RFR: Use PLABs for old gen allocations, including promotions.

[earthling-amzn]

On Mon, 12 Apr 2021 19:50:45 GMT, Bernd Mathiske <bmathiske at openjdk.org> wrote:

> Introducing a 3rd kind of LAB for generational mode: "PLAB".
> 
> (This PR is in draft form as testing is still ongoing.
> Our smoke testing till flags a few unexpected crashes in generational mode.)
> 
> Shenandoah already has TLABs and GCLABs. The latter pertain firmly to young gen and allocations in old gen are so far always shared allocations, without LAB. With this PR, old gen allocations go through LABs as well and we separate those from the other two kinds. In other words, each generation has its separate GC-decicated LAB. 
> 
> When not in generational mode, GCLABs work as before and PLABs are never used.
> 
> The new diagnostic flag -XX:-ShenandoahUsePLAB can be used to turn off PLAB use, so that all old gen allocations are shared as before this PR. By default PLABs will be used.
> 
> Note that In source code, the type of both GCLABs and PLABs is "PLAB*", sonce GCLABs already had that type, but variable references and other value-level identifiers are consistently named "gclab" and "plab".
> 
> In ShenandoahFreeSet::allocate_single() there is a notable additional change that can easily be reverted if needed. Instead of fitting the intended allocation into any free or occupied region that can hold it, we now search for an occupied region in the same generation first, before considering free regions. The idea is to pack regions more densely as long as they have space left. This provides more opportunity for region borrowing between generations, should the need arise. For single-generational Shenandoah, it should not make a huge difference, right? Or is it crucial to find any free slot hit in that search loop ASAP?
> 
> Full collections need to set empty/trash regions that they compact into to non-FREE. For now, they will be made "YOUNG". (See the second commit.)

src/hotspot/share/gc/shenandoah/shenandoahFreeSet.cpp line 147:

> 145:             HeapWord *result = try_allocate_in(r, req, in_new_region);
> 146:             if (result != NULL) {
> 147:               if (r->is_old()) {

Sorry, it's not clear to me why we aren't concerned about pointers to young anymore?

src/hotspot/share/gc/shenandoah/shenandoahHeap.inline.hpp line 248:

> 246:         // We should revisit this.
> 247:         // Furthermore, the object start should be registered for remset scanning.
> 248:         MemRegion mr(cast_from_oop<HeapWord*>(result), result->size());

Don't we need this? The object going into the old region may have pointers to young that need to be scanned.

src/hotspot/share/gc/shenandoah/shenandoahHeapRegion.cpp line 102:

> 100:       do_commit();
> 101:     case _empty_committed:
> 102:       set_affiliation(YOUNG_GENERATION);

It's not clear to me why we would set the affiliation here. Do we know this region isn't going to be used for evacuations in old gen?

-------------

PR: https://git.openjdk.java.net/shenandoah/pull/30