Merge branch 'bug20534_029_squashed' into maint-0.2.9

changes/bug20534

@@ -2,5 +2,7 @@
     - Remove the maximum delay on exponential-backoff scheduling.
       Since we now allow an infinite number of failures (see ticket
       20536), we must now allow the time to grow longer on each failure.
-      Fixes bug 20534; bugfix on 0.2.9.1-alpha.
-
+      Fixes part of bug 20534; bugfix on 0.2.9.1-alpha.
+    - Use initial delays and decrements in download scheduling closer to
+      those from 0.2.8. Fixes another part of bug 20534; bugfix on
+      0.2.9.1-alpha.

changes/bug20593

@@ -0,0 +1,6 @@
+  o Minor bugfixes (client directory scheduling):
+    - Treat "relay too busy to answer request" as a failed request and a
+      reason to back off on our retry frequency. This is safe now that
+      exponential backups retry indefinitely, and avoids a bug where we would
+      reset our download schedule erroneously.
+      Fixes bug 20593; bugfix on 0.2.9.1-alpha.

src/or/config.c

@@ -501,7 +501,7 @@ static config_var_t option_vars_[] = {
    * When clients have authorities and fallbacks available, they use these
    * schedules: (we stagger the times to avoid thundering herds) */
   V(ClientBootstrapConsensusAuthorityDownloadSchedule, CSV_INTERVAL,
-    "10, 11, 3600, 10800, 25200, 54000, 111600, 262800" /* 3 days + 1 hour */),
+    "6, 11, 3600, 10800, 25200, 54000, 111600, 262800" /* 3 days + 1 hour */),
   V(ClientBootstrapConsensusFallbackDownloadSchedule, CSV_INTERVAL,
     "0, 1, 4, 11, 3600, 10800, 25200, 54000, 111600, 262800"),
   /* When clients only have authorities available, they use this schedule: */
@@ -512,7 +512,7 @@ static config_var_t option_vars_[] = {
    * blackholed. Clients will try 3 directories simultaneously.
    * (Relays never use simultaneous connections.) */
   V(ClientBootstrapConsensusMaxInProgressTries, UINT, "3"),
-  V(TestingBridgeDownloadSchedule, CSV_INTERVAL, "3600, 900, 900, 3600"),
+  V(TestingBridgeDownloadSchedule, CSV_INTERVAL, "1200, 900, 900, 3600"),
   V(TestingClientMaxIntervalWithoutRequest, INTERVAL, "10 minutes"),
   V(TestingDirConnectionMaxStall, INTERVAL, "5 minutes"),
   V(TestingConsensusMaxDownloadTries, UINT, "8"),

src/or/directory.c

@@ -3796,14 +3796,21 @@ next_random_exponential_delay(int delay, int max_delay)
 
   /* How much are we willing to add to the delay? */
   int max_increment;
+  const int multiplier = 3; /* no more than quadruple the previous delay */
 
-  if (delay)
-    max_increment = delay; /* no more than double. */
-  else
-    max_increment = 1; /* we're always willing to slow down a little. */
+  if (delay && delay < (INT_MAX-1) / multiplier) {
+    max_increment = delay * multiplier;
+  } else if (delay) {
+    max_increment = INT_MAX-1;
+  } else {
+    max_increment = 1;
+  }
+
+  if (BUG(max_increment < 1))
+    max_increment = 1;
 
-  /* the + 1 here is so that we include the end of the interval */
-  int increment = crypto_rand_int(max_increment+1);
+  /* the + 1 here is so that we always wait longer than last time. */
+  int increment = crypto_rand_int(max_increment)+1;
 
   if (increment < max_delay - delay)
     return delay + increment;
@@ -3933,15 +3940,16 @@ time_t
 download_status_increment_failure(download_status_t *dls, int status_code,
                                   const char *item, int server, time_t now)
 {
+  (void) status_code; // XXXX no longer used.
+  (void) server; // XXXX no longer used.
   int increment = -1;
   int min_delay = 0, max_delay = INT_MAX;
 
   tor_assert(dls);
 
-  /* only count the failure if it's permanent, or we're a server */
-  if (status_code != 503 || server) {
-    if (dls->n_download_failures < IMPOSSIBLE_TO_DOWNLOAD-1)
-      ++dls->n_download_failures;
+  /* count the failure */
+  if (dls->n_download_failures < IMPOSSIBLE_TO_DOWNLOAD-1) {
+    ++dls->n_download_failures;
   }
 
   if (dls->increment_on == DL_SCHED_INCREMENT_FAILURE) {