relay: Overload state on DNS timeout is now X% over Y secs

With this commit, we will only report a general overload state if we've
seen more than X% of DNS timeout errors over Y seconds. Previous
behavior was to report when a single timeout occured which is really too
small of a threshold.

The value X is a consensus parameters called
"overload_dns_timeout_scale_percent" which is a scaled percentage
(factor of 1000) so we can represent decimal points for X like 0.5% for
instance. Its default is 1000 which ends up being 1%.

The value Y is a consensus parameters called
"overload_dns_timeout_period_secs" which is the time period for which
will gather DNS errors and once over, we assess if that X% has been
reached ultimately triggering a general overload signal.

Closes #40491

Signed-off-by: David Goulet <dgoulet@torproject.org>

1 files changed, 78 insertions, 0 deletions

diff --git a/src/test/test_stats.c b/src/test/test_stats.c
index 081ae22cd5..e85ad40699 100644
--- a/src/test/test_stats.c
+++ b/src/test/test_stats.c
@@ -51,6 +51,8 @@
 #include "feature/stats/bw_array_st.h"
 #include "feature/relay/router.h"
 
+#include <event2/dns.h>
+
 /** Run unit tests for some stats code. */
 static void
 test_stats(void *arg)
@@ -865,6 +867,81 @@ test_overload_stats(void *arg)
   tor_free(stats_str);
 }
 
+/** Test the overload stats logic. */
+static void
+test_overload_dns_timeout(void *arg)
+{
+  char *stats_str = NULL;
+  (void) arg;
+
+  /* Lets simulate a series of timeouts but below our default 1% threshold. */
+
+  for (int i = 0; i < 1000; i++) {
+    /* This should trigger 9 timeouts which is just below 1% (10) */
+    if (i > 0 && !(i % 100)) {
+      rep_hist_note_dns_error(0, DNS_ERR_TIMEOUT);
+    } else {
+      rep_hist_note_dns_error(0, DNS_ERR_NONE);
+    }
+  }
+
+  /* No overload yet. */
+  stats_str = rep_hist_get_overload_general_line();
+  tt_assert(!stats_str);
+
+  /* Move it 10 minutes in the future and see if we get a general overload. */
+  update_approx_time(approx_time() + (10 * 60));
+
+  /* This query should NOT trigger the general overload because we are below
+   * our default of 1%. */
+  rep_hist_note_dns_error(0, DNS_ERR_NONE);
+  stats_str = rep_hist_get_overload_general_line();
+  tt_assert(!stats_str);
+
+  /* We'll now go above our 1% threshold. */
+  for (int i = 0; i < 1000; i++) {
+    /* This should trigger 10 timeouts which is our threshold of 1% (10) */
+    if (!(i % 10)) {
+      rep_hist_note_dns_error(0, DNS_ERR_TIMEOUT);
+    } else {
+      rep_hist_note_dns_error(0, DNS_ERR_NONE);
+    }
+  }
+
+  /* Move it 10 minutes in the future and see if we get a general overload. */
+  update_approx_time(approx_time() + (10 * 60));
+
+  /* This query should trigger the general overload because we are above 1%. */
+  rep_hist_note_dns_error(0, DNS_ERR_NONE);
+  stats_str = rep_hist_get_overload_general_line();
+  tt_assert(stats_str);
+  tor_free(stats_str);
+
+  /* Move 72h in the future, we should NOT get an overload anymore. */
+  update_approx_time(approx_time() + (72 * 3600));
+
+  stats_str = rep_hist_get_overload_general_line();
+  tt_assert(!stats_str);
+
+  /* This query should NOT trigger the general overload. */
+  rep_hist_note_dns_error(0, DNS_ERR_TIMEOUT);
+  stats_str = rep_hist_get_overload_general_line();
+  tt_assert(!stats_str);
+
+  /* Move it 10 minutes in the future and see if we get a general overload. We
+   * have now 100% of requests timing out. */
+  update_approx_time(approx_time() + (10 * 60));
+
+  /* This query should trigger the general overload with 50% of timeouts. */
+  rep_hist_note_dns_error(0, DNS_ERR_NONE);
+  stats_str = rep_hist_get_overload_general_line();
+  tt_assert(stats_str);
+  tor_free(stats_str);
+
+ done:
+  tor_free(stats_str);
+}
+
 #define ENT(name)                                                       \
   { #name, test_ ## name , 0, NULL, NULL }
 #define FORK(name)                                                      \
@@ -881,6 +958,7 @@ struct testcase_t stats_tests[] = {
   FORK(rephist_v3_onions),
   FORK(load_stats_file),
   FORK(overload_stats),
+  FORK(overload_dns_timeout),
 
   END_OF_TESTCASES
 };