server: a query that finds every permit taken waits for one instead of failing, the budget is 64, permit and upstream turns wait on a futex with one thread each, the thread pool has no task limit, and transparent huge pages are off for the process

src/platform/huge_pages.zig

@@ -0,0 +1,36 @@
+//! Opting the process out of transparent huge pages.
+//!
+//! With THP set to `always`, the kernel backs any 2 MiB-aligned anonymous
+//! region with a huge page on first touch. Each worker thread's stack mapping
+//! qualifies, so a thread that touches a few KiB of stack can hold 2 MiB
+//! resident, and `std.Io.Threaded` never retires a worker: one burst on such a
+//! host left about 40 of 200 workers at 2 MiB each. nxdns's memory is sized
+//! for small pages, so the whole process opts out instead of chasing each
+//! mapping.
+
+const std = @import("std");
+const linux = std.os.linux;
+
+pub const DisableError = error{
+    /// A kernel older than 3.15, which has no such switch.
+    Unsupported,
+    Unexpected,
+};
+
+/// Sets `PR_SET_THP_DISABLE`, which covers every mapping of the process,
+/// existing and future, and is inherited across `fork`.
+pub fn disable() DisableError!void {
+    const rc = linux.prctl(@intFromEnum(linux.PR.SET_THP_DISABLE), 1, 0, 0, 0);
+    switch (linux.errno(rc)) {
+        .SUCCESS => {},
+        .INVAL => return error.Unsupported,
+        else => return error.Unexpected,
+    }
+}
+
+test "disable takes effect for the process" {
+    try disable();
+    const rc = linux.prctl(@intFromEnum(linux.PR.GET_THP_DISABLE), 0, 0, 0, 0);
+    try std.testing.expectEqual(linux.E.SUCCESS, linux.errno(rc));
+    try std.testing.expectEqual(@as(usize, 1), rc);
+}