r15939@catbus: nickm | 2007-10-18 22:14:15 -0400

 Remember the valid-until time of the most recent consensus that listed
 a router, and (if we are a cache) never delete the routerdesc until
 that conensus is expired.  This is way easier than retaining multiple
 consensuses.  (Of course, the info isn't retained across restarts,
 but that only affects a few caches at a time.) 
 


svn:r12041

5 files changed, 53 insertions, 5 deletions

diff --git a/ChangeLog b/ChangeLog
index 6c8f6d5ef..cdbad9619 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -21,6 +21,9 @@ Changes in version 0.2.0.9-alpha - 2007-10-??
     - If we find a cached-routers file that's been sitting around for more
       than 28 days unmodified, then most likely it's a leftover from when we
       upgraded to 0.2.0.8-alpha.  Remove it.  It has no good routers anyway.
+    - When we (as a cache) download a descriptor because it was listed in a
+      consensus, remember when the consensus was supposed to expire, and
+      don't expire the descriptor until then.
 
   o Minor features (performance):
     - Call routerlist_remove_old_routers() much less often.  This should
diff --git a/src/or/networkstatus.c b/src/or/networkstatus.c
index 83029627e..b1afddfb8 100644
--- a/src/or/networkstatus.c
+++ b/src/or/networkstatus.c
@@ -1049,6 +1049,8 @@ routers_update_all_from_networkstatus(time_t now)
   routers_update_status_from_consensus_networkstatus(rl->routers, 0);
   SMARTLIST_FOREACH(rl->routers, routerinfo_t *, ri,
                     ri->routerlist_index = ri_sl_idx);
+  if (rl->old_routers)
+    signed_descs_update_status_from_consensus_networkstatus(rl->old_routers);
   entry_guards_compute_status();
 
   me = router_get_my_routerinfo();
@@ -1216,6 +1218,11 @@ routers_update_status_from_consensus_networkstatus(smartlist_t *routers,
       else
         router->is_named = 0;
     }
+    if (!memcmp(router->cache_info.signed_descriptor_digest,
+                rs->descriptor_digest, DIGEST_LEN)) {
+      if (ns->valid_until > router->cache_info.last_listed_as_valid_until)
+        router->cache_info.last_listed_as_valid_until = ns->valid_until;
+    }
 
     if (!authdir) {
       /* If we're not an authdir, believe others. */
@@ -1239,6 +1246,31 @@ routers_update_status_from_consensus_networkstatus(smartlist_t *routers,
   router_dir_info_changed();
 }
 
+/**DOCDOC*/
+void
+signed_descs_update_status_from_consensus_networkstatus(smartlist_t *descs)
+{
+  networkstatus_vote_t *ns = current_consensus;
+  if (!ns)
+    return;
+
+  if (!ns->desc_digest_map) {
+    char dummy[DIGEST_LEN];
+    /* instantiates the digest map. */
+    memset(dummy, 0, sizeof(dummy));
+    router_get_consensus_status_by_descriptor_digest(dummy);
+  }
+  SMARTLIST_FOREACH(descs, signed_descriptor_t *, d,
+  {
+    routerstatus_t *rs = digestmap_get(ns->desc_digest_map,
+                                       d->signed_descriptor_digest);
+    if (rs) {
+      if (ns->valid_until > d->last_listed_as_valid_until)
+        d->last_listed_as_valid_until = ns->valid_until;
+    }
+  });
+}
+
 /** Generate networkstatus lines for a single routerstatus_t object, and
  * return the result in a newly allocated string.  Used only by controller
  * interface (for now.) */
diff --git a/src/or/or.h b/src/or/or.h
index f37e8865b..afee5ce8d 100644
--- a/src/or/or.h
+++ b/src/or/or.h
@@ -1102,6 +1102,9 @@ typedef struct signed_descriptor_t {
   /** If saved_location is SAVED_IN_CACHE or SAVED_IN_JOURNAL, the offset of
    * this descriptor in the corresponding file. */
   off_t saved_offset;
+  /** The valid-until time of the most recent consensus that listed this
+   * descriptor.  0 for "never listed in a consensus, so far as we know." */
+  time_t last_listed_as_valid_until;
   /* If true, we do not ever try to save this object in the cache. */
   unsigned int do_not_cache : 1;
   /* If true, this item is meant to represent an extrainfo. */
@@ -3098,6 +3101,9 @@ void routers_update_all_from_networkstatus(time_t now);
 void routerstatus_list_update_from_consensus_networkstatus(time_t now);
 void routers_update_status_from_consensus_networkstatus(smartlist_t *routers,
                                                         int reset_failures);
+void signed_descs_update_status_from_consensus_networkstatus(
+                                                         smartlist_t *descs);
+
 char *networkstatus_getinfo_helper_single(routerstatus_t *rs);
 int getinfo_helper_networkstatus(control_connection_t *conn,
                                  const char *question, char **answer);
diff --git a/src/or/routerlist.c b/src/or/routerlist.c
index 6c7b252d9..27fb2dbf8 100644
--- a/src/or/routerlist.c
+++ b/src/or/routerlist.c
@@ -2791,7 +2791,8 @@ _compare_duration_idx(const void *_d1, const void *_d2)
  * indices <b>lo</b> or higher may be changed.
  */
 static void
-routerlist_remove_old_cached_routers_with_id(time_t cutoff, int lo, int hi,
+routerlist_remove_old_cached_routers_with_id(time_t now,
+                                             time_t cutoff, int lo, int hi,
                                              digestmap_t *retain)
 {
   int i, n = hi-lo+1;
@@ -2827,7 +2828,8 @@ routerlist_remove_old_cached_routers_with_id(time_t cutoff, int lo, int hi,
     signed_descriptor_t *r = smartlist_get(lst, i);
     signed_descriptor_t *r_next;
     lifespans[i-lo].idx = i;
-    if (retain && digestmap_get(retain, r->signed_descriptor_digest)) {
+    if (r->last_listed_as_valid_until >= now ||
+        (retain && digestmap_get(retain, r->signed_descriptor_digest))) {
       must_keep[i-lo] = 1;
     }
     if (i < hi) {
@@ -2933,6 +2935,7 @@ routerlist_remove_old_routers(void)
     for (i = 0; i < smartlist_len(routerlist->routers); ++i) {
       router = smartlist_get(routerlist->routers, i);
       if (router->cache_info.published_on <= cutoff &&
+          router->cache_info.last_listed_as_valid_until < now &&
           !digestmap_get(retain,router->cache_info.signed_descriptor_digest)) {
         /* Too old: remove it.  (If we're a cache, just move it into
          * old_routers.) */
@@ -2952,6 +2955,7 @@ routerlist_remove_old_routers(void)
   for (i = 0; i < smartlist_len(routerlist->old_routers); ++i) {
     sd = smartlist_get(routerlist->old_routers, i);
     if (sd->published_on <= cutoff &&
+        sd->last_listed_as_valid_until < now &&
         !digestmap_get(retain, sd->signed_descriptor_digest)) {
       /* Too old.  Remove it. */
       routerlist_remove_old(routerlist, sd, i--);
@@ -2987,13 +2991,14 @@ routerlist_remove_old_routers(void)
       hi = i;
     }
     if (memcmp(cur_id, r->identity_digest, DIGEST_LEN)) {
-      routerlist_remove_old_cached_routers_with_id(cutoff, i+1, hi, retain);
+      routerlist_remove_old_cached_routers_with_id(now,
+                                                   cutoff, i+1, hi, retain);
       cur_id = r->identity_digest;
       hi = i;
     }
   }
   if (hi>=0)
-    routerlist_remove_old_cached_routers_with_id(cutoff, 0, hi, retain);
+    routerlist_remove_old_cached_routers_with_id(now, cutoff, 0, hi, retain);
   //routerlist_assert_ok(routerlist);
 
  done:
diff --git a/src/or/routerparse.c b/src/or/routerparse.c
index d186af50c..2b5c29882 100644
--- a/src/or/routerparse.c
+++ b/src/or/routerparse.c
@@ -74,6 +74,7 @@ typedef enum {
   K_VOTE_DIGEST,
   K_CONSENSUS_DIGEST,
   K_CONSENSUS_METHODS,
+  K_CONSENSUS_METHOD,
 
   A_PURPOSE,
   _A_UNKNOWN,
@@ -339,7 +340,8 @@ static token_rule_t networkstatus_consensus_token_table[] = {
   T1( "known-flags",         K_KNOWN_FLAGS,     CONCAT_ARGS, NO_OBJ ),
 
   T01("client-versions",     K_CLIENT_VERSIONS, CONCAT_ARGS, NO_OBJ ),
-  T01("server-versions",     K_SERVER_VERSIONS, CONCAT_ARGS,    NO_OBJ ),
+  T01("server-versions",     K_SERVER_VERSIONS, CONCAT_ARGS, NO_OBJ ),
+  T01("consensus-method",    K_CONSENSUS_METHOD,    EQ(1),   NO_OBJ),
 
   END_OF_TABLE
 };