upstream: one absolute per-query budget across queueing and failover

waiting for a slot now spends the query budget; truncated attempts that
expire fault the budget, not the upstream, and are never attributed.
admission sweeps in priority order before blocking. forward zones spend
read_timeout_ms once across udp, truncation and tcp. adds
nxdns_upstream_budget_exhausted_total and a 64-upstream validation limit.
This commit is contained in:
2026-08-27 21:10:43 +02:00
parent 6170571d23
commit 72cdbbd113
16 changed files with 1598 additions and 207 deletions
+39 -2
View File
@@ -166,6 +166,12 @@ pub const Sample = struct {
udp_listener: ?udp_server.Snapshot = null,
tcp_listener: ?tcp_server.Snapshot = null,
upstreams: []const UpstreamSample = &.{},
/// Exchanges the pool gave up on because the request's own budget ran out.
/// Pool-wide rather than per-upstream on purpose: budget exhaustion is
/// evidence about the pool, never about an endpoint, so it carries no url
/// label and cannot live in `UpstreamSample`. Absent while no pool is
/// wired, like every other collaborator.
upstream_budget_exhausted_total: ?u64 = null,
};
pub fn handle(
@@ -271,7 +277,10 @@ pub fn collect(state: *server.WebState, io: std.Io, arena: Allocator) Allocator.
if (state.upstreams) |owner| {
const generation = owner.acquire(io);
defer owner.release(io, generation);
if (generation.pool) |pool| sample.upstreams = try upstreams(pool, io, arena);
if (generation.pool) |pool| {
sample.upstreams = try upstreams(pool, io, arena);
sample.upstream_budget_exhausted_total = pool.budgetExhaustedTotal();
}
}
return sample;
@@ -465,6 +474,15 @@ pub fn render(w: *std.Io.Writer, sample: Sample) std.Io.Writer.Error!void {
if (sample.doh_certs != null or sample.dot_certs != null) try renderCerts(w, sample);
if (sample.upstreams.len != 0) try renderUpstreams(w, sample.upstreams);
if (sample.upstream_budget_exhausted_total) |total| {
try labeledHead(
w,
"nxdns_upstream_budget_exhausted_total",
"Exchanges that ran out of their own total budget before any upstream answered.",
"counter",
);
try w.print("nxdns_upstream_budget_exhausted_total {d}\n", .{total});
}
}
fn renderCerts(w: *std.Io.Writer, sample: Sample) std.Io.Writer.Error!void {
@@ -1540,7 +1558,7 @@ test "the queue families carry what a real pool recorded, through the real snaps
.priority = 10,
.enabled = true,
.health = .init,
.sem = .{ .permits = slots.len },
.admission = .{ .permits = slots.len },
.reuse_recoveries = &recoveries,
}};
var pool: pool_mod.Pool = .init(&entries, .{}, .{
@@ -1662,3 +1680,22 @@ fn fieldIndex(comptime name: []const u8) usize {
}
@compileError("no such counter: " ++ name);
}
test "the budget-exhausted counter renders pool-wide, without a url label" {
const text = try renderToString(testing.allocator, .{ .upstream_budget_exhausted_total = 7 });
defer testing.allocator.free(text);
try testing.expect(std.mem.containsAtLeast(
u8,
text,
1,
"# TYPE nxdns_upstream_budget_exhausted_total counter\n",
));
try testing.expect(std.mem.containsAtLeast(u8, text, 1, "nxdns_upstream_budget_exhausted_total 7\n"));
// No pool, no series: an operator tells "no upstreams wired" from "zero
// exhausted budgets" the same way every other collaborator is told.
const absent = try renderToString(testing.allocator, .{});
defer testing.allocator.free(absent);
try testing.expect(!std.mem.containsAtLeast(u8, absent, 1, "nxdns_upstream_budget_exhausted_total"));
}