Reland of "[heap] Divide available memory upon compaction tasks"

Reland of "[heap] Divide available memory upon compaction tasks"

This reverts commit cf71c28f13425d0e8c041391a2b37f0908b9e4b5.

Original message:

[heap] Divide available memory upon compaction tasks
- Fairly (round-robin) divide available memory upon compaction tasks.
- Ensure an upper limit (of memory) since dividing is O(n) for n free-space
  nodes.
- Refill from free lists managed by sweeper once a compaction space becomes
  empty.

Assumption for dividing memory: Memory in the free lists is sparse upon starting
compaction (which means that only few nodes are available), except for memory
reducer GCs, which happen in idle time though (so it's less of a problem).

BUG=chromium:524425
LOG=N

Committed: https://crrev.com/63f42ecb965d04877f45043c1416170b6f79b962
Cr-Commit-Position: refs/heads/master@{#31436}

[Michael Lippautz, 2015-10-20 13:02:01]

Description was changed from

==========
Reland of "[heap] Divide available memory upon compaction tasks"

This reverts commit cf71c28f13425d0e8c041391a2b37f0908b9e4b5.

BUG=
==========

to

==========
Reland of "[heap] Divide available memory upon compaction tasks"

This reverts commit cf71c28f13425d0e8c041391a2b37f0908b9e4b5.

Original message:

[heap] Divide available memory upon compaction tasks
- Fairly (round-robin) divide available memory upon compaction tasks.
- Ensure an upper limit (of memory) since dividing is O(n) for n free-space
  nodes.
- Refill from free lists managed by sweeper once a compaction space becomes
  empty.

Assumption for dividing memory: Memory in the free lists is sparse upon starting
compaction (which means that only few nodes are available), except for memory
reducer GCs, which happen in idle time though (so it's less of a problem).

BUG=chromium:524425
LOG=N
==========

[Michael Lippautz, 2015-10-20 13:46:52]

The CQ bit was checked by mlippautz@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2015-10-20 13:46:57]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1415733004/20001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1415733004/20001

[commit-bot: I haz the power, 2015-10-20 14:25:24]

The CQ bit was unchecked by commit-bot@chromium.org

[commit-bot: I haz the power, 2015-10-20 14:25:25]

Dry run: This issue passed the CQ dry run.

[Michael Lippautz, 2015-10-21 09:52:45]

mlippautz@chromium.org changed reviewers:
+ hpayer@chromium.org

[Michael Lippautz, 2015-10-21 09:52:45]

PTAL

[Hannes Payer (out of office), 2015-10-21 10:10:46]

LGTM, with one nit.

https://codereview.chromium.org/1415733004/diff/20001/src/heap/spaces.cc
File src/heap/spaces.cc (right):

https://codereview.chromium.org/1415733004/diff/20001/src/heap/spaces.cc#newc...
src/heap/spaces.cc:2492: intptr_t aligned_size = RoundUp(hint_size_in_bytes,
FreeSpace::kMinSize);
Let's round up to kSmallListMin, then we can drop the new constant kMinSize.

[Michael Lippautz, 2015-10-21 10:25:51]

https://codereview.chromium.org/1415733004/diff/20001/src/heap/spaces.cc
File src/heap/spaces.cc (right):

https://codereview.chromium.org/1415733004/diff/20001/src/heap/spaces.cc#newc...
src/heap/spaces.cc:2492: intptr_t aligned_size = RoundUp(hint_size_in_bytes,
FreeSpace::kMinSize);
On 2015/10/21 10:10:46, Hannes Payer wrote:
> Let's round up to kSmallListMin, then we can drop the new constant kMinSize.

Done.

[Michael Lippautz, 2015-10-21 10:27:04]

The CQ bit was checked by mlippautz@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2015-10-21 10:27:19]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1415733004/60001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1415733004/60001

[commit-bot: I haz the power, 2015-10-21 10:40:33]

The CQ bit was unchecked by commit-bot@chromium.org

[commit-bot: I haz the power, 2015-10-21 10:40:34]

Dry run: Try jobs failed on following builders:
  v8_mac_rel on tryserver.v8 (JOB_FAILED,
http://build.chromium.org/p/tryserver.v8/builders/v8_mac_rel/builds/10923)

[Michael Lippautz, 2015-10-21 10:59:46]

Patchset #5 (id:80001) has been deleted

[Michael Lippautz, 2015-10-21 11:00:09]

The CQ bit was checked by mlippautz@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2015-10-21 11:00:13]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1415733004/100001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1415733004/100001

[commit-bot: I haz the power, 2015-10-21 11:23:19]

The CQ bit was unchecked by commit-bot@chromium.org

[commit-bot: I haz the power, 2015-10-21 11:23:20]

Dry run: This issue passed the CQ dry run.

[Michael Lippautz, 2015-10-21 11:25:44]

Patchset #5 (id:100001) has been deleted

[Michael Lippautz, 2015-10-21 11:26:33]

Patchset #5 (id:120001) has been deleted

[Michael Lippautz, 2015-10-21 11:27:16]

The CQ bit was checked by mlippautz@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2015-10-21 11:27:26]

Dry run: CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1415733004/90008
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1415733004/90008

[commit-bot: I haz the power, 2015-10-21 11:58:53]

The CQ bit was unchecked by commit-bot@chromium.org

[commit-bot: I haz the power, 2015-10-21 11:58:54]

Dry run: This issue passed the CQ dry run.

[Michael Lippautz, 2015-10-21 12:03:07]

The CQ bit was checked by mlippautz@chromium.org

[Michael Lippautz, 2015-10-21 12:03:07]

The patchset sent to the CQ was uploaded after l-g-t-m from hpayer@chromium.org
Link to the patchset: https://codereview.chromium.org/1415733004/#ps90008
(title: "Fix size computation in TryRemoveMemory")

[commit-bot: I haz the power, 2015-10-21 12:03:16]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1415733004/90008
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1415733004/90008

[commit-bot: I haz the power, 2015-10-21 12:05:25]

Committed patchset #5 (id:90008)

[commit-bot: I haz the power, 2015-10-21 12:05:55]

Patchset 5 (id:??) landed as
https://crrev.com/63f42ecb965d04877f45043c1416170b6f79b962
Cr-Commit-Position: refs/heads/master@{#31436}

[Michael Lippautz, 2015-10-21 13:14:03]

A revert of this CL (patchset #5 id:90008) has been created in
https://codereview.chromium.org/1405273003/ by mlippautz@chromium.org.

The reason for reverting is: Failing again:
http://build.chromium.org/p/client.v8/builders/V8%20Linux64%20GC%20Stress%20-....