runtime: scavenge on growth instead of inline with allocation

Inline scavenging causes significant performance regressions in tail
latency for k8s and has relatively little benefit for RSS footprint.

We disabled inline scavenging in Go 1.12.5 (CL 174102) as well, but
we thought other changes in Go 1.13 had mitigated the issues with
inline scavenging. Apparently we were wrong.

This CL switches back to only doing foreground scavenging on heap
growth, rather than doing it when allocation tries to allocate from
scavenged space.

Fixes #32828.

Change-Id: I1f5df44046091f0b4f89fec73c2cde98bf9448cb
Reviewed-on: https://go-review.googlesource.com/c/go/+/183857
Run-TryBot: Austin Clements <[email protected]>
TryBot-Result: Gobot Gobot <[email protected]>
Reviewed-by: Keith Randall <[email protected]>
Reviewed-by: Michael Knyszek <[email protected]>

Author: mknyszek

src/runtime/mheap.go

@@ -1226,16 +1226,6 @@ HaveSpan:
 		// heap_released since we already did so earlier.
 		sysUsed(unsafe.Pointer(s.base()), s.npages<<_PageShift)
 		s.scavenged = false
-
-		// Since we allocated out of a scavenged span, we just
-		// grew the RSS. Mitigate this by scavenging enough free
-		// space to make up for it but only if we need to.
-		//
-		// scavengeLocked may cause coalescing, so prevent
-		// coalescing with s by temporarily changing its state.
-		s.state = mSpanManual
-		h.scavengeIfNeededLocked(s.npages * pageSize)
-		s.state = mSpanFree
 	}
 
 	h.setSpans(s.base(), npage, s)
@@ -1311,6 +1301,10 @@ func (h *mheap) grow(npage uintptr) bool {
 //
 // h must be locked.
 func (h *mheap) growAddSpan(v unsafe.Pointer, size uintptr) {
+	// Scavenge some pages to make up for the virtual memory space
+	// we just allocated, but only if we need to.
+	h.scavengeIfNeededLocked(size)
+
 	s := (*mspan)(h.spanalloc.alloc())
 	s.init(uintptr(v), size/pageSize)
 	h.setSpans(s.base(), s.npages, s)