*** empty log message ***

Changes

@@ -1,8 +1,10 @@
 Revision history for libev, a high-performance and full-featured event loop.
 
-	- use 1-based heaps, simplifies code, reduces codesize, makes
-          for better cache-efficiency and increases memory requirements
-          by up to two pointers/loop.
+        - use 1-based 2-heap for EV_MINIMAL, simplifies code, reduces
+          codesize and makes for better cache-efficiency.
+        - use 3-based 4-heap for !EV_MINIMAL. this makes better use
+          of cpu cache lines and gives better growth behaviour than
+          2-based heaps.
         - fix a potential aliasing issue in ev_timer_again.
         - add/document ev_periodic_at, retract direct access to ->at.
         - improve ev_stat docs.

ev.c

@@ -810,6 +810,7 @@ downheap (WT *heap, int N, int k)
       // find minimum child
       if (expect_true (pos +3 < E))
         {
+          /* fast path */
                                    (minpos = pos + 0), (minat = (*minpos)->at);
           if (pos [1]->at < minat) (minpos = pos + 1), (minat = (*minpos)->at);
           if (pos [2]->at < minat) (minpos = pos + 2), (minat = (*minpos)->at);
@@ -817,9 +818,9 @@ downheap (WT *heap, int N, int k)
         }
       else
         {
+          /* slow path */
           if (pos >= E)
             break;
-
                                                   (minpos = pos + 0), (minat = (*minpos)->at);
           if (pos + 1 < E && pos [1]->at < minat) (minpos = pos + 1), (minat = (*minpos)->at);
           if (pos + 2 < E && pos [2]->at < minat) (minpos = pos + 2), (minat = (*minpos)->at);

ev.pod

@@ -2982,8 +2982,9 @@ defined to be C<0>, then they are not.
 =item EV_MINIMAL
 
 If you need to shave off some kilobytes of code at the expense of some
-speed, define this symbol to C<1>. Currently only used for gcc to override
-some inlining decisions, saves roughly 30% codesize of amd64.
+speed, define this symbol to C<1>. Currently this is used to override some
+inlining decisions, saves roughly 30% codesize of amd64. It also selects a
+much smaller 2-heap for timer management over the default 4-heap.
 
 =item EV_PID_HASHSIZE
 
@@ -3178,8 +3179,8 @@ have many watchers waiting for the same fd or signal).
 
 =item Finding the next timer in each loop iteration: O(1)
 
-By virtue of using a binary heap, the next timer is always found at the
-beginning of the storage array.
+By virtue of using a binary or 4-heap, the next timer is always found at a
+fixed position in the storage array.
 
 =item Each change on a file descriptor per loop iteration: O(number_of_watchers_for_this_fd)