dnsdist: Account for the health-check run time between two runs

We used to wait one full second between every run, which only makes
sense if the runs are not taking a long time. But as soon as we have
at least one check timing out, the run is taking roughly the time
of the longest timeout configured, so after this commit we:
- do not wait at all if the last run took more than a full second
- wait one second minus the elapsed time of the last run otherwise

diff --git a/pdns/dnsdist.cc b/pdns/dnsdist.cc
index 06aa910ab68f91e832c0853007591d388951f93b..e786041e6857154e394641166a1e50bdb0514481 100644 (file)
--- a/pdns/dnsdist.cc
+++ b/pdns/dnsdist.cc
@@ -2027,11 +2027,24 @@ static void healthChecksThread()
 {
   setThreadName("dnsdist/healthC");
 
-  constexpr int interval = 1;
+  constexpr int intervalUsec = 1000 * 1000;
+  struct timeval lastRound{
+    .tv_sec = 0,
+    .tv_usec = 0
+  };
   auto states = g_dstates.getLocal(); // this points to the actual shared_ptrs!
 
   for (;;) {
-    sleep(interval);
+    struct timeval now;
+    gettimeofday(&now, nullptr);
+    auto elapsedTimeUsec = uSec(now - lastRound);
+    if (elapsedTimeUsec < intervalUsec) {
+      usleep(intervalUsec - elapsedTimeUsec);
+      gettimeofday(&lastRound, nullptr);
+    }
+    else {
+      lastRound = now;
+    }
 
     std::unique_ptr<FDMultiplexer> mplexer{nullptr};
     for (auto& dss : *states) {