+brettw, haraken: FYI.

This seems high-priority to address, to reduce paging thrash when systems are already under pressure - the issue isn't just that the GCing page may hang, but that the extra paging load caused by the GC can gunk up everything else.

wez@, this issue is about doing full GC vs incremental GC in rare corner case when context disposal rate is high.

It is not related to GC/paging trashing under pressure and it is not going to fix that. Do you want to file a new bug for that issue? 

The following revision refers to this bug:
  https://chromium.googlesource.com/v8/v8.git/+/52708b63412c96203cb0438e52dbe7e45c611383

commit 52708b63412c96203cb0438e52dbe7e45c611383
Author: Ulan Degenbaev <ulan@chromium.org>
Date: Fri Jun 30 09:43:27 2017

[heap] Avoid full GC for large heaps.

BUG= chromium:738031 

Change-Id: I98d1015caadd7214a7076f7b39a4514bfd908061
Reviewed-on: https://chromium-review.googlesource.com/555971
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46345}
[modify] https://crrev.com/52708b63412c96203cb0438e52dbe7e45c611383/src/heap/gc-idle-time-handler.cc
[modify] https://crrev.com/52708b63412c96203cb0438e52dbe7e45c611383/src/heap/gc-idle-time-handler.h
[modify] https://crrev.com/52708b63412c96203cb0438e52dbe7e45c611383/test/unittests/heap/gc-idle-time-handler-unittest.cc

wez@: Are you observing any specific issues about this? Or are you talking about the cases where the memory pressure had been forcing GCs after the OS has started a swap storm?