Commit Graph

221 Commits

Author SHA1 Message Date
Michael Lippautz
fe76251df3 [heap] Add GC sum counters
Adds reporting for
- V8.GCMarkCompactor as sum of V8 mark-compact events

Bug: chromium:843903
Change-Id: I5e8a80c8d1a9c5bf696635b54659ac56403f52d5
Reviewed-on: https://chromium-review.googlesource.com/c/1256764
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56750}
2018-10-17 19:42:30 +00:00
Clemens Hammacher
75b5666175 [base] Introduce MutexGuard as typedef for LockGuard<Mutex>
LockGuard is mostly used with Mutex. Since both are defined outside the
internal namespace, we often have to write
{base::LockGuard<base::Mutex>}. This CL shortens this to
{base::MutexGuard} across the code base

R=mlippautz@chromium.org

Bug: v8:8238
Cq-Include-Trybots: luci.chromium.try:linux_chromium_headless_rel;master.tryserver.blink:linux_trusty_blink_rel
Change-Id: I020d5933b73aafb98c4b72e3bb2dfd07c979ba73
Reviewed-on: https://chromium-review.googlesource.com/c/1278796
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Commit-Queue: Clemens Hammacher <clemensh@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56612}
2018-10-12 15:44:51 +00:00
Michael Lippautz
dfa56840fe [heap] Use non-nestable tasks for finalizing garbage collection
Pass on information about the embedder state using the fact that tasks
are run from top level

Bug: chromium:893944
Change-Id: I01441778770c5acc784540e496eec5c3fdb87796
Reviewed-on: https://chromium-review.googlesource.com/c/1273048
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56540}
2018-10-10 18:38:14 +00:00
Igor Sheludko
8034b9a539 [heap] Add missing notification about freed code range
It was accidentally removed in CL that introduced BoundedPageAllocator.

This CL also cleans up the CodeRangeAddressHint a bit.

Bug: v8:8096, chromium:887252
Change-Id: Idc84796dd1ff1b440cbe3515732984264defcf2d
Reviewed-on: https://chromium-review.googlesource.com/1249125
Commit-Queue: Igor Sheludko <ishell@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56287}
2018-09-28 11:01:50 +00:00
Michael Lippautz
1f3802a1e7 [heap] Remove obsolete AbortTracing calls and deprecate interface
V8 does not abort incremental marking anymore.

Bug: chromium:843903
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: Id39e9cf8ef2afc388bab2bbad1d458ee2649f8e8
Reviewed-on: https://chromium-review.googlesource.com/1226889
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Adam Klein <adamk@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56009}
2018-09-19 05:17:21 +00:00
Florian Sattler
6df4c37779 [cleanup] Mark heap/ methods in subclasses with override.
Fixing clang-tidy warning.

Bug: v8:8015
Change-Id: Ibdb4b81e1ba764d73bac6592eeef5783097076fc
Reviewed-on: https://chromium-review.googlesource.com/1225896
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Commit-Queue: Florian Sattler <sattlerf@google.com>
Cr-Commit-Position: refs/heads/master@{#55965}
2018-09-17 15:32:31 +00:00
Florian Sattler
b2dac95379 [cleanup] Replace 0 and NULL with nullptr for test files.
Fixing clang-tidy warning.

Bug: v8:8015
Change-Id: I2a7a8c8447d2835205f7a506f04efe4d1801b934
Reviewed-on: https://chromium-review.googlesource.com/1224316
Reviewed-by: Andreas Haas <ahaas@chromium.org>
Commit-Queue: Florian Sattler <sattlerf@google.com>
Cr-Commit-Position: refs/heads/master@{#55903}
2018-09-14 12:56:00 +00:00
Florian Sattler
49d1c8663e [cleanup] Refactor heap classes to use default members.
Fixing clang-tidy warning.

Bug: v8:8015
Change-Id: Ibe5906fa96f2d7327bce1eff70637a2d00f99668
Reviewed-on: https://chromium-review.googlesource.com/1224030
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Commit-Queue: Florian Sattler <sattlerf@google.com>
Cr-Commit-Position: refs/heads/master@{#55865}
2018-09-13 13:35:56 +00:00
Michael Lippautz
22b2b34c26 [heap] Refactor HeapController
Split off from
  https://chromium-review.googlesource.com/c/v8/v8/+/1196484

Bug: chromium:879045
Change-Id: I58b1a2ad10729f54c9a452dcfecd7511660460f6
Reviewed-on: https://chromium-review.googlesource.com/1216285
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55764}
2018-09-10 19:47:15 +00:00
Michael Lippautz
ad832c4145 [heap, api] Keep lower limit when adjusting external memory
Previously explicit calls to external memory adjustment could yield in lowering
the limit below the initial default limit. The consequence is repeated useless
garbage collections when e.g. passing around ArrayBuffers.

Bug: chromium:880036
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: I429f5adcd9ae523e5ac7621cf7976686b0dec71b
Reviewed-on: https://chromium-review.googlesource.com/1209784
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55694}
2018-09-06 15:44:37 +00:00
Michael Lippautz
1d1d4d21e0 [heap] Record UMA for Scavenger sub phases
Reocord UMA counters for the following phases:
- Scavenging roots
- Scavenging object graph in parallel

Bug: chromium:850508
Change-Id: I07210271179ce6801ea6daf3b486b4ce237a3261
Reviewed-on: https://chromium-review.googlesource.com/1199302
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55619}
2018-09-04 18:57:11 +00:00
Michael Lippautz
8206187381 Revert GC scheduling for external backing stores
Revert "Reland "[heap] Attempt to incorporate backing store counters into heap sizing and GC trigger stragery.""

This reverts commit eb164dbd00.

Revert "[d8] Fixed external gc test (limit multiplied by number of isolates)."

This reverts commit 38cbc26a75.

Revert "[heap] Fixed typo in method name."

This reverts commit 263174af75.

Bug: chromium:845409, chromium:879045
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: I555bcff2ad04ae23368c7b3999a237083010f9c6
Reviewed-on: https://chromium-review.googlesource.com/1196550
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55529}
2018-08-30 14:24:38 +00:00
Rodrigo Bruno
eb164dbd00 Reland "[heap] Attempt to incorporate backing store counters into heap sizing and GC trigger stragery."
This is a reland of ba735dde20

Original change's description:
> [heap] Attempt to incorporate backing store counters into heap sizing and GC trigger stragery.
> 
> Bug: chromium:845409
> Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
> Change-Id: Ic62a4339110e3dd2a6b1961a246e2bee0c07c03b
> Reviewed-on: https://chromium-review.googlesource.com/1160162
> Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#55128}

Bug: chromium:845409
Change-Id: Iaff177f7bebbc073460fab0ae4e5cd9e632e1921
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Reviewed-on: https://chromium-review.googlesource.com/1177301
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Cr-Commit-Position: refs/heads/master@{#55454}
2018-08-28 12:41:53 +00:00
Michael Lippautz
a6938128f4 [embedder-tracing] Add GarbageCollectionForTesting call
This call can be used by embedder to request a GC for testing reasons.
The GC also takes the current embedder stack state as an argument that
is forwarded to the embedder when entering the atomic pause.

This way embedders can request garbage collections for testing and set
how the embedder should treat the stack.

Bug: chromium:843903
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: Id10604565b4457dd0fca402afeb5f8e592fa0bae
Reviewed-on: https://chromium-review.googlesource.com/1183431
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55285}
2018-08-21 18:42:05 +00:00
Ulan Degenbaev
4d474c51d8 [heap] Reuse freed CodeRange addresses.
This patch adds a singleton that tracks recently freed code range
regions and provides hints for newly created code ranges such that
the freed addresses are reused.

This is a workaround for the CFG leak described in the linked bug.

Bug: chromium:870054

Change-Id: Ice237a056268379f0fef40abdb1accad125a56b3
Reviewed-on: https://chromium-review.googlesource.com/1174837
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55139}
2018-08-15 18:53:11 +00:00
Sathya Gunasekaran
7eded3003a Revert "[heap] Attempt to incorporate backing store counters into heap sizing and GC trigger stragery."
This reverts commit ba735dde20.

Reason for revert: https://ci.chromium.org/p/v8/builders/luci.v8.ci/V8%20Linux64%20TSAN/21991

Original change's description:
> [heap] Attempt to incorporate backing store counters into heap sizing and GC trigger stragery.
> 
> Bug: chromium:845409
> Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
> Change-Id: Ic62a4339110e3dd2a6b1961a246e2bee0c07c03b
> Reviewed-on: https://chromium-review.googlesource.com/1160162
> Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#55128}

TBR=ulan@chromium.org,mlippautz@chromium.org,rfbpb@google.com

Change-Id: Iaf65227c65c11effa11662ac7d7bd7736f4d7846
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: chromium:845409
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Reviewed-on: https://chromium-review.googlesource.com/1174858
Reviewed-by: Sathya Gunasekaran <gsathya@chromium.org>
Commit-Queue: Sathya Gunasekaran <gsathya@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55129}
2018-08-14 17:17:17 +00:00
Rodrigo Bruno
ba735dde20 [heap] Attempt to incorporate backing store counters into heap sizing and GC trigger stragery.
Bug: chromium:845409
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: Ic62a4339110e3dd2a6b1961a246e2bee0c07c03b
Reviewed-on: https://chromium-review.googlesource.com/1160162
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55128}
2018-08-14 16:31:32 +00:00
Rodrigo Bruno
ecf51e3477 [heap] refactoring HeapController.
The HeapController is now refactored in a way that new controllers only
need to specify the constants that define how a space grows and shrinks.

Bug: chromium:845409
Change-Id: I804eed440a791d6fbd232b7540a1cbe66b16a5f1
Reviewed-on: https://chromium-review.googlesource.com/1165347
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#55006}
2018-08-09 09:04:26 +00:00
Rodrigo Bruno
d623c25a84 [heap] Refactoring HeapController. Created new ExternalMemoryController.
This CL introduces a new MemoryController that will be used to control
the size of external memory (array buffers and external string for now).

Bug: chromium:845409
Change-Id: I119506ce0243ac33cec2b783b888b53ee11225a9
Reviewed-on: https://chromium-review.googlesource.com/1156393
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54854}
2018-08-02 06:52:26 +00:00
Michael Lippautz
db02a0eb18 [heap] Fix SpacesTest.WriteBarrierFromHeapObject
Instead of actually allocating an objects just test the corner cases
around the page boundary by casting addresses.

Bug: v8:7984
Change-Id: I27615cc193d6f85abc91cfe898719a4a9b761f23
Reviewed-on: https://chromium-review.googlesource.com/1151114
Reviewed-by: Leszek Swirski <leszeks@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54717}
2018-07-26 11:17:14 +00:00
Michael Lippautz
9e3d6cbec5 [heap,iwyu] Provide slim write barrier header
Move write barrier essentials into heap/heap-write-barrier-inl.h. Avoid
including further heap inline headers by relying on constant to load
flags from.

Bug: v8:7490
Change-Id: I2891299f1b1ca2c3e2031cb9c63b583b1665e3f9
Reviewed-on: https://chromium-review.googlesource.com/1148448
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Michael Starzinger <mstarzinger@chromium.org>
Reviewed-by: Clemens Hammacher <clemensh@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54710}
2018-07-26 09:04:48 +00:00
Michael Lippautz
8de19ddbcf [unified-heap] Add finalization trigger
Allows embedders using the EmbedderHeapTracer to synchronously finalize
an already running garbage collection

Bug: chromium:843903
Tbr: ulan@chromium.org
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: Iea01451ea2c1204c34dc7904732abae6b63e1704
Reviewed-on: https://chromium-review.googlesource.com/1128971
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54378}
2018-07-11 12:25:40 +00:00
Michael Lippautz
848f989e3d [embedder-tracing] Deprecate NumberOfWrappersToTrace
Deprecates EmbedderHeapTracer::NumberOfWrappersToTrace and replaces it
with EmbedderHeapTracer::IsTracingDone.

V8 only really cares about the final state (emptiness) here and
embedders may choose implementations that have a hard time determinining
exact size for their work queues.

Bug: chromium:843903
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: I1e141c47771ef08aab7dbe204e8175cfee99cf92
Reviewed-on: https://chromium-review.googlesource.com/1127599
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54311}
2018-07-09 08:06:49 +00:00
Dominik Inführ
f176e1aa3f [heap] Rename IsGlobalEmpty to IsEmpty
Rename method to IsEmpty for Worklist. IsGlobalEmpty is easy to
confuse with IsGlobalPoolEmpty.

Change-Id: Id9744cef2630f7c0642ec37ef9a18296acee87e3
Reviewed-on: https://chromium-review.googlesource.com/1115222
Commit-Queue: Dominik Inführ <dinfuehr@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54153}
2018-07-03 07:15:34 +00:00
Rodrigo Bruno
c6d9a82093 [heap] Simplifying growing strategy.
Bug: chromium:852748
Change-Id: Iac1c52d45e84af190415aeae5df167ab501b4bc4
Reviewed-on: https://chromium-review.googlesource.com/1109821
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Cr-Commit-Position: refs/heads/master@{#53918}
2018-06-21 11:39:09 +00:00
Rodrigo Bruno
4735bc7e6b [heap] Fixing the performance issue of the new heap growing strategy.
Bug: chromium:852748
Change-Id: Ifdadf3188815fe38741e6f0e817070972e7f445b
Reviewed-on: https://chromium-review.googlesource.com/1108205
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53904}
2018-06-21 08:16:28 +00:00
Rodrigo Bruno
748e33944d [heap ]Added test to verify the output of CalculateOldGenerationAllocationLimit.
Bug: chromium:845409
Change-Id: Id8b89e6dac48bba9065ac9f04ce48f951aa2186b
Reviewed-on: https://chromium-review.googlesource.com/1092860
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53617}
2018-06-08 16:45:41 +00:00
Ulan Degenbaev
7f442da6d8 Fix Linux64_TSAN-concurrent_marking bot after 7a9e3ec
The mock histogram functions cannot be cleared and can be called on
isolate tear down if incremental marking is in progress.

Bug: chromium:850508
Tbr: mlippautz@chromium.org
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Change-Id: I99e52aaa81c863f71e195aeed691b37da9e71da6
Reviewed-on: https://chromium-review.googlesource.com/1093073
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53616}
2018-06-08 15:46:44 +00:00
Ulan Degenbaev
65ba1cb618 Fix jumbo build after 7a9e3ec
Bug: chromium:850508

Tbr: mlippautz@chromium.org
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Change-Id: I99adf68c4b3e26decf3b68c8062ce74cbf27874d
Reviewed-on: https://chromium-review.googlesource.com/1093071
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53615}
2018-06-08 15:31:45 +00:00
Ulan Degenbaev
7a9e3ec98d [heap] Record histograms for Mark-Compact phases.
This adds the following histograms recorded corresponding to
V8.GCFinalizeMC phases:
- V8.GCFinalizeMC.Clear
- V8.GCFinalizeMC.Epilogue
- V8.GCFinalizeMC.Evacuate
- V8.GCFinalizeMC.Finish
- V8.GCFinalizeMC.Mark
- V8.GCFinalizeMC.Prologue
- V8.GCFinalizeMC.Sweep

Bug: chromium:850508
Change-Id: I47adc125a9a28436d09e35db68a8e8198cbee2dd
Reviewed-on: https://chromium-review.googlesource.com/1091311
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53614}
2018-06-08 14:23:09 +00:00
Rodrigo Bruno
db4b7e7598 [heap] Refactoring heap growing strategy from Heap to HeapController class.
Bug: chromium:845409
Change-Id: I377d6f9d26a193f7fd829f7b74f9fdabc1337dc0
Reviewed-on: https://chromium-review.googlesource.com/1089053
Commit-Queue: Rodrigo Bruno <rfbpb@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53580}
2018-06-07 12:38:34 +00:00
Hannes Payer
5e31f9ffdf [heap] Cleanup Heap SetUp/TearDown a bit.
Change-Id: Ieec4dccdf8a5241f439bde9fffc75f4f300930e1
Reviewed-on: https://chromium-review.googlesource.com/1089333
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Hannes Payer <hpayer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53567}
2018-06-07 06:37:54 +00:00
Jakob Kummerow
2459046c1d [ubsan] Change Address typedef to uintptr_t
The "Address" type is V8's general-purpose type for manipulating memory
addresses. Per the C++ spec, pointer arithmetic and pointer comparisons
are undefined behavior except within the same array; since we generally
don't operate within a C++ array, our general-purpose type shouldn't be
a pointer type.

Bug: v8:3770
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng;master.tryserver.blink:linux_trusty_blink_rel
Change-Id: Ib96016c24a0f18bcdba916dabd83e3f24a1b5779
Reviewed-on: https://chromium-review.googlesource.com/988657
Commit-Queue: Jakob Kummerow <jkummerow@chromium.org>
Reviewed-by: Leszek Swirski <leszeks@chromium.org>
Cr-Commit-Position: refs/heads/master@{#52601}
2018-04-14 01:25:28 +00:00
Ulan Degenbaev
d65d57a7fa [heap] Track average mutator utilization in GC tracer.
The mutator utilizaton is computed for each mark-compact GC cycle as
mutator_time / total_time, where
- total_time is the time from the end of the previous GC to the end of
  the current GC
- mutator_time = total_time - incremental_steps_duration - gc_time.

Bug: chromium:824214
Change-Id: Ie1814f22f0816a3c9c579107f4950f6fc8c8a72d
Reviewed-on: https://chromium-review.googlesource.com/978215
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#52221}
2018-03-26 13:36:00 +00:00
Gabriel Charette
85b8daed63 Add V8.GC.ParallelTaskLatencyMicroSeconds metric.
It will record the time-to-schedule-after-job-start for different
task types to try to highlight use cases where contention might
be a problem (and show improvements to it later).

Also introducing AsyncTimedHistogram to support this use case whose
reported timings go beyond a single scope (i.e. the async version of
ScopedTimedHistogram).

Bug: chromium:807606
Change-Id: Ib4d581fa8b001723dfe8c91102280e9608b4fabb
Reviewed-on: https://chromium-review.googlesource.com/899365
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Gabriel Charette <gab@chromium.org>
Cr-Commit-Position: refs/heads/master@{#51131}
2018-02-06 21:53:49 +00:00
Gabriel Charette
18c1942371 Do not block in non-main thread tasks in ItemParallelJobTests.
Otherwise bots with a low number of cores will hang trying to schedule
a mere 4 tasks.
This change allowing scheduling of an arbitrary number of test tasks,
the count was also augmented to better stress test the system.

Bug: chromium:805932
Change-Id: Ia10cd583c0675c256b4fd5d2765b50855d77a7f9
Reviewed-on: https://chromium-review.googlesource.com/895584
Commit-Queue: Gabriel Charette <gab@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#51019}
2018-02-01 09:09:29 +00:00
Gabriel Charette
de49b57404 Reland "Smoother distribution of worker assignment in parallel task array."
This is a reland of 76195d9e08.

It was reverted because the new parallel tasks (with higher number
of workers) hang on client.v8.ports bots. Since each test task steals
the worker thread it's assigned but only processes one item before
waiting for completion by others: I think the problem is that there
aren't enough workers in client.v8.ports' config. There aren't any
try bots for this config... reduce the tests to use 4 tasks and
hope for the best (i.e. a 4 core machine that uses "num cores")...

Original change's description:
> Smoother distribution of worker assignment in parallel task array.
>
> This is a merge of https://chromium-review.googlesource.com/c/v8/v8/+/888704
> and https://chromium-review.googlesource.com/c/v8/v8/+/887084
>
> Which implements the fix in CL 887084 correctly in a world where
> there can be more tasks_ than items_ (crbug.com/806237).
>
> Bug: chromium:805932
> Change-Id: I05401be4fdce442644a8973281a9d88bd959b271
> Reviewed-on: https://chromium-review.googlesource.com/892883
> Commit-Queue: Gabriel Charette <gab@chromium.org>
> Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#50956}

Reverted-on: https://chromium-review.googlesource.com/893462

Bug: chromium:805932
Change-Id: I4d0bda3b9f52e9160e613a8f34a95e48b814bb9e
Reviewed-on: https://chromium-review.googlesource.com/893362
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Commit-Queue: Gabriel Charette <gab@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50967}
2018-01-30 20:03:53 +00:00
Gabriel Charette
396e7bc801 Revert "Smoother distribution of worker assignment in parallel task array."
This reverts commit 76195d9e08.

Reason for revert: New parallel tests timeout on the waterfall (I think because it's configured to use less worker threads and TaskProcessingOneItem is currently designed to steal a worker but only process one item...).

Original change's description:
> Smoother distribution of worker assignment in parallel task array.
> 
> This is a merge of https://chromium-review.googlesource.com/c/v8/v8/+/888704
> and https://chromium-review.googlesource.com/c/v8/v8/+/887084
> 
> Which implements the fix in CL 887084 correctly in a world where
> there can be more tasks_ than items_ (crbug.com/806237).
> 
> Bug: chromium:805932
> Change-Id: I05401be4fdce442644a8973281a9d88bd959b271
> Reviewed-on: https://chromium-review.googlesource.com/892883
> Commit-Queue: Gabriel Charette <gab@chromium.org>
> Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#50956}

TBR=gab@chromium.org,hpayer@chromium.org,mlippautz@chromium.org

Change-Id: Icf52eb3afeb9467557c1e0db6922d590466943f0
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: chromium:805932
Reviewed-on: https://chromium-review.googlesource.com/893462
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Commit-Queue: Gabriel Charette <gab@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50965}
2018-01-30 16:33:36 +00:00
Gabriel Charette
76195d9e08 Smoother distribution of worker assignment in parallel task array.
This is a merge of https://chromium-review.googlesource.com/c/v8/v8/+/888704
and https://chromium-review.googlesource.com/c/v8/v8/+/887084

Which implements the fix in CL 887084 correctly in a world where
there can be more tasks_ than items_ (crbug.com/806237).

Bug: chromium:805932
Change-Id: I05401be4fdce442644a8973281a9d88bd959b271
Reviewed-on: https://chromium-review.googlesource.com/892883
Commit-Queue: Gabriel Charette <gab@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50956}
2018-01-30 11:58:24 +00:00
Gabriel Charette
2407b2bd1b Revert "v8::ItemParallelJob : Do not launch more Tasks than there are Items to process."
This reverts commit 8a27c7d396.

Reason for revert: 

Having more tasks then work items is intentional in some use cases, i.e. Scavenging where RunInParallel() does parallel processing on a dynamic workload *after* the initial set of work items:

    {
      barrier_->Start();
      TimedScope scope(&scavenging_time);
      PageScavengingItem* item = nullptr;
      while ((item = GetItem<PageScavengingItem>()) != nullptr) {
        item->Process(scavenger_);
        item->MarkFinished();
      }
      do {
        scavenger_->Process(barrier_);
      } while (!barrier_->Wait());
      scavenger_->Process();
    }

Original change's description:
> v8::ItemParallelJob : Do not launch more Tasks than there are Items to process.
> 
> Except when there are 0 items. For some reason I don't quite understand yet, not
> calling Run() on tasks_[0] when there are 0 items results in DCHECKs...
> 
> Bug: chromium:806237
> Change-Id: I38c8fffde64a42f93f4efda492832651137eebd7
> Reviewed-on: https://chromium-review.googlesource.com/888704
> Commit-Queue: Gabriel Charette <gab@chromium.org>
> Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#50924}

TBR=gab@chromium.org,mlippautz@chromium.org

Change-Id: Iad2ab16bb41f339de8e3fbca1c08c5d26b8a0111
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: chromium:806237
Reviewed-on: https://chromium-review.googlesource.com/891186
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Gabriel Charette <gab@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50928}
2018-01-29 16:03:46 +00:00
Gabriel Charette
8a27c7d396 v8::ItemParallelJob : Do not launch more Tasks than there are Items to process.
Except when there are 0 items. For some reason I don't quite understand yet, not
calling Run() on tasks_[0] when there are 0 items results in DCHECKs...

Bug: chromium:806237
Change-Id: I38c8fffde64a42f93f4efda492832651137eebd7
Reviewed-on: https://chromium-review.googlesource.com/888704
Commit-Queue: Gabriel Charette <gab@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50924}
2018-01-29 12:53:53 +00:00
Ali Ijaz Sheikh
95249bca1f [heap] allocation step should before limit update
Do a step before selecting the limit for the next step. However, as seen
on crbug.com/795323, while this fix makes us more precise in our
accounting, we do ending up seeing steps more frequently. This ends up
invoking the idle scavenger more frequently. To compensate, we adjust
the idle scavenger step size.

Bug: 
Change-Id: I7bc2b1785a564dee27aa3ce6a5a196efe9eb6283
Reviewed-on: https://chromium-review.googlesource.com/838440
Commit-Queue: Ali Ijaz Sheikh <ofrobots@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50816}
2018-01-23 19:32:05 +00:00
Michael Lippautz
dfa36e9fab [object-stats] Add unittest for clashing instance types
Bug: v8:7266
Change-Id: I1436d39281caa9daf33289840d19a4a5e1ba476d
Reviewed-on: https://chromium-review.googlesource.com/880843
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50795}
2018-01-23 11:38:15 +00:00
Bill Budge
a449f09fad [Memory] Create memory management API in v8::internal.
- Creates a memory management API in v8::internal, which corresponds
  to the existing one in base::OS.
- Implements the new API in terms of the old one.
- Changes all usage of the base::OS API to the one in v8::internal. This
  includes all tests, except platform and OS tests.
- Makes OS:: methods private.
- Moves all LSAN calls into the v8::internal functions.

Bug: chromium:756050
Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
Change-Id: Iaa3f022e3e12fdebf937f3c76b6c6455014beb8a
Reviewed-on: https://chromium-review.googlesource.com/794856
Commit-Queue: Bill Budge <bbudge@chromium.org>
Reviewed-by: Eric Holk <eholk@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#50139}
2017-12-15 18:49:47 +00:00
Ulan Degenbaev
fd554885a8 [heap] Add background GC tracing infrastructure.
A background task can now use GCTracer::BackgroundScope to
trace the time spent in the task. The time shows up in
--trace-gc-nvp output and in the runtime call stats for GC.

The destructor of GCTracer::BackgroundScope increments the
corresponding counter in heap()->tracer()->background_counter_,
which is protected by a mutex.

The GCTracer::Stop function fetches background_counter_ items
into the global scope and into the runtime call stats.

Bug: chromium:758183
Change-Id: Id7bcd5089ba6c027fe9a57eb3f7db1cb5092aec5
Reviewed-on: https://chromium-review.googlesource.com/801694
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Camillo Bruni <cbruni@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#49841}
2017-12-04 17:28:41 +00:00
Mathias Bynens
822be9b238 Normalize casing of hexadecimal digits
This patch normalizes the casing of hexadecimal digits in escape
sequences of the form `\xNN` and integer literals of the form
`0xNNNN`.

Previously, the V8 code base used an inconsistent mixture of uppercase
and lowercase.

Google’s C++ style guide uses uppercase in its examples:
https://google.github.io/styleguide/cppguide.html#Non-ASCII_Characters

Moreover, uppercase letters more clearly stand out from the lowercase
`x` (or `u`) characters at the start, as well as lowercase letters
elsewhere in strings.

BUG=v8:7109
TBR=marja@chromium.org,titzer@chromium.org,mtrofin@chromium.org,mstarzinger@chromium.org,rossberg@chromium.org,yangguo@chromium.org,mlippautz@chromium.org
NOPRESUBMIT=true

Cq-Include-Trybots: master.tryserver.blink:linux_trusty_blink_rel;master.tryserver.chromium.linux:linux_chromium_rel_ng
Change-Id: I790e21c25d96ad5d95c8229724eb45d2aa9e22d6
Reviewed-on: https://chromium-review.googlesource.com/804294
Commit-Queue: Mathias Bynens <mathias@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Cr-Commit-Position: refs/heads/master@{#49810}
2017-12-02 01:24:40 +00:00
Bill Budge
5c461ae868 Revert "[Memory] Move GetRandomMmapAddr from base::OS platform to v8::internal."
This reverts commit d607f1e72d.

Reason for revert: Suspected cause of hanging tests:

https://bugs.chromium.org/p/v8/issues/detail?id=6927#c13

Original change's description:
> [Memory] Move GetRandomMmapAddr from base::OS platform to v8::internal.
> 
> - Moves GetRandomMmapAddr from platform to v8::internal allocation
>   primitives, in preparation for delegating this to the embedder.
> - Adds hint parameters to OS functions that used to use this function.
> 
> Bug: chromium:756050
> Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
> Change-Id: Iad72e6eac9c08a3e22c2cd2b2905623b8e514ae0
> Reviewed-on: https://chromium-review.googlesource.com/677777
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Commit-Queue: Bill Budge <bbudge@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#48124}

TBR=bbudge@chromium.org,ulan@chromium.org

# Not skipping CQ checks because original CL landed > 1 day ago.

Bug: chromium:756050
Change-Id: I2c515934906e67b47ceea2863bc2992ac1d23ab3
Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
Reviewed-on: https://chromium-review.googlesource.com/726319
Commit-Queue: Bill Budge <bbudge@chromium.org>
Reviewed-by: Bill Budge <bbudge@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#48701}
2017-10-18 18:48:27 +00:00
Michael Lippautz
b7e6eb9208 [heap] Introduce on-hold concurrent marking work list
When hitting objects that are allocated in the most recent lienar
allocation area, the concurrent marker currently has to bail out to the
main thread.

However, we only have to delay processing those objects until we are at
a safepoint, e.g. IM::Step(). With this change we flush those
on-hold-objects back to the shared queue upon performing an incremental
marking step.

Bug: chromium:694255
Change-Id: I25647d0fc581a5c4de0346bc394dc51062f65f70
Reviewed-on: https://chromium-review.googlesource.com/707315
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#48424}
2017-10-10 11:33:39 +00:00
Bill Budge
d607f1e72d [Memory] Move GetRandomMmapAddr from base::OS platform to v8::internal.
- Moves GetRandomMmapAddr from platform to v8::internal allocation
  primitives, in preparation for delegating this to the embedder.
- Adds hint parameters to OS functions that used to use this function.

Bug: chromium:756050
Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
Change-Id: Iad72e6eac9c08a3e22c2cd2b2905623b8e514ae0
Reviewed-on: https://chromium-review.googlesource.com/677777
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Bill Budge <bbudge@chromium.org>
Cr-Commit-Position: refs/heads/master@{#48124}
2017-09-22 15:26:18 +00:00
Michael Lippautz
4e5db9a6c8 [heap] Remove marking deque overflow handling
Removes
- SequentialMarkingDeque
- The ability to handle marking deque overflow
- BlackToGrey transitions

We switched to a different marking work list on M61 that fails
in OOM upon failing to allocate Segments used in the work list.

Bug: chromium:758570
Change-Id: I66e2ab912271bf84b085dccc9b4bdd96076b64fb
Reviewed-on: https://chromium-review.googlesource.com/632676
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#48078}
2017-09-19 05:20:20 +00:00
Michael Lippautz
9619b7f23c [heap] Factor out the barrier from Scavenger and add tests
Bug: chromium:738865, chromium:750084
Change-Id: Ife30da4be118cd6f3212e84752978ebb39500f15
Reviewed-on: https://chromium-review.googlesource.com/641414
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#47710}
2017-08-30 12:05:56 +00:00
Ulan Degenbaev
1518b1e349 [heap] Refactor page initialization.
This fixes layering between page and its owner, so that the page does
not update the owner state.

Bug: chromium:694255
Change-Id: Ic4f594340bed42d4f2c13d0a30f451317cbc9f50
Reviewed-on: https://chromium-review.googlesource.com/620732
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#47437}
2017-08-18 16:28:34 +00:00
Ulan Degenbaev
dfc6b4ddaa [heap] New live byte tracking.
This patch changes how space size and capacity are updated in GC:
- space capacity changes only when a page added/removed from the space.
- space size is reset to zero before sweeping and incremented by
  page->live_bytes_count_ for each to-be-swept page.
- space size is refined after sweeping using the accurate
  page->allocated_bytes counter produces by the sweeper.

Invariants:
1. space.capacity = sum [page.size | for page in space].
2. After marking, before sweeping:
   a) space.size = sum [page.live_bytes_count | for page in space].
3. After sweeping, before marking ends:
   a) space.size = sum [page.allocated_bytes | for page in space].
   b) page.allocated_bytes >= (sum [object.size | for object in page] +
         page.linear_allocation_area).
   c) page.area_size = (page.allocated_bytes + page.wasted_memory +
         sum [free_list_entry.size | for free_list_entry in page].

3.b becomes equality if the mutator is not doing array trimming,
object slack tracking during sweeping.

Bug: chromium:694255
Change-Id: Ic8d16a8171187a113fee2df8bf3c2a4c5e77bc08
Reviewed-on: https://chromium-review.googlesource.com/618889
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#47409}
2017-08-17 18:16:33 +00:00
Ulan Degenbaev
2178bbaf3f [heap] Adjust upper limit in ComputeMaxSemiSpaceSize.
This ensures that 2GB devices get 512K initial semi-space.

Bug: chromium:735649
TBR: mlippautz@chromium.org
Change-Id: I864c9dfa7cd3ea9040fa56d81d6bf1187c1cf776
Reviewed-on: https://chromium-review.googlesource.com/608129
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#47246}
2017-08-09 13:06:41 +00:00
Ulan Degenbaev
7486dc3331 [heap] Partially reland "Allow a minimum semi-space size of 512K."
This sets the minimum semi-space size to 512K, but does not
change the initial semi-space size.

This reverts commit 774a4c5e24.

Original commit message:
> [heap] Allow a minimum semi-space size of 512K.
> This CL also reduces the minimum semi-space size to 512K.
> BUG=chromium:716032
BUG=chromium:735649
TBR=mlippautz@chromium.org

Change-Id: I1f5dd05b0851ba2b438bedcc023a5cf5f9242a81
Reviewed-on: https://chromium-review.googlesource.com/594107
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#47016}
2017-07-31 15:45:06 +00:00
Ulan Degenbaev
774a4c5e24 Revert "[heap] Reland "[heap] Allow a minimum semi-space size of 512K.""
This reverts commit 176a2b24fb.

Reason for revert: performance regression on the benchmarks.

Original change's description:
> [heap] Reland "[heap] Allow a minimum semi-space size of 512K."
> 
> This patch changes the semi-space size to 512K.
> 
> > Original commit message:
> > Revert "[heap] Allow a minimum semi-space size of 512K."
> > This reverts commit 0d2ed6c328.
> > The CL introduced perf regressions: crbug.com/735649.
> > We are going to reland the CL in an isolated V8 roll to ensure
> > that perf regressions are attributed correctly.
> 
> > Original commit message:
> > > [heap] Allow a minimum semi-space size of 512K.
> > > This CL also reduces the minimum semi-space size to 512K.
> > > BUG=chromium:716032
> > BUG=chromium:735649
> 
> Change-Id: Iabc377cba2911b28d51b98bb5b85134d4e893632
> Reviewed-on: https://chromium-review.googlesource.com/575066
> Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
> Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#46763}

TBR=ulan@chromium.org,mlippautz@chromium.org

# Not skipping CQ checks because original CL landed > 1 day ago.

Change-Id: I80f8b6699f41e91512f7cec38060c829252ff95e
Reviewed-on: https://chromium-review.googlesource.com/591309
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46982}
2017-07-28 19:42:31 +00:00
Ulan Degenbaev
176a2b24fb [heap] Reland "[heap] Allow a minimum semi-space size of 512K."
This patch changes the semi-space size to 512K.

> Original commit message:
> Revert "[heap] Allow a minimum semi-space size of 512K."
> This reverts commit 0d2ed6c328.
> The CL introduced perf regressions: crbug.com/735649.
> We are going to reland the CL in an isolated V8 roll to ensure
> that perf regressions are attributed correctly.

> Original commit message:
> > [heap] Allow a minimum semi-space size of 512K.
> > This CL also reduces the minimum semi-space size to 512K.
> > BUG=chromium:716032
> BUG=chromium:735649

Change-Id: Iabc377cba2911b28d51b98bb5b85134d4e893632
Reviewed-on: https://chromium-review.googlesource.com/575066
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46763}
2017-07-19 13:04:47 +00:00
Ulan Degenbaev
bb29f9a4d6 [heap] Add API to set heap semi-space limits in KB.
This relands parts of "[heap] Allow a minimum semi-space size of 512K."
excluding the actual semi-space size change.

This partially reverts commit f341bb0f62

> Original commit message:
> Revert "[heap] Allow a minimum semi-space size of 512K."
> This reverts commit 0d2ed6c328.
> The CL introduced perf regressions: crbug.com/735649.
> We are going to reland the CL in an isolated V8 roll to ensure
> that perf regressions are attributed correctly.

> Original commit message:
> > [heap] Allow a minimum semi-space size of 512K.
> > This CL also reduces the minimum semi-space size to 512K.
> > BUG=chromium:716032
> BUG=chromium:735649

Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
Change-Id: I5ed66b72104aa877d67fcd20bdadc807ea1551c3
Reviewed-on: https://chromium-review.googlesource.com/575065
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46762}
2017-07-19 12:53:27 +00:00
Ulan Degenbaev
0640cbf378 [heap] Rework ASLR for base::Platform::VirtualMemory
Currently every VirtualMemory allocation on 64-bit systems
uses a random 46-bit address hint for ASLR.

This leads to wired page leak on MacOS discovered by Erik Chen (see
crbug.com/700928 and https://chromium-review.googlesource.com/c/557958/):
"The Darwin kernel [as of macOS 10.12.5] does not clean up page directory
entries [PDE] created from mmap or mach_vm_allocate, even after
the region is destroyed. Using a virtual address space that is too large
causes a leak of about 1 wired [can never be paged out] page per call to
mmap(). The page is only reclaimed when the process is killed."

This patch changes VirtualMemory to accept the hint parameter explicitly.

On MacOS the hints are confined to 4GB contiguous region. Algorithm:
- On startup, set heap.mmap_region_base_ to a random address.
- For each mmap use heap.mmap_region_base_ + (random_offset % (4*GB)).

BUG=chromium:700928

Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
Change-Id: I2ae6a024e02fbe63f940105d7920b57c19abacc6
Reviewed-on: https://chromium-review.googlesource.com/558876
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46656}
2017-07-14 07:15:40 +00:00
Michael Lippautz
660fb963b1 [heap] Templatize worklist for arbitrary entry types
To be used with tuples of heap objects and sizes.

Bug: chromium:738865
Change-Id: I29d9cf98bb2097cc8e1616aaf19a251507ffbd9e
Reviewed-on: https://chromium-review.googlesource.com/559050
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46407}
2017-07-05 10:13:33 +00:00
Michael Lippautz
8c8bb2b150 [heap] Templatize Worklist segment size
Bug: chromium:738865
Change-Id: I67b65f3006d6fe7e88854806f364d9863076b49b
Reviewed-on: https://chromium-review.googlesource.com/558969
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46397}
2017-07-04 09:24:26 +00:00
Ulan Degenbaev
f341bb0f62 Revert "[heap] Allow a minimum semi-space size of 512K."
This reverts commit 0d2ed6c328.

The CL introduced perf regressions: crbug.com/735649.

We are going to reland the CL in an isolated V8 roll to ensure
that perf regressions are attributed correctly.

Original commit message:
> [heap] Allow a minimum semi-space size of 512K.
> This CL also reduces the minimum semi-space size to 512K.
> BUG=chromium:716032

BUG=chromium:735649

Cq-Include-Trybots: master.tryserver.chromium.linux:linux_chromium_rel_ng
Change-Id: I1f1b08ca6853347c00070f000c309d839ff8a4bb
Reviewed-on: https://chromium-review.googlesource.com/552541
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46349}
2017-06-30 12:03:04 +00:00
Ulan Degenbaev
52708b6341 [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}
2017-06-30 09:43:27 +00:00
Ulan Degenbaev
ede03cd97e [heap] Add unit tests for Worklist::FlushToGlobal.
BUG=chromium:694255

Change-Id: I3e9c5e6b47b4dd0fbd2524b3329dbef14d4ad4e7
Reviewed-on: https://chromium-review.googlesource.com/550158
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46267}
2017-06-27 16:19:28 +00:00
Ulan Degenbaev
acf4929379 [heap] Replace concurrent marking deque with work-stealing worklist.
BUG=chromium:694255
TBR=mlippautz@chromium.org

Change-Id: I8eaec556d187453bd0d1cfbd0a12c0e81306862c
Reviewed-on: https://chromium-review.googlesource.com/548597
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46224}
2017-06-26 15:16:33 +00:00
Ulan Degenbaev
7dc3b0b829 [heap] Support clear and update operation in worklist.
BUG=chromium:694255

Change-Id: Ie4f14e62afa63339c586c3872d6acfa2bf4833d8
Reviewed-on: https://chromium-review.googlesource.com/545717
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46207}
2017-06-26 10:59:41 +00:00
Ulan Degenbaev
b00de2a927 [heap] Rename WorkStealingBag to Worklist.
Change-Id: I5d5df00a38b7196001fb91e2642914271d8e66d0
Reviewed-on: https://chromium-review.googlesource.com/544932
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46164}
2017-06-23 11:12:59 +00:00
Michael Lippautz
baf954759b [heap] Implement workstealing bag based on segments
Bug: chromium:651354
Change-Id: I8aa122f48986f494146d4e896b254846de7ce295
Reviewed-on: https://chromium-review.googlesource.com/543500
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#46119}
2017-06-22 09:05:30 +00:00
hpayer
0d2ed6c328 [heap] Allow a minimum semi-space size of 512K.
This CL also reduces the minimum semi-space size to 512K.

BUG=chromium:716032
CQ_INCLUDE_TRYBOTS=master.tryserver.chromium.linux:linux_chromium_rel_ng

Review-Url: https://codereview.chromium.org/2942543002
Cr-Commit-Position: refs/heads/master@{#45992}
2017-06-19 10:16:13 +00:00
Michael Lippautz
35b9776f81 [heap] Move AccessMode out from MarkBit into globals
Bug: 
Change-Id: I5ea0e072c3ac100a6f3bed62a9a4d2c11d2b7c9a
Reviewed-on: https://chromium-review.googlesource.com/533414
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#45920}
2017-06-13 17:49:17 +00:00
Ulan Degenbaev
711073a340 [heap] Add memory fence after mark-bit range update operations.
The fence ensures that the concurrent marker observes consistent state
of mark-bits for newly allocated objects.

The patch also moves Bitmap functions to cc file and removes non-atomic
versions of SetRange and ClearRange.

BUG=chromium:694255

Change-Id: I466bef654f3d4a21b7aaebdfd6d5a39ddb5f2a0a
Reviewed-on: https://chromium-review.googlesource.com/530367
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#45868}
2017-06-12 16:11:19 +00:00
hpayer
07b7d7206a [heap] Scale max heap growing factor.
BUG=chromium:716032

Review-Url: https://codereview.chromium.org/2919023003
Cr-Commit-Position: refs/heads/master@{#45850}
2017-06-12 11:37:15 +00:00
Ulan Degenbaev
bdf0ea99df [heap] Make SetRange and ClearRange operations of Bitmap thread-safe.
The boundary cells of the mark-bitmap can be access concurrently,
so they need to be updated with atomic CAS.

BUG=chromium:694255

Change-Id: Ibe85f00c8b4ccc61edc43b400c5b08a6d0ba620e
Reviewed-on: https://chromium-review.googlesource.com/521103
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#45731}
2017-06-06 13:26:45 +00:00
hpayer
d37dd4a66e [heap] Simplify and linearly scale ResourceConstraints::ConfigureDefaults.
Perf Sheriffs: This CL may change performance on various benchmarks.

BUG=chromium:716032

Review-Url: https://codereview.chromium.org/2895473003
Cr-Commit-Position: refs/heads/master@{#45495}
2017-05-23 17:00:57 +00:00
Michael Lippautz
17a2c6e847 [heap] Introduce WorkStealingMarkingDeque
Currently only relies on private stacks of segments, i.e., doesn't steal
anything, yet.

Bug: chromium:651354
Change-Id: Icedad3e3169b61afe988a1ece10f73f3a973bdb2
Reviewed-on: https://chromium-review.googlesource.com/508351
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#45422}
2017-05-19 11:49:59 +00:00
Michael Lippautz
15805b2d53 [heap] Fix ItemParallelJobTest.DistributeItemsMultipleTasks
TBR=ulan@chromium.org

Bug: chromium:651354
Change-Id: Ib3a53a62e048e438bc31cbfd2ea44d17fd6a3b94
Reviewed-on: https://chromium-review.googlesource.com/506204
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#45360}
2017-05-17 08:31:04 +00:00
Michael Lippautz
b02bb408ef [heap] Add ItemParallelJob
Adds a generic job that is based on items and tasks.

Bug: chromium:651354
Change-Id: I378e04741c5761ea6c4a74816b9af8ea22867f53
Reviewed-on: https://chromium-review.googlesource.com/506075
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#45353}
2017-05-16 21:50:56 +00:00
mlippautz
bf74d43de0 [heap] MinorMC: Evacuation for young generation
In the spirit of the full MC, we evacuate and update pointers in parallel for
the young generation.

The collectors are connected during incremental marking when mark bits are
transferred from the young generation bitmap to the old generation bitmap.

The evacuation phase cannot (yet) move pages and relies completely on copying
objects.

BUG=chromium:651354

Review-Url: https://codereview.chromium.org/2796233003
Cr-Commit-Position: refs/heads/master@{#45074}
2017-05-03 21:31:06 +00:00
ulan
c6816cd87d [heap] Implement simple concurrent marking deque.
This patch adds a concurrent marking deque that exposes the same interface
for the main thread as the existing marking deque.

The matching interface makes the concurrent marking deque a drop-in
replacement for the sequential marking deque without any change in
mark-compactor and incremental marker.

BUG=chromium:694255

Review-Url: https://codereview.chromium.org/2810893002
Cr-Commit-Position: refs/heads/master@{#45042}
2017-05-02 17:03:31 +00:00
mlippautz
a0655790ae Reland of [heap] Fix CompactionSpace test and move to unittests
This reverts commit eddf90c4a7.

BUG=chromium:651354

Review-Url: https://codereview.chromium.org/2792063004
Cr-Commit-Position: refs/heads/master@{#44398}
2017-04-05 07:36:15 +00:00
mlippautz
eddf90c4a7 Revert of [heap] Fix CompactionSpace test and move to unittests (patchset #3 id:40001 of https://codereview.chromium.org/2796033002/ )
Reason for revert:
Breaks
https://uberchromegw.corp.google.com/i/client.v8/builders/V8%20Linux%20-%20shared/builds/17291

Original issue's description:
> [heap] Fix CompactionSpace test and move to unittests
>
> BUG=chromium:651354
>
> Review-Url: https://codereview.chromium.org/2796033002
> Cr-Commit-Position: refs/heads/master@{#44382}
> Committed: ce9a2db1e1

TBR=ulan@chromium.org
# Skipping CQ checks because original CL landed less than 1 days ago.
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=chromium:651354

Review-Url: https://codereview.chromium.org/2793033004
Cr-Commit-Position: refs/heads/master@{#44383}
2017-04-04 14:47:06 +00:00
mlippautz
ce9a2db1e1 [heap] Fix CompactionSpace test and move to unittests
BUG=chromium:651354

Review-Url: https://codereview.chromium.org/2796033002
Cr-Commit-Position: refs/heads/master@{#44382}
2017-04-04 14:28:21 +00:00
hpayer
b643bb7713 [heap] Add atomics to mark bit operations.
BUG=chromium:694255

Review-Url: https://codereview.chromium.org/2492263002
Cr-Commit-Position: refs/heads/master@{#43679}
2017-03-08 16:31:18 +00:00
hpayer
bb31612af1 [heap] Remove Marking::BlackToWhite and Marking::GreyToWhite.
BUG=chromium:694255

Review-Url: https://codereview.chromium.org/2737483002
Cr-Commit-Position: refs/heads/master@{#43609}
2017-03-06 12:10:05 +00:00
hpayer
b7944a5cd5 [heap] Remove Marking::AnyToGrey and change its callers to use simple marking functions.
BUG=chromium:694255

Review-Url: https://codereview.chromium.org/2728113002
Cr-Commit-Position: refs/heads/master@{#43586}
2017-03-03 13:31:52 +00:00
hpayer
c45d065edc [heap] Remove Marking::MarkBlack and some minor cleanups.
BUG=chromium:694255

Review-Url: https://codereview.chromium.org/2720133005
Cr-Commit-Position: refs/heads/master@{#43519}
2017-03-01 14:53:20 +00:00
mlippautz
504d0e5979 [heap] Fix address space leak in Unmapper
BUG=v8:5945

Review-Url: https://codereview.chromium.org/2689683002
Cr-Commit-Position: refs/heads/master@{#43102}
2017-02-10 14:26:04 +00:00
krasin
5ccc719a31 Fix unused lambda captures.
Clang just got more strict about unused lambda captures,
and that requires us to clean all places with this issue
across all the Chromium code base. This CL fixes all such
cases in V8.

BUG=chromium:681136

Review-Url: https://codereview.chromium.org/2646553002
Cr-Commit-Position: refs/heads/master@{#42523}
2017-01-19 21:34:00 +00:00
mlippautz
5622bc15f1 Reland of "[heap] Report wrappers after processing the marking deque incrementally"
We need to report cached wrappers within v8 to the embedder after each atomic
phase of v8 marking because the embedder can invalidate the wrappers in-between
v8 marking steps.

E.g., in Chrome, a conservative GC might need to wipe dead wrappables from
the wrapper tracing marking deque.

BUG=chromium:676700, chromium:468240

Review-Url: https://codereview.chromium.org/2610563002
Cr-Commit-Position: refs/heads/master@{#42011}
2017-01-02 13:06:11 +00:00
machenbach
061a3a152c Revert of [heap] Report wrappers after processing the marking deque incrementally (patchset #5 id:80001 of https://codereview.chromium.org/2604583002/ )
Reason for revert:
Speculative revert. Might block the roll:
https://codereview.chromium.org/2606503002/

The gpu bots crash with this stack top:v88internal18IncrementalMarking25AdvanceIncrementalMarkingEdNS1_16CompletionActionENS1_21ForceCompletionActionENS0_10StepOrigin

Original issue's description:
> [heap] Report wrappers after processing the marking deque incrementally
>
> BUG=chromium:676700, chromium:468240
>
> Review-Url: https://codereview.chromium.org/2604583002
> Cr-Commit-Position: refs/heads/master@{#41946}
> Committed: 1344e3a9ca

TBR=hpayer@chromium.org,mlippautz@chromium.org
# Skipping CQ checks because original CL landed less than 1 days ago.
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=chromium:676700, chromium:468240

Review-Url: https://codereview.chromium.org/2604673002
Cr-Commit-Position: refs/heads/master@{#41951}
2016-12-24 12:07:32 +00:00
mlippautz
1344e3a9ca [heap] Report wrappers after processing the marking deque incrementally
BUG=chromium:676700, chromium:468240

Review-Url: https://codereview.chromium.org/2604583002
Cr-Commit-Position: refs/heads/master@{#41946}
2016-12-23 17:11:42 +00:00
mlippautz
119db080c5 [heap] Fix unittest compilation on mips
BUG=
TBR=hpayer@chromium.org
NOTRY=true

Review-Url: https://codereview.chromium.org/2587363002
Cr-Commit-Position: refs/heads/master@{#41841}
2016-12-20 09:56:39 +00:00
mlippautz
17318bbd39 [heap] Create a thin wrapper around wrapper tracing in V8 to avoid misuse
BUG=chromium:468240

Review-Url: https://codereview.chromium.org/2576453002
Cr-Commit-Position: refs/heads/master@{#41837}
2016-12-20 09:35:05 +00:00
cbruni
c0282f608c Add unittests to keep InstanceType lists in sync
STRUCT_LIST and INSTANCE_TYPE_LIST are now forced to have the same order
as the InstanceType enum.

Drive-by-fix 1: Move type check and cast functions closer together in objects-inl.h

Drive-by-fix 2: Remove unused instance types SIGNATURE_INFO_TYPE and  TYPE_SWITCH_INFO_TYPE.

BUG=

Review-Url: https://codereview.chromium.org/2578573002
Cr-Commit-Position: refs/heads/master@{#41804}
2016-12-19 12:50:30 +00:00
ulan
b9f8ad002e [heap] Reland "Add a guard for restarting the memory reducer after mark-compact."
This reverts commit 3c96c5e232.

The CL was reverted to see its impact on UMA memory counters.
There was no impact, so we can safely reland the CL.

BUG=

Review-Url: https://codereview.chromium.org/2507293004
Cr-Commit-Position: refs/heads/master@{#41109}
2016-11-18 13:50:22 +00:00
mlippautz
7e5755cbc5 [heap] Minor MC: Add marking
Adds the marking logic to mark the young generation.

BUG=chromium:651354

Review-Url: https://codereview.chromium.org/2498583002
Cr-Commit-Position: refs/heads/master@{#41104}
2016-11-18 12:56:16 +00:00
ulan
f18d56d130 Fix more -Wsign-compare warnings in heap, mips, base, etc.
BUG=v8:5614

Review-Url: https://codereview.chromium.org/2496913002
Cr-Commit-Position: refs/heads/master@{#40931}
2016-11-11 14:56:10 +00:00
ulan
ade3bc6da9 [heap] Fix -Wsign-compare warnings
BUG=v8:5614

Review-Url: https://codereview.chromium.org/2489933002
Cr-Commit-Position: refs/heads/master@{#40880}
2016-11-10 10:16:35 +00:00
ulan
3c96c5e232 Revert of [heap] Add a guard for restarting the memory reducer after mark-compact. (patchset #1 id:1 of https://chromiumcodereview.appspot.com/2433933005/ )
Reason for revert:
Speculative revert to see impact on crbug.com/659531

Original issue's description:
> [heap] Add a guard for restarting the memory reducer after mark-compact.
>
> Currently it is possible to get into a cycle of
> mark-compact -> memory reducer -> mark-compact -> memory reducer ...
> where the memory reducer does not free memory.
>
> This patch ensures that the memory reducer restarts only if the
> committed memory increased by sufficient amount after the last run.
>
> BUG=

TBR=hpayer@chromium.org,davidroutier17@gmail.com
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG=

Review-Url: https://codereview.chromium.org/2472053003
Cr-Commit-Position: refs/heads/master@{#40737}
2016-11-03 17:27:04 +00:00
hpayer
a007dfc18e [heap] Move typed slot filtering logic into sweeper.
Additionally, remove all code related to the old-style slots filtering and black area end markers.

BUG=chromium:648568

Review-Url: https://chromiumcodereview.appspot.com/2440683002
Cr-Commit-Position: refs/heads/master@{#40494}
2016-10-21 09:05:00 +00:00