milestone 30: overview as a dashboard, explicit health contract, period aggregations

This commit is contained in:
2026-08-22 16:45:15 +02:00
parent 0e83477d80
commit 623667e475
89 changed files with 7222 additions and 4239 deletions
+1 -62
View File
@@ -31,7 +31,6 @@ const dns_handler = @import("../server/handler.zig");
const disk_monitor = @import("../storage/disk_monitor.zig");
const dot_server = @import("../server/dot_server.zig");
const events_mod = @import("../storage/events.zig");
const history_mod = @import("../upstream/history.zig");
const http_util = @import("http_util.zig");
const logging = @import("../platform/logging.zig");
const pool_mod = @import("../upstream/pool.zig");
@@ -136,9 +135,6 @@ pub const Sample = struct {
tracker: ?TrackerSample = null,
client_names: ?client_names.Resolver.Stats = null,
retention: ?retention_mod.Stats = null,
/// The upstream-history flush loop's counters (m26 ruling 7). Absent while
/// no accumulator is wired, like every other collaborator.
history: ?history_mod.Accumulator.Stats = null,
/// The diagnostics store's open episodes and its failed writes. Absent
/// while no store is wired, like every other collaborator — an operator
/// distinguishes "no series" from "zero episodes" through `/api/health`,
@@ -218,8 +214,6 @@ pub fn collect(state: *server.WebState, io: std.Io, arena: Allocator) Allocator.
if (state.retention) |retention| sample.retention = retention.snapshotStats();
if (state.history) |history| sample.history = history.snapshotStats(io);
if (state.events) |store| {
const counts = store.activeCounts(io);
sample.diagnostics = .{
@@ -382,36 +376,6 @@ pub fn render(w: *std.Io.Writer, sample: Sample) std.Io.Writer.Error!void {
try counterGroup(w, "nxdns_retention_", "Query log retention counter", retention);
}
if (sample.history) |history| {
// Written out rather than reflected over `Accumulator.Stats`: three of
// its fields are counters, one is a gauge, and two — the drop watermark
// and the current flush state — are not exposition numbers at all.
try counter(
w,
"nxdns_upstream_history_flushes_total",
"Upstream history flush transactions that committed.",
history.flushes,
);
try counter(
w,
"nxdns_upstream_history_flush_failures_total",
"Upstream history flush attempts that failed; the rows are retried on the next pass.",
history.flush_failures,
);
try counter(
w,
"nxdns_upstream_history_rows_dropped_total",
"Upstream history minutes dropped because the accumulator was full.",
history.rows_dropped,
);
try gauge(
w,
"nxdns_upstream_history_pending",
"Upstream history minutes recorded but not yet flushed.",
history.pending,
);
}
if (sample.diagnostics) |diagnostics| {
try gauge(
w,
@@ -638,7 +602,7 @@ fn writeUpstreamLabels(
/// through this function too, so the guarantee cannot be one caller away.
/// `UpstreamSample.url` stays whole for the same reason it is safe to: nothing
/// but this function reads it, and the session-authenticated
/// `GET /api/upstream/health` reports the same pool with the same urls whole.
/// `GET /api/upstreams` reports the same urls whole.
///
/// **`redact` output is not safe to interpolate into a label value, and this
/// function is the reason it never has to be.** Do not delete the second layer
@@ -803,31 +767,6 @@ test "a full sample renders the whole exposition, byte for byte" {
));
}
test "the upstream-history family renders three counters and one gauge" {
const text = try renderToString(testing.allocator, .{
.history = .{
.flushes = 12,
.flush_failures = 2,
.rows_dropped = 5,
.pending = 3,
.last_drop_minute = 1_700_000_040,
.last_flush_failed = true,
},
});
defer testing.allocator.free(text);
try testing.expect(std.mem.containsAtLeast(u8, text, 1, "nxdns_upstream_history_flushes_total 12\n"));
try testing.expect(std.mem.containsAtLeast(u8, text, 1, "nxdns_upstream_history_flush_failures_total 2\n"));
try testing.expect(std.mem.containsAtLeast(u8, text, 1, "nxdns_upstream_history_rows_dropped_total 5\n"));
try testing.expect(std.mem.containsAtLeast(u8, text, 1, "# TYPE nxdns_upstream_history_pending gauge\n"));
try testing.expect(std.mem.containsAtLeast(u8, text, 1, "nxdns_upstream_history_pending 3\n"));
// No accumulator is an absent family, not a family of zeros.
const bare = try renderToString(testing.allocator, .{});
defer testing.allocator.free(bare);
try testing.expect(!std.mem.containsAtLeast(u8, bare, 1, "nxdns_upstream_history_"));
}
test "the diagnostics family renders two gauges and one counter" {
const text = try renderToString(testing.allocator, .{
.diagnostics = .{ .active_warnings = 3, .active_errors = 1, .write_failures = 7 },