tidaldb/tidal-net/tests/catchup_retry.rs

//! m11p4: the catch-up retry timer.
//!
//! The event path alone (re-pull on the next pushed segment) deadlocks an
//! idle cluster: a follower whose pull failed — e.g. the leader's gRPC
//! server was not yet ready during a rolling restart — waited for a push
//! that never came and stayed lagged forever (the 2026-06-11 p3 rollout
//! incident). These tests drive the REAL transports over real sockets: a
//! pull that fails against a not-yet-listening leader must self-heal on the
//! timer with NO push ever sent, and a pull that completes cleanly must not
//! keep re-pulling.

use std::{
    net::SocketAddr,
    sync::{
        Arc,
        atomic::{AtomicU64, Ordering},
    },
    time::{Duration, Instant},
};

use tidal_net::{
    GrpcTransport, GrpcTransportConfig,
    sources::{SegmentChunk, SegmentReadError, SegmentSource, ServingSources},
};
use tidaldb::replication::{shard::ShardId, transport::Transport};

/// Bind port 0 to obtain a free, OS-assigned address (tonic cannot bind 0
/// directly, so we resolve a concrete port up front).
fn free_addr() -> SocketAddr {
    let listener = std::net::TcpListener::bind("127.0.0.1:0").expect("bind");
    listener.local_addr().expect("local_addr")
}

/// A leader-side WAL read-back serving one synthetic chunk `[1..=5]`, plus a
/// stream-open counter (`flushed_seq` is read exactly once per
/// `StreamSegments` open, so it doubles as the open count).
struct FixedSegments {
    opens: Arc<AtomicU64>,
}

impl SegmentSource for FixedSegments {
    fn source_shard(&self) -> ShardId {
        ShardId(0)
    }
    fn stream_baseline(&self) -> u64 {
        0
    }
    fn flushed_seq(&self) -> u64 {
        self.opens.fetch_add(1, Ordering::AcqRel);
        5
    }
    fn collect_from(
        &self,
        from_seq: u64,
        _max_events: u64,
        _max_bytes: usize,
    ) -> Result<Vec<SegmentChunk>, SegmentReadError> {
        if from_seq > 5 {
            return Ok(vec![]);
        }
        Ok(vec![SegmentChunk {
            bytes: vec![0xAB; 16],
            first_seq: from_seq,
            last_seq: 5,
            event_count: 5 - from_seq + 1,
        }])
    }
}

fn follower_config(listen: SocketAddr, leader: SocketAddr) -> GrpcTransportConfig {
    GrpcTransportConfig {
        local_shard: ShardId(1),
        listen_addr: listen,
        // m11p5: `peers` is now a `host:port` string, not a SocketAddr.
        peers: std::iter::once((ShardId(0), leader.to_string())).collect(),
        insecure: true,
        // Short enough to keep the test fast; the re-arm-on-skip logic walks
        // it past MIN_CATCHUP_INTERVAL's 2s rate limit regardless.
        catchup_retry_interval: Duration::from_millis(300),
        ..GrpcTransportConfig::default()
    }
}

/// THE incident shape: the follower's only pull fails (leader not yet
/// listening), the cluster stays completely idle (no pushes, no further
/// `request_catchup`), and the data must still arrive — via the retry timer
/// alone.
#[test]
#[allow(clippy::significant_drop_tightening)] // transports intentionally live to test end
fn failed_pull_retries_on_timer_with_no_push() {
    let leader_addr = free_addr();
    let follower =
        GrpcTransport::new(follower_config(free_addr(), leader_addr)).expect("follower transport");

    // One pull while the leader is down: `tcp connect error`, exactly like
    // the rolling-restart race.
    follower.request_catchup(ShardId(0), 1);

    // The leader comes up ~200ms later. NOTHING else happens: no writes, no
    // pushes, no new request_catchup.
    std::thread::sleep(Duration::from_millis(200));
    let opens = Arc::new(AtomicU64::new(0));
    let leader_sources = ServingSources {
        applied: None,
        segments: Some(Arc::new(FixedSegments {
            opens: Arc::clone(&opens),
        })),
        applied_sink: Arc::default(),
        election: Arc::default(),
        snapshots: Arc::default(),
        snapshot_required: Arc::default(),
        catchup_served: Arc::default(),
        join: Arc::default(),
    };
    let _leader = GrpcTransport::new_with_sources(
        GrpcTransportConfig {
            local_shard: ShardId(0),
            listen_addr: leader_addr,
            insecure: true,
            ..GrpcTransportConfig::default()
        },
        leader_sources,
    )
    .expect("leader transport");

    // The retry cadence is 300ms, but the shared MIN_CATCHUP_INTERVAL rate
    // limit (2s) defers real attempts — the re-arm-on-skip logic must carry
    // the wake-up across those skips. Allow a generous deadline; typical
    // arrival is ~2.5s.
    let deadline = Instant::now() + Duration::from_secs(15);
    let payload = loop {
        if let Some(p) = follower.try_recv_segment() {
            break p;
        }
        assert!(
            Instant::now() < deadline,
            "catch-up payload never arrived: the retry timer is not firing \
             (followers would stay lagged forever in an idle cluster)"
        );
        std::thread::sleep(Duration::from_millis(25));
    };

    assert_eq!(payload.id.shard_id, ShardId(0));
    assert_eq!(
        payload.id.seqno, 1,
        "the pull starts at the requested seqno"
    );
    assert_eq!(payload.leader_last_seq, 5);
    assert_eq!(payload.event_count, 5);
}

/// A pull that completes cleanly must NOT keep the timer alive: no further
/// streams open once the follower is caught up (the retry exists for FAILED
/// pulls, not as a polling loop).
#[test]
#[allow(clippy::significant_drop_tightening)] // transports intentionally live to test end
fn clean_completion_does_not_keep_retrying() {
    let leader_addr = free_addr();
    let opens = Arc::new(AtomicU64::new(0));
    let leader_sources = ServingSources {
        applied: None,
        segments: Some(Arc::new(FixedSegments {
            opens: Arc::clone(&opens),
        })),
        applied_sink: Arc::default(),
        election: Arc::default(),
        snapshots: Arc::default(),
        snapshot_required: Arc::default(),
        catchup_served: Arc::default(),
        join: Arc::default(),
    };
    let _leader = GrpcTransport::new_with_sources(
        GrpcTransportConfig {
            local_shard: ShardId(0),
            listen_addr: leader_addr,
            insecure: true,
            ..GrpcTransportConfig::default()
        },
        leader_sources,
    )
    .expect("leader transport");

    let follower =
        GrpcTransport::new(follower_config(free_addr(), leader_addr)).expect("follower transport");

    // The leader is up: the one pull succeeds.
    follower.request_catchup(ShardId(0), 1);
    let deadline = Instant::now() + Duration::from_secs(10);
    while follower.try_recv_segment().is_none() {
        assert!(Instant::now() < deadline, "the healthy pull must succeed");
        std::thread::sleep(Duration::from_millis(25));
    }
    let opens_after_success = opens.load(Ordering::Acquire);
    assert_eq!(opens_after_success, 1, "exactly one stream served the pull");

    // Wait past several retry intervals AND the 2s MIN_CATCHUP_INTERVAL rate
    // limit: a buggy always-armed timer would only produce its real re-open
    // once the rate limit allows (~2.1s), so a shorter wait would miss it.
    std::thread::sleep(Duration::from_millis(2600));
    assert_eq!(
        opens.load(Ordering::Acquire),
        opens_after_success,
        "a completed pull must not keep re-opening streams on the timer"
    );
}