Serialize build retirement and clone classification, bound ops accepts

Review fixes for M7.6-M7.9. Schema v9 applies one lock order: the
barrier takes a database-wide upgrade lock exclusively, while
acquisitions, lease checks, provisioning and the retired-build trigger
take it shared first, so a queued acquisition can no longer regain
authority for a just-retired build and concurrent barriers cannot
retire the last current build. Provisioning takes a per-world lock
before classifying a world as original or a clone of one source. The
operations listener makes at most four accept attempts per serve().
Race regressions prove each contender is blocked before commit.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
dingo
2026-09-29 08:38:13 -04:00
co-authored by Claude Opus 5.5
parent f59cca2c3b
commit 168c90d5b2
14 changed files with 616 additions and 15 deletions
+77
View File
@@ -1,9 +1,11 @@
// M7.8 operational endpoints on real evo-server processes (ADR-0066): liveness is
// never authority, readiness follows the lease, metrics are bounded, and the
// responder is bounded against idle, excess and malformed clients.
#include "evo/server/ops_http.hpp"
#include "fixtures/server_process.hpp"
#include <algorithm>
#include <arpa/inet.h>
#include <atomic>
#include <netinet/in.h>
#include <source_location>
#include <sys/socket.h>
@@ -184,9 +186,84 @@ void stale_process_is_live_not_ready() {
current.signal(SIGTERM);
CHECK(stale.wait_exit(20s) == 0 && current.wait_exit(20s) == 0);
}
// Review fix: accept work per serve() is bounded, refused connections included, so
// replenished connection pressure cannot hold the host loop; accepted connections
// are still answered while the pressure continues.
void accept_work_is_bounded_per_serve() {
using evo::server::OpsServer;
auto made = OpsServer::listen("127.0.0.1:0");
CHECK(made);
auto& ops = **made;
const auto handler = [](std::string_view) { return evo::server::OpsResponse{200, "ok\n"}; };
constexpr auto per = OpsServer::max_accepts_per_serve;
std::vector<int> clients;
clients.reserve(64);
for (int i = 0; i < 16; ++i)
clients.push_back(connect_local(ops.port())); // Queued in the listen backlog.
std::this_thread::sleep_for(50ms);
ops.serve(handler);
CHECK(ops.open_connections() == per && ops.refused() == 0);
ops.serve(handler);
CHECK(ops.open_connections() == OpsServer::max_connections && ops.refused() == 0);
// At the connection cap, each call still refuses at most the budget.
ops.serve(handler);
CHECK(ops.open_connections() == OpsServer::max_connections && ops.refused() == per);
// The first accepted client is answered while new connections keep arriving.
const std::string request = "GET /livez HTTP/1.1\r\n\r\n";
CHECK(::send(clients[0], request.data(), request.size(), MSG_NOSIGNAL) ==
static_cast<ssize_t>(request.size()));
for (int round = 0; round < 6; ++round) {
clients.push_back(connect_local(ops.port()));
const auto before = ops.refused();
ops.serve(handler);
CHECK(ops.refused() - before <= per);
}
char reply[64] = {};
CHECK(::recv(clients[0], reply, sizeof reply - 1, 0) > 0);
CHECK(std::string_view(reply).starts_with("HTTP/1.1 200"));
for (const int fd : clients)
::close(fd);
}
// A real server under sustained connection churn keeps its lease and readiness.
void connection_pressure_keeps_authority() {
const auto r = provision(54, 0x0D);
Child server{with_ops(r)};
const auto port = ops_port(server);
CHECK(server.wait_for([](const std::string& l) { return l == "ready 1"; }, 15s));
std::atomic<bool> stop{false};
std::thread flood([&] {
while (!stop.load()) {
const int fd = ::socket(AF_INET, SOCK_STREAM | SOCK_CLOEXEC, 0);
sockaddr_in address{};
address.sin_family = AF_INET;
address.sin_port = htons(port);
address.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
if (fd >= 0) {
// Refusal or backlog overflow is part of the pressure; ignore it.
[[maybe_unused]] const int connected =
::connect(fd, reinterpret_cast<sockaddr*>(&address), sizeof address);
::close(fd);
}
}
});
// Longer than the fast lease (4 s): renewals must keep happening under pressure.
server.send(input_lines(1, 60, false));
const bool acked = server.wait_line("ack " + request_hex(60) + " 60 ", 20s);
stop = true;
flood.join();
CHECK(acked);
CHECK(!server.printed("ready 0"));
CHECK(get(port, "/readyz").status == 200);
server.signal(SIGTERM);
CHECK(server.wait_exit(20s) == 0);
}
} // namespace
void run_region_ops_tests() {
accept_work_is_bounded_per_serve();
connection_pressure_keeps_authority();
probes_follow_authority_and_stay_bounded();
unavailable_database_is_live_not_ready();
stale_process_is_live_not_ready();