Avoid taking vm barrier in heap_prepare()

luke-gruber · luke-gruber · commit b3a2555e29b6 · 2025-09-16T15:37:42.000-04:00
We can avoid taking this barrier if we're not incremental marking or lazy sweeping. I found this was taking a significant amount of samples when profiling `Psych.load` in multiple ractors due to the vm barrier. With this change, we get significant improvements in ractor benchmarks that allocate lots of objects. -- Psych.load benchmark -- ``` Before: After: r: itr: time r: itr: time 0 #1: 960ms 0 #1: 943ms 0 #2: 979ms 0 #2: 939ms 0 #3: 968ms 0 #3: 948ms 0 #4: 963ms 0 #4: 946ms 0 #5: 964ms 0 #5: 944ms 1 #1: 947ms 1 #1: 940ms 1 #2: 950ms 1 #2: 947ms 1 #3: 962ms 1 #3: 950ms 1 #4: 947ms 1 #4: 945ms 1 #5: 947ms 1 #5: 943ms 2 #1: 1131ms 2 #1: 1005ms 2 #2: 1153ms 2 #2: 996ms 2 #3: 1155ms 2 #3: 1003ms 2 #4: 1205ms 2 #4: 1012ms 2 #5: 1179ms 2 #5: 1012ms 4 #1: 1555ms 4 #1: 1209ms 4 #2: 1509ms 4 #2: 1244ms 4 #3: 1529ms 4 #3: 1254ms 4 #4: 1512ms 4 #4: 1267ms 4 #5: 1513ms 4 #5: 1245ms 6 #1: 2122ms 6 #1: 1584ms 6 #2: 2080ms 6 #2: 1532ms 6 #3: 2079ms 6 #3: 1476ms 6 #4: 2021ms 6 #4: 1463ms 6 #5: 1999ms 6 #5: 1461ms 8 #1: 2741ms 8 #1: 1630ms 8 #2: 2711ms 8 #2: 1632ms 8 #3: 2688ms 8 #3: 1654ms 8 #4: 2641ms 8 #4: 1684ms 8 #5: 2656ms 8 #5: 1752ms ```
diff --git a/gc/default/default.c b/gc/default/default.c
@@ -982,6 +982,9 @@ total_final_slots_count(rb_objspace_t *objspace)
 #define GC_INCREMENTAL_SWEEP_SLOT_COUNT 2048
 #define GC_INCREMENTAL_SWEEP_POOL_SLOT_COUNT 1024
 #define is_lazy_sweeping(objspace)           (GC_ENABLE_LAZY_SWEEP && has_sweeping_pages(objspace))
+/* In lazy sweeping or the previous incremental marking finished and did not yield a free page. */
+#define needs_continue_sweeping(objspace, heap) \
+    ((heap)->free_pages == NULL && is_lazy_sweeping(objspace))
 
 #if SIZEOF_LONG == SIZEOF_VOIDP
 # define obj_id_to_ref(objid) ((objid) ^ FIXNUM_FLAG) /* unset FIXNUM_FLAG */
@@ -2012,7 +2015,10 @@ static void
 gc_continue(rb_objspace_t *objspace, rb_heap_t *heap)
 {
     unsigned int lock_lev;
-    gc_enter(objspace, gc_enter_event_continue, &lock_lev);
+    bool needs_gc = is_incremental_marking(objspace) || needs_continue_sweeping(objspace, heap);
+    if (!needs_gc) return;
+
+    gc_enter(objspace, gc_enter_event_continue, &lock_lev); // takes vm barrier, try to avoid
 
     /* Continue marking if in incremental marking. */
     if (is_incremental_marking(objspace)) {
@@ -2021,9 +2027,7 @@ gc_continue(rb_objspace_t *objspace, rb_heap_t *heap)
         }
     }
 
-    /* Continue sweeping if in lazy sweeping or the previous incremental
-     * marking finished and did not yield a free page. */
-    if (heap->free_pages == NULL && is_lazy_sweeping(objspace)) {
+    if (needs_continue_sweeping(objspace, heap)) {
         gc_sweep_continue(objspace, heap);
     }
 
