Emit final heap alloc events and rearrange code to calculate alloc totals

In stat_exit we want to emit a final EVENT_HEAP_ALLOCATED for each cap
so that we get the same total allocation count as reported via +RTS -s.
To do so we need to update the per-cap total_allocated counts.

Previously we had a single calcAllocated(rtsBool) function that counted
the large allocations and optionally the nurseries for all caps. The GC
would always call it with false, and the stat_exit always with true.
The reason for these two modes is that the GC counts the nurseries via
clearNurseries() (which also updates the per-cap total_allocated
counts), so it's only the stat_exit() path that needs to count them.

We now split the calcAllocated() function into two: countLargeAllocated
and updateNurseriesStats. As the name suggests, the latter now updates
the per-cap total_allocated counts, in additon to returning a total.

1 files changed, 6 insertions, 0 deletions

diff --git a/rts/Stats.c b/rts/Stats.c
index a7335531ce..29cae21bf3 100644
--- a/rts/Stats.c
+++ b/rts/Stats.c
@@ -588,6 +588,12 @@ stat_exit(int alloc)
 
 	GC_tot_alloc += alloc;
 
+        for (i = 0; i < n_capabilities; i++) {
+            traceEventHeapAllocated(&capabilities[i],
+                                    CAPSET_HEAP_DEFAULT,
+                                    capabilities[i].total_allocated * sizeof(W_));
+        }
+
 	/* Count total garbage collections */
 	for (g = 0; g < RtsFlags.GcFlags.generations; g++)
 	    total_collections += generations[g].collections;