Previously, a function for continuing IO processing on the next UV
tick was introduced (http_do_bio_async()). The intention behind this
function was to ensure that http_do_bio() is eventually called at
least once in the future. However, the current implementation allows
queueing multiple such delayed requests needlessly. There is currently
no need for these excessive requests as http_do_bio() can requeue them
if needed. At the same time, each such request can lead to a memory
allocation, particularly in BIND 9.18.
This commit ensures that the number of enqueued delayed IO processing
requests never exceeds one in order to avoid potentially bombarding IO
threads with the delayed requests needlessly.
(cherry picked from commit
0e1b02868a63d2c4f6f0c414b20d4b999adbcc46)
size_t data_in_flight;
+ bool async_queued;
+
/*
* The statistical values below are for usage on server-side
* only. They are meant to detect clients that are taking too many
REQUIRE(VALID_HTTP2_SESSION(session));
+ session->async_queued = false;
+
if (session->handle != NULL &&
!isc__nmsocket_closing(session->handle->sock))
{
REQUIRE(VALID_HTTP2_SESSION(session));
if (session->handle == NULL ||
- isc__nmsocket_closing(session->handle->sock))
+ isc__nmsocket_closing(session->handle->sock) ||
+ session->async_queued)
{
return;
}
+ session->async_queued = true;
isc__nm_httpsession_attach(session, &tmpsess);
isc__nm_async_run(
&session->handle->sock->mgr->workers[session->handle->sock->tid],