Refactoring of the GC in preparation for parallel GC

  
This patch localises the state of the GC into a gc_thread structure,
and reorganises the inner loop of the GC to scavenge one block at a
time from global work lists in each "step".  The gc_thread structure
has a "workspace" for each step, in which it collects evacuated
objects until it has a full block to push out to the step's global
list.  Details of the algorithm will be on the wiki in due course.

At the moment, THREADED_RTS does not compile, but the single-threaded
GC works (and is 10-20% slower than before).

1 files changed, 14 insertions, 0 deletions

diff --git a/rts/RtsFlags.c b/rts/RtsFlags.c
index f8c8403328..69064ea743 100644
--- a/rts/RtsFlags.c
+++ b/rts/RtsFlags.c
@@ -212,6 +212,7 @@ void initRtsFlagsDefaults(void)
     RtsFlags.ParFlags.nNodes	        = 1;
     RtsFlags.ParFlags.migrate           = rtsTrue;
     RtsFlags.ParFlags.wakeupMigrate     = rtsFalse;
+    RtsFlags.ParFlags.gcThreads         = 1;
 #endif
 
 #ifdef PAR
@@ -445,6 +446,7 @@ usage_text[] = {
 #endif /* DEBUG */
 #if defined(THREADED_RTS) && !defined(NOSMP)
 "  -N<n>     Use <n> OS threads (default: 1)",
+"  -g<n>     Use <n> OS threads for GC (default: 1)",
 "  -qm       Don't automatically migrate threads between CPUs",
 "  -qw       Migrate a thread to the current CPU when it is woken up",
 #endif
@@ -1117,6 +1119,18 @@ error = rtsTrue;
 		      errorBelch("bad value for -N");
 		      error = rtsTrue;
 		    }
+		}
+		) break;
+
+	      case 'g':
+		THREADED_BUILD_ONLY(
+		if (rts_argv[arg][2] != '\0') {
+		    RtsFlags.ParFlags.gcThreads
+		      = strtol(rts_argv[arg]+2, (char **) NULL, 10);
+		    if (RtsFlags.ParFlags.nNodes <= 0) {
+		      errorBelch("bad value for -g");
+		      error = rtsTrue;
+		    }
 #if defined(PROFILING)
                     if (RtsFlags.ParFlags.nNodes > 1) {
                         errorBelch("bad option %s: only -N1 is supported with profiling", rts_argv[arg]);