back to the peer, no AEAD compute or wire bytes are
spent.
Bypass preserved for known peers (reconnect / cross-connection): if
the sender's NodeAddr is already in self.peers, or if a pending
outbound connection is in flight to the same identity, the gate is
skipped so legitimate maintenance traffic continues to work. The
late check inside promote_connection is intentionally retained as
defense-in-depth against future call sites or a disconnect racing
between the early-gate decision and promotion.
Wire-cost rationale: a 45 s tcpdump at saturation observed ~3.6
cap-denials/s steady-state, each previously paying the full Noise IK
responder crypto + Msg2 (~104 B) on the wire before being rejected.
The bigger value is cleaner peer-side semantics — the peer no longer
sees a fake-completed handshake whose data frames subsequently fail
decryption locally.
Two new unit tests cover the cases:
- handle_msg1_silent_drops_at_cap_for_new_peer drives a wire-pumped
Msg1 from a fresh identity into a saturated node and asserts no
Msg2 reaches the sender socket. Stash-verifies as FAIL on the
pre-fix tree (Msg2 hits the wire) and PASS post-fix.
- handle_msg1_admits_existing_peer_at_cap drives a Msg1 from an
identity already in self.peers and asserts the gate does not evict
it. This is a regression check (the no-gate tree behaves the same
way here, but the test guards against an accidental future gate
that breaks known-peer admit).
Brings two structural fixes landed on maint:
- compute_mesh_size: explicit parent skip in the children loop, so the
disjoint-subtree invariant no longer depends on peer_declaration cache
freshness.
- max_peers: outbound connection-initiation gated on the cap (auto-reconnect
retries, Nostr-mediated discovery established adoption, and both sides
of the NAT-traversal punch sequence). Inbound msg1 admission gate
unchanged.
node.limits.max_peers was honored only on inbound msg1 admission
(handshake.rs handle_msg1 returns PeerLimitExceeded when peers.len
is at the cap). Four outbound initiation paths proceeded unconditionally
at capacity: auto-reconnect retries (process_pending_retries),
Nostr-mediated discovery's BootstrapEvent::Established adoption
(poll_nostr_discovery), NAT-traversal punch initiation (the outgoing
side of the offer/answer/punch sequence in the Nostr discovery
runtime), and NAT-traversal punch response (the incoming side of the
same sequence). A saturated node burned CPU, UDP probes, STUN
observations, and Nostr relay traffic on connections that the inbound
gate would reject the moment they reached msg1.
Introduce Node::outbound_admission_check (peers.len < max_peers, or
true when max_peers == 0 as the no-cap sentinel) and gate the four
paths. The discovery runtime lives in a separate task and does not
hold a Node reference; bridge via an Arc<AtomicBool> the runtime
reads and Node refreshes once per tick from outbound_admission_check.
The atomic granularity is intentionally loose: one-tick lag is
acceptable because the inbound msg1 gate continues to be the
authoritative cap, and in-flight handshakes started below the cap
are allowed to complete.
Inbound gate at handshake.rs is unchanged.
The mesh-size estimator's children loop relied on the cached
peer_declaration(parent_id).parent_id() != my_addr check to exclude
the parent. That cached view briefly disagrees with our own latest
my_declaration().parent_id() during the window between a local
parent-switch and the new parent's next inbound TreeAnnounce: the
peer-declaration cache still names us as the parent's parent, so the
parent is iterated as if it were a child and its (typically dominant)
bloom cardinality is added a second time. Symptom: estimated mesh size
displayed in fipsctl show status and fipstop nearly-but-not-exactly
doubles during tree rebalancing.
Make the invariant structural with an explicit peer_addr == parent_id
skip at the head of the children loop. Per-peer 500 ms rate-limiter
and overall recompute cadence are unchanged.
Adds a regression test that constructs the stale-peer-declaration
scenario directly and asserts the parent is not double-counted.
Adds a tree/mmp-targeted compose overlay (compose-trace-tree.yml) and
a new FIPS_MESH_LAB_TRACE_TREE env-var gate in run_rekey_family,
layered independently of the existing FIPS_MESH_LAB_TRACE rekey-class
overlay. Trace targets: fips::node::tree, fips::tree,
fips::node::handlers::mmp, fips::node::handlers::handshake.
Used for tree-partition race investigations during multi-peer startup
where evaluate_parent inputs, send_tree_announce_to_all recipient
enumeration, and process_receiver_report first-RTT triggers all need
to be visible together to bracket the loss window.
Extend parse_rekey to emit phase1_status / phase1_baseline_passed /
phase1_baseline_total fields in signature.json by scraping rekey-test.sh's
"Best observed baseline before timeout: N/M passed" line (the timeout
path) and "Pre-rekey baseline (all 20 pairs): N/M passed" (the success
path). Phase-5-shape parsing is unchanged.
Extend mechanism_match_rekey to also fire on the Phase 1 characteristic
12/20 split — the multi-hop-routing-failure shape where direct-peer pairs
pass and the four multi-hop pairs (x 2 directions) fail. The Phase 5
predicate remains intact for the pre-existing flake class.
Add FIPS_MESH_LAB_NO_RESOURCE_LIMITS=1 to run_rekey_family for
unconstrained characterization runs where the goal is to surface a race
or scheduling artefact rather than reproduce GHA pressure. Default
behaviour (variable unset) keeps the compose-resource-limits.yml overlay
engaged.
Documented in README.md and the in-script env-var header block.
Closes the eventually-consistent gap in spanning-tree state
distribution. Every existing send_tree_announce_to_all call site
gates on a local state-change event (parent switch, self-root
promotion, ancestry change, peer promotion, parent loss). Once a
partition latches — for example a parent-switch announce stranded
in the brief cross-init handshake swap window, where the announce
arrives on a session-index whose decrypt-worker entry has been
unregistered — neither side's state changes again, so neither
side ever re-broadcasts. The existing 60 s check_periodic_parent_reeval
was a re-evaluation, not a re-broadcast: it short-circuited
silently on no-change. Production-side healing depended on
incidental link churn; lab harnesses with stable docker-bridge
links had no equivalent path.
Add a final else branch that fires send_tree_announce_to_all
unconditionally on the no-change path, alongside the existing
switch and self-promote arms. Receivers coalesce by sequence
comparison (ParentDeclaration::is_fresher_than) and short-circuit
at the `if !updated` gate in handle_tree_announce; same-sequence
repeats drop silently with no cascade. The per-peer 500 ms
rate-limiter is well below this 60 s cadence and does not suppress
the heartbeat broadcast.
The fix is a general protocol-robustness improvement: it addresses
any in-flight TreeAnnounce loss class, not only the specific
cross-init swap-window drop site.
testing/static/scripts/rekey-test.sh BASELINE_CONVERGENCE_TIMEOUT
60 -> 65 so a partition healed by the periodic broadcast at T+60
lands inside the convergence window. wait_for_full_baseline
early-exits on PASS, so successful reps see no extra wall-clock.
The cross-connection-won path in handle_msg1 removes the old peer and frees
its allocated index, but does not unregister the old (transport_id, our_index)
cache_key from the decrypt worker pool. The orphan entry sits in the
per-shard HashMap until the index allocator recycles old_idx to a different
peer and that peer's register_decrypt_worker_session call overwrites it.
In the interim, any decrypt job that lands at the recycled cache_key
resolves to the wrong session and AEAD silently fails — observed as
multi-hop routing failure in 5-node static-mesh on next-branch where
bidirectional auto_connect drives cross-connections at every peer pair
on startup.
The tick body's per-peer check_* loops (heartbeats, bloom
announces, MMP reports, tree announces) called transport.send
for every active peer, which on TCP/Tor fell through to a 5 s
connect-on-send wait for any peer whose pool entry was not yet
established. That wedged the entire tick body for the full
connect_timeout_ms per unreachable peer; under post-restart
convergence on a high-peer mesh, this cascaded into multi-
second tick stalls. On master, the same mechanism also starved
the per-tick control-snapshot republish and pushed fipsctl
queries onto an mpsc fallback that was itself queued behind
the wedged rx_loop, producing the 5-second fipsctl head-of-line
pattern operators observed on loaded nodes.
Gate send_encrypted_link_message_with_ce on
transport.connection_state before the send: proceed only when
Connected; on None, kick off a non-blocking background connect
(idempotent — TransportHandle::connect dedupes against the
connecting pool and spawns the timeout-bounded TcpStream::connect
inside its own tokio task) and fail this send fast with a
clear "transport connection not ready" error. A subsequent
tick retries once the pool has an entry. The reconnect
lifecycle (check_link_heartbeats, process_pending_retries,
poll_pending_connects) is unchanged. The connect-on-send
branch in transport.send_async itself remains in place for
code paths that legitimately need synchronous connect (e.g.,
explicit operator-driven fipsctl connect).
When both peers' Nostr-mediated UDP punches complete within the
same scheduling window, each side's `BootstrapEvent::Established`
event arrives with `is_connecting_to_peer` already true: each side
received an inbound msg1 from the peer's pre-punch outbound
attempt, which created a connecting-state record. The deduplication
skip then fires on both sides, neither installs the fresh
traversal socket as canonical, and the peer-adoption budget
(45 s) expires. Cross-node wall-clock alignment of the skip log
line in observed failures was within ~1 ms — simultaneous dual-
fire under contention, the dual-initiation pattern.
Apply the deterministic NodeAddr tie-breaker already used at
`handlers/handshake.rs:269` for rekey dual-initiation and in
`peer::cross_connection_winner` for cross-connection resolution.
Smaller NodeAddr wins as adopter: enumerate the in-flight
connections whose `expected_identity` points at this peer, tear
them down via the canonical `cleanup_stale_connection` helper, and
fall through to `adopt_established_traversal`. Larger NodeAddr
loses and keeps the existing `continue` semantics; the loser's
in-flight outbound is reconciled by `handle_msg1`'s cross-
connection logic when the winner's fresh msg1 arrives over the
adopted socket.
`cleanup_stale_connection` visibility bumped from module-private
to `pub(in crate::node)` so it is callable from `lifecycle.rs`.
The defensive re-check inside `adopt_established_traversal`
itself is left as-is — after the outer cleanup the winner reaches
it with `is_connecting_to_peer == false`, so the inner skip
won't trip. The `BootstrapEvent::Failed` arm is unchanged: there
is no winning outcome on dual failure, and the existing skip +
retry-schedule semantics are correct.
Three deltas to the mesh-lab nat-lan suite for stall characterization:
- FIPS_NAT_LAN_CPUSET env-var-driven CPU-pinning sidecar in
run_nat_lan, mirroring the bloom-storm pattern. Pinning is needed
because the mesh-lab compose-resource-limits.yml override is
rekey-family service-name specific (rekey-* / rekey-accept-off-* /
rekey-outbound-only-*), so it does not constrain the nat-lan
containers. Default cpuset 0,1 mimics a GHA 2-core runner; empty
disables the sidecar.
- New compose-trace-nat.yml overlay that bumps RUST_LOG to trace on
discovery::nostr, transport::udp, node::lifecycle,
handlers::handshake, handlers::forwarding — the modules covering
the cross-init / adoption / handshake path. Picked up by the
nat-test.sh COMPOSE array via a new FIPS_NAT_EXTRA_COMPOSE
colon-separated env-var hook. run_nat_lan sets this hook when
FIPS_MESH_LAB_TRACE is non-empty; the README env-var section
updated to reflect that FIPS_MESH_LAB_TRACE now applies to nat-lan
in addition to the rekey-family.
- parse_nat_lan extended with a per-node stall_signature emitting
last-occurrence timestamps for eight event categories (startup,
discovery, adoption, handshake_init, msg2_sent, cross_init_ignore_*,
handshake_failed) plus derived last_meaningful_event_ts,
last_event_category, silent_gap_s. Top-level stall_class binned as
no_timeout / silent / localized / distributed / incomplete from
the per-node categories. Aggregation phase consumes the per-rep
signatures across a characterization run to classify stall
mechanism.
Wired support in nat-test.sh: FIPS_NAT_EXTRA_COMPOSE colon-separated
list of repo-relative or absolute compose files layered onto the
base via the COMPOSE array; FIPS_NAT_SKIP_FINAL_CLEANUP gates the
success-path teardown so the mesh-lab harness can capture docker
logs before tearing down (failure paths already returned without
cleanup, leaving stall-state containers intact for capture).
Smoke-tested on idle profile with TRACE on: 1 rep PASS, 32/36 TRACE
lines per node, signature.json events all populated with the
expected category timestamps.
The bloom-storm scenario's bloom_send_rate ceiling has been bumped
from 30 to 40 sends per node over the trailing 30 s window. A 59-rep
characterization run under `github-runner-equivalent` pressure with
per-container CPU pinning to `cpuset=0,1` (mimicking a 2-core
`ubuntu-latest` runner) measured n04 (the structural max-spike node)
at mean 24.4, P99 29, max 30. The original ceiling of 30 sat at the
lab's structural max, leaving no headroom for the asymmetric transient
spikes observed on GitHub Actions (n04=34 on master CI run 25933972365,
re-fired on run 26008950865). GHA fires do not reproduce on this lab
host even with the cpuset sidecar applied.
Rationale: lab max + ~2σ ≈ 39.4 → round to 40, giving 33 % margin over
the lab maximum while staying well below the deployment-scale storm
rate (~480× steady state). The companion `min_parent_switches` guard
is unchanged.
See README.md alongside this file for the updated threshold derivation.
Wires the bloom-storm chaos scenario into the mesh-lab harness as
a first-class suite, with optional per-container CPU pinning to
mimic GitHub Actions' 2-core ubuntu-latest budget.
Dispatch path — three new run-loop.sh functions plus the
dispatch_suite and dispatch_mechanism_match case-arm additions:
- `run_bloom_storm` invokes `bash testing/chaos/scripts/chaos.sh
bloom-storm` and captures stdout+stderr into the rep's
test-output.log. Chaos uses its own python sim runner
(`python3 -m sim`), not docker-compose, so this suite gets no
per-container compose override, no separate `docker logs`
capture, and no in-container netem injection — the chaos
scenario yaml owns its own netem and link-swap config.
- `parse_bloom_storm` extracts the bloom_send_rate result
(pass/fail/unknown), ceiling, max-observed per-node delta,
offenders list, full per-node delta distribution, the companion
min_parent_switches result, and panic + error counts. Lands in
the rep's signature.json. Two parser details: assertion greps
are anchored on `^(PASS|FAIL)` so they only match the bare
end-of-run summary line, not python-logger-prefixed lines that
contain the same substring; and `grep -c` panic/error counts
use `; true` + a defensive empty-string check instead of the
common `|| echo 0` fallback (`grep -c` exits 1 on zero matches
while also printing "0", so the fallback would corrupt the
count to "0\\n0").
- `mechanism_match_bloom_storm` returns true when a rep both
fails the bloom_send_rate assertion and the FAIL line carries
a named offender (filtering the harness-side "failed to sample
window endpoints" sub-failure out of the mechanism count).
CPU-pinning sidecar — bloom-storm's chaos sim spawns containers
directly via the docker SDK, so the mesh-lab compose-resource-
limits override does not apply. A poll-and-pin loop around the
chaos.sh invocation lists \`fips-*\` containers every 0.5 s and
applies \`docker update --cpuset-cpus <set>\` to each. Pinning is
idempotent (re-applying the same cpuset is a no-op). Default
cpuset \`0,1\` mimics the GHA 2-core budget; override via
\`FIPS_BLOOM_STORM_CPUSET=<set>\` (any comma-separated CPU list),
or set to the empty string to disable. Only applies to the
bloom-storm suite; other suites' dispatch paths are unchanged.
README's "Suites supported" entry covers the assertion class, and
the \`FIPS_BLOOM_STORM_CPUSET\` knob is documented alongside the
other mesh-lab env-var knobs.
The cross-connection-won branch of `promote_connection` builds a
fresh ActivePeer with a new Noise session and our_index, inserts
it into peers, and registers identity, but did not hand the new
session to the decrypt shard worker pool. The normal-promotion
tail in the same function does make that call. A session
established via the cross-connection race path therefore missed
the worker fast-path for its lifetime, falling back to inline
decryption on the rx loop. Correctness was unaffected, but the
throughput/latency benefit of the worker pool was lost for peerspromoted through that path.
Mirror the normal-promotion tail and call
`register_decrypt_worker_session` after the fresh ActivePeer is
inserted into `self.peers` in the `this_wins` arm.
Logs source, destination, and payload size at the existing no-route
drop site so investigations can attribute transit drops without
enabling trace-level instrumentation. Diagnostic-only; no behavior
change on the success path.
Johnathan Corgan
Martti MalmiandJohnathan Corgan
