[tor-commits] [tor/master] Fix various issues with fallback directory data handling

[nickm at torproject.org]

commit da968e558e89b3ee9201d6c9cdd339ef48979071
Author: teor (Tim Wilson-Brown) <teor2345 at gmail.com>
Date:   Tue Jan 12 14:15:22 2016 +1100

    Fix various issues with fallback directory data handling
    
    * support maximum history age in _avg_generic_history()
    * fix division-by-zero trap in _avg_generic_history()
    * skip missing (i.e. null/None) intervals in _avg_generic_history()
    * Python timedelta.total_seconds() function not available in 2.6;
      replace with equivalent expression
    * set DEBUG logging level to make relay exclusion reasons visible
    * move CUTOFF_GUARD test to end in order to expose more exclusion
      reasons
    
    Patch by "starlight", merge modifications by "teor".
---
 changes/bug18035                    |    6 ++++++
 scripts/maint/updateFallbackDirs.py |   28 ++++++++++++++++++++--------
 2 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/changes/bug18035 b/changes/bug18035
new file mode 100644
index 0000000..31889f5
--- /dev/null
+++ b/changes/bug18035
@@ -0,0 +1,6 @@
+  o Minor fixes (fallback directories):
+    - Work around an issue where OnionOO supplies the entire history,
+      rather than the requested 120 days. Activate debug logging by
+      default. Fix other minor calculation and compatibility issues.
+      Closes ticket #18035. Patch by "starlight", merge fixes by
+      "teor". Not in any released version of tor.
diff --git a/scripts/maint/updateFallbackDirs.py b/scripts/maint/updateFallbackDirs.py
index 8fe234f..29be433 100755
--- a/scripts/maint/updateFallbackDirs.py
+++ b/scripts/maint/updateFallbackDirs.py
@@ -27,7 +27,7 @@ import dateutil.parser
 #from bson import json_util
 
 import logging
-logging.basicConfig(level=logging.INFO)
+logging.basicConfig(level=logging.DEBUG)
 
 ## Top-Level Configuration
 
@@ -579,9 +579,15 @@ class Candidate(object):
                      %(p, which))
       for v in reversed(h['values']):
         if (this_ts <= newest):
+          agt1 = now - this_ts
+          agt2 = interval
+          agetmp1 = (agt1.microseconds + (agt1.seconds + agt1.days * 24 * 3600)
+                     * 10**6) / 10**6
+          agetmp2 = (agt2.microseconds + (agt2.seconds + agt2.days * 24 * 3600)
+                     * 10**6) / 10**6
           generic_history.append(
-            { 'age': (now - this_ts).total_seconds(),
-              'length': interval.total_seconds(),
+            { 'age': agetmp1,
+              'length': agetmp2,
               'value': v
             })
           newest = this_ts
@@ -599,6 +605,8 @@ class Candidate(object):
   def _avg_generic_history(generic_history):
     a = []
     for i in generic_history:
+      if i['age'] > (ADDRESS_AND_PORT_STABLE_DAYS * 24 * 3600):
+        continue
       if (i['length'] is not None
           and i['age'] is not None
           and i['value'] is not None):
@@ -608,7 +616,11 @@ class Candidate(object):
     sv = math.fsum(map(lambda x: x[0], a))
     sw = math.fsum(map(lambda x: x[1], a))
 
-    return sv/sw
+    if sw == 0.0:
+      svw = 0.0
+    else:
+      svw = sv/sw
+    return svw
 
   def _add_generic_history(self, history):
     periods = r['read_history'].keys()
@@ -659,10 +671,6 @@ class Candidate(object):
       logging.debug('%s not a candidate: running avg too low (%lf)',
                     self._fpr, self._running)
       return False
-    if self._guard < CUTOFF_GUARD:
-      logging.debug('%s not a candidate: guard avg too low (%lf)',
-                    self._fpr, self._guard)
-      return False
     if self._v2dir < CUTOFF_V2DIR:
       logging.debug('%s not a candidate: v2dir avg too low (%lf)',
                     self._fpr, self._v2dir)
@@ -675,6 +683,10 @@ class Candidate(object):
     if (not self._data.has_key('recommended_version')
         or not self._data['recommended_version']):
       return False
+    if self._guard < CUTOFF_GUARD:
+      logging.debug('%s not a candidate: guard avg too low (%lf)',
+                    self._fpr, self._guard)
+      return False
     return True
 
   def is_in_whitelist(self, relaylist):