This reverts commit c84963eaa7.
Reason for revert: Fails on msan: https://ci.chromium.org/p/v8/builders/ci/V8%20Linux%20-%20arm64%20-%20sim%20-%20MSAN/31376
Original change's description:
> [heap] Introduce safepoint mechanism
>
> Add safepoint mechanism to stop concurrent threads and bring them to a
> safepoint. Threads are stopped before the safepoint and after e.g. the
> GC resumed again. Each thread needs to be stopped in a safepoint, such
> that all roots can be iterated safely.
>
> Running threads need to be cooperative and are required to perform
> regular safepoint polls.
>
> Bug: v8:10315
> Change-Id: I47f07e7d2ef5bc5adbba6b9e8e79a1f0f45b97ad
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2102578
> Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#66727}
TBR=ulan@chromium.org,dinfuehr@chromium.org
Change-Id: If11281b2b9fc622b91261417b202676f23f60b50
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: v8:10315
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2105634
Reviewed-by: Clemens Backes <clemensb@chromium.org>
Commit-Queue: Clemens Backes <clemensb@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66729}
Add safepoint mechanism to stop concurrent threads and bring them to a
safepoint. Threads are stopped before the safepoint and after e.g. the
GC resumed again. Each thread needs to be stopped in a safepoint, such
that all roots can be iterated safely.
Running threads need to be cooperative and are required to perform
regular safepoint polls.
Bug: v8:10315
Change-Id: I47f07e7d2ef5bc5adbba6b9e8e79a1f0f45b97ad
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2102578
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66727}
Instead of directly using the Heap class concurrent threads will use the
LocalHeap class for all heap operations.
Bug: v8:10315
Change-Id: Ie007abb5b914af7f2507c9e790f34baacbcdf588
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2096620
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66663}
Remove OffThreadHandle, HandleOrOffThreadHandle, and HandleFor, and
make the OffThreadIsolate allocate "real" Handles. Rather than using
the main-thread Isolate's handle scopes, these off-thread Handles are
backed by a Zone, which is tied to the lifetime of the nearest
OffThreadHandleScope. Eventually, we'll likely want to merge the
implementation of OffThreadHandleScope and HandleScope, but currently
the latter is too tightly coupled to the main thread to do so.
Bug: chromium:1011762
Change-Id: I2a6361931fe3f90a7bef4cc28ee42155fa8d062f
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2071865
Reviewed-by: Ross McIlroy <rmcilroy@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66516}
GlobalSize will be used as a hint to schedule scavenger work in
https://chromium-review.googlesource.com/c/v8/v8/+/2036661
This is implemented as an atomic variable that's updated when adding/removing
segments.
Bug: chromium:1012816
Change-Id: I8f6c3f10612f8febda9bfe640d91e235aa3c2f12
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2043273
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Etienne Pierre-Doray <etiennep@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66175}
Allow caching the result of allocating AstConsStrings, to allow
sharing of inferred names between functions.
This is a partial revert of https://crrev.com/c/2020953, with
the observation that *some* AstConsStrings are always flattened,
while others are only ever used as ConsStrings, so we want to
allow the allocation to be lazy while still caching the result.
As a drive-by, cleanup the old AstConsString linked list fields.
Bug: chromium:1011762
Bug: chromium:1048082
Change-Id: Icc14342eb3f6f97359596b42b2c296cbc49fd791
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2042093
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Auto-Submit: Leszek Swirski <leszeks@chromium.org>
Reviewed-by: Victor Gomes <victorgomes@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66168}
A pointer-compressed heap has the same heap limit heuristics as a 32-bit
heap. Specifically, the heap limit is restricted to 1GB due to scarce
virtual addresses space on 32-bit platforms. That limitation does not
apply for pointer-compressed heaps which can use 4GB.
This CL changes the heap limit computation to use system the pointer
size instead of the tagged pointer size. Note that the young generation
limit continues to use the tagged pointer size.
Bug: chromium:1045034
Change-Id: I9d5bb818c32a82322476e9c97feee331400ebe0f
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2042102
Reviewed-by: Igor Sheludko <ishell@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66159}
The Factory/OffThreadFactory allows us to cleanly separate object
construction behaviour between main-thread and off-thread in a
syntactically consistent way (so that methods templated on the factory
type can be made to work on both).
However, there are cases where we also have to access the Isolate, for
handle creation or exception throwing. So far we have been pushing more
and more "customization points" into the factories to allow these
factory-templated methods to dispatch on this isolate behaviour via
these factory methods. Unfortunately, this is an increasing layering
violation between Factory and Isolate, particularly around exception
handling.
Now, we introduce an OffThreadIsolate, analogous to Isolate in the same
way as OffThreadFactory is analogous to Factory. All methods which were
templated on Factory are now templated on Isolate, and methods which
used to take an Isolate, and which were recently changed to take a
templated Factory, are changed/reverted to take a templated Isolate.
OffThreadFactory gets an isolate() method to match Factory's.
Notably, FactoryHandle is changed to "HandleFor", where the template
argument can be either of the Isolate type or the Factory type (allowing
us to dispatch on both depending on what is available).
Bug: chromium:1011762
Change-Id: Id144176f7da534dd76f3d535ab2ade008b6845e3
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2030909
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66101}
Remove AstConsString "internalization", and instead make the conversion
to heap String be on-demand with an Allocate method. We never actually
need the heapified cons string more than once, so there's no need to do
the internalization walk or do the next/string union dance in the
AstConsString class.
This also allows us to specify how we want to allocate the String at the
call site. In particular, it allows us to allocate a flat SeqString rather
rather than a ConsString. This allows us to avoid allocating ConsStrings
which will just be passed to a flatten call, and especially avoid
allocating dead ConsStrings in the off-thread old space.
Bug: chromium:1011762
Bug: chromium:1043168
Change-Id: Id851f2f7529d92ad7e5388eb22823fd6d1959cd0
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2020953
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Cr-Commit-Position: refs/heads/master@{#66042}
The SequentialUnmapperTest replaces the process-global PageAllocator
with a wrapper which tracks allocations. The suite was deleting the
tracking allocator without first restoring the original PageAllocator,
causing any subsequent tests which tried to use it to use-after-free.
Bug: chromium:934932
Change-Id: I0f69b6a07542a3f381724afdbfb2e9b67a9f39de
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2010113
Commit-Queue: Wez <wez@chromium.org>
Commit-Queue: Michael Achenbach <machenbach@chromium.org>
Auto-Submit: Wez <wez@chromium.org>
Reviewed-by: Michael Achenbach <machenbach@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65872}
Add support for internalizing an AstValueFactory using the off-thread
factory. Includes adding ConsString support to OffThreadFactory.
This introduces a Handle union wrapper, which is used in locations that
can store a Handle or an OffThreadHandle. This is used in this patch for
the internalized "string" field of AST strings, and will be able to be
used for other similar fields in other classes (e.g. the ScopeInfo
handle in Scope, object boilerplate descriptor handles, the inferred
name handle on FunctionLiterals, etc.). It has a Factory-templated
getter which returns the appropriate handle for the factory, and a
debug-only tag to make sure the right getter is used at runtime. This
union wrapper currently decomposes implicitly to a Handle if the getter
is not called, to minimise code changes, but this implicit conversion
will likely be removed for clarity.
Bug: chromium:1011762
Change-Id: I5dd3a7bbdc483b66f5ff687e0079c545b636dc13
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1993971
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65816}
Introduce OffThreadFactory with initial string construction support.
The OffThreadFactory shares with Factory a new CRTP base class, called
FactoryBase. Methods in FactoryBase return a FactoryHandle<Factory, T>
alias, which is Handle<T> for normal Factory and a new OffThreadHandle<T>
for OffThreadFactory. OffThreadHandle<T> behaves like Handle<T>, except
it stores the object in-line rather than needing external storage.
Any shared factory methods are moved into FactoryBase, which uses CRTP
to call the sub-class's AllocateRaw method (plus a few more customization
points which need Isolate access on the main thread).
Methods that used to take an Isolate or Factory, and are needed off the
main thread, are now expected to be templated on the factory type and
to use the appropriate handle.
Once an OffThreadFactory has finished being used (e.g. off-thread
compilation completed) its pages are "Published" into the main-thread
Heap. To deal with string internalization without creating a bunch of
ThinStrings, this is done in two stages:
1. 'FinishOffThread': The off-thread pages are walked to
collect all slots pointing to "internalized" strings. After this is
called it is invalid to allocate any more objects with the factory.
2. 'Publish': On the main thread, we transform these slots into
<Handle to holder, offset> pairs, then for each saved slot
re-internalize its string and update the slot to point to the
internalized string.
Bug: chromium:1011762
Change-Id: I008a694da3c357de34362bd86fe7e1f46b535d5e
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1992434
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65787}
- Introduces a API to set top of the stack through
EmbedderHeapTracer::SetStackTop.
- Introduces a new API to inform V8 about an empty embedder stack.
- Switch internal representation of TracedReference
for on-stack handles to a proper stack that considers all
contained handles as roots.
- Handle garbage is avoided by cleaning up on handle creation or
GC.
Design doc: https://bit.ly/on-stack-traced-reference
Bug: chromium:1040038
Change-Id: I927ef0abb268fdb5853c9e17b1bc96e2491cf101
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1993973
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65757}
These worklists are needed for accounting of objects retained by
native contexts for the new memory measurement API.
Bug: chromium:973627
Change-Id: I354c5ebbbac11da4d01800164e15b94a93aa654c
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1943158
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65542}
Before this CL a byte was used per bucket to store whether the bucket
is possibly empty or not. This CL changes this such that each bucket
only needs a single bit.
PossiblyEmptyBuckets is now a word in the page header. If more bits
are needed than fit into a single word, an external bitmap is
allocated using AlignedAlloc. Storing this on the page header, allows
to remove initial_buckets from the SlotSet. The SlotSet allocation is
then again a power-of-2 in release mode.
Reland of https://crrev.com/c/1906376: Incorrect DCHECK was removed.
WordsForBuckets was simplified and a test was added for it.
Bug: chromium:1023139
Change-Id: I9a08e03a9c10e5781a146b9a28dab38824aad91f
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1954391
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65385}
This reverts commit 80caf2cf53.
Reason for revert: Breaks gpu tests:
https://ci.chromium.org/p/v8/builders/ci/Win%20V8%20FYI%20Release%20(NVIDIA)/5570
# Debug check failed: !possibly_empty_buckets->Contains(bucket_index).
Original change's description:
> [heap] Reduce size of possibly empty buckets
>
> Before this CL a byte was used per bucket to store whether the bucket
> is possibly empty or not. This CL changes this such that each bucket
> only needs a single bit.
>
> PossiblyEmptyBuckets is now a word in the page header. If more bits
> are needed than fit into a single word, an external bitmap is
> allocated using AlignedAlloc. Storing this on the page header, allows
> to remove initial_buckets from the SlotSet. The SlotSet allocation is
> then again a power-of-2 in release mode.
>
> Change-Id: If61fd5cfa153f98757beeb444a530f6e2803fdb6
> Bug: chromium:1023139
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1906376
> Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#64991}
TBR=ulan@chromium.org,dinfuehr@chromium.org
# Not skipping CQ checks because original CL landed > 1 day ago.
Bug: chromium:1023139
Change-Id: Ia90b07b9562af934dacba012da31e4f172f2922d
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1918258
Reviewed-by: Michael Achenbach <machenbach@chromium.org>
Commit-Queue: Michael Achenbach <machenbach@chromium.org>
Cr-Commit-Position: refs/heads/master@{#65001}
Before this CL a byte was used per bucket to store whether the bucket
is possibly empty or not. This CL changes this such that each bucket
only needs a single bit.
PossiblyEmptyBuckets is now a word in the page header. If more bits
are needed than fit into a single word, an external bitmap is
allocated using AlignedAlloc. Storing this on the page header, allows
to remove initial_buckets from the SlotSet. The SlotSet allocation is
then again a power-of-2 in release mode.
Change-Id: If61fd5cfa153f98757beeb444a530f6e2803fdb6
Bug: chromium:1023139
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1906376
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64991}
Add a new LargeObjectSpace for off-thread allocation. Similar to the
paged OffThreadSpace, it always allocates pages, doesn't participate
in mark or sweep, and can be merged into the OldLargeObjectSpace once
its objects are ready.
Bug: chromium:1011762
Change-Id: I95e2d38b10a9cc5eae4ffd35afef95272e13c731
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1881153
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64727}
Change SlotSet representation to a variable-sized array of pointers to
buckets. The length of the array/number of buckets depends on the size
of the page.
Before this change the SlotSet always stored a fixed number of
buckets. Large pages needed a SlotSet-Array to cover the whole object.
Now both regular and large pages both use a single SlotSet object,
which contains all bucket pointers.
Change-Id: I2d8d62fad54b58409cd39ae7a52c64497ee7c261
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1876811
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64635}
Add a new PagedSpace called OffThreadSpace. This space will be used for
off-thread allocation -- it never marks or sweeps, and always expands
into fresh pages. Once allocation completes, this space's pages can be
merged into the old space.
The space is similar to the CompactionSpace, and merging for both is
identical, so we intrduce a new LocalSpace base class that both extend.
They differ in interaction with the sweeper and in how new pages are
acquired.
This patch adds the new space and uses it in a few unittests. Future
work will use it in the main source code.
Bug: chromium:1011762
Change-Id: Ia008cc95c6e1ef1d1e7ae305fa80fbfc1ff4be2d
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1873690
Commit-Queue: Leszek Swirski <leszeks@chromium.org>
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64509}
This CL ensures that recorded slots are either in the sweeping or the
old-to-new remembered set after mark-compact depending on whether the
page was already swept or not.
All pages that are swept during the evacuation phase also have their
remembered sets merged. is_local() is renamed to
is_compaction_space() and non-virtual. The PagedSpace now not only
knows whether it is a compaction space or not but also for which
collection through the compaction_space_kind_ field. This allows
RefillFreeList to merge the remembered sets immediately also for the
mark-compact collection.
Change-Id: I7457f8393d73f3e8d6b6ebedc46ebc36af509729
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1868613
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64458}
With the smi-corrupting decompression approach we don't have to sign
extend Smis anymore and therefore we can switch to zero extending
approach by moving the isolate root to the beginning of the reserved
4Gb region.
Bug: v8:9706
Change-Id: Icd6008fa87d0924519b574fdec445976f742e306
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1835548
Commit-Queue: Igor Sheludko <ishell@chromium.org>
Reviewed-by: Jakob Gruber <jgruber@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64144}
Do not store page_start_ in SlotSet anymore, when needed this address
can be calculated cheaply and be passed in from the caller.
Bug: v8:9454
Change-Id: I4cdb010e4126680d8df500e40ae3d0bc884cf501
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1838731
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#64103}
Since https://crrev.com/c/1771783 the mutator owns the old-to-new
remembered set, while the sweeper modifies the sweeping-slot-set.
This allows us to update the old-to-new remembered set non-atomically.
In this CL the mutator now inserts non-atomically into the remembered
set. The AccessMode is now explicit for Insert-operations as well.
Bug: v8:9454
Change-Id: I94730345f7dd34fe309839969330687c94b3080b
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1803652
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63971}
Before this CL the main thread fetched the background GC stats and
added them to the main runtime-call-stats table. This resulted
in background GC stats showing up in the main thread trace.
This CL switches the background GC stats to use worker thread runtime-
calls-stats table. This is now consistent with other background
components of V8 suchs background compiler and parser.
Bug: v8:9508
Change-Id: Ic4c0685ded6024f78d0f22f81419fd5677202f25
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1776083
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63459}
This new FreeList should be a reasonable replacement for our old
FreeListLegacy: it is slightly less efficient (~1%), but uses much
less memory (often 5% less old_space size).
It is based on FreeListMany, with the following additions:
- A cache to waste less time iterating empty categories
- A fast path for allocations done in the runtime and generated code
- A slow path (the same as FreeListMany actually) for allocations
done in the GC.
Bug: v8:9329
Change-Id: Ifc10b88df7861266a721afd2c6e6d8357255ec4e
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1762292
Commit-Queue: Darius Mercadier <dmercadier@google.com>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63345}
Do not pass it as argument to CreateObjectFillerAt and remove the enum.
Bug: v8:9454
Change-Id: Iafa37acbfea73d3cabb1732dbec0944db859fac2
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1762017
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63282}
This reverts commit 60843b426b.
Reason for revert: TSAN detected issue between Scavenge workers.
One task could invoke RefillFreeList(), while the other task iterates the remembered set of a swept page.
Original change's description:
> Use list of invalidated objects for old-to-new refs
>
> Instead of inserting "deletion" entries into the store buffer, keep a
> list of invalidated objects to filter out invalid old-to-new slots.
>
> The first CL https://crrev.com/c/1704109 got reverted because both the
> sweeper and the main task were modifying the invalidated slots data
> structure concurrently. This CL changes this, such that the sweeper
> only modifies the invalidated slots during the final atomic pause when
> the main thread is not running. The sweeper does not need to clean this
> data structure after the pause, since the "update pointers" phase
> already removed all invalidated slots.
>
> The second CL https://crrev.com/c/1733081 got reverted because the
> sweeper might find more free space than the full GC before it. If an
> object shrinks after the pause but before the sweep, the invalidated
> object might span free memory and potentially new allocated objects.
> Therefore shrink invalidated objects when processing swept pages on
> the main thread. Also clean recorded slots in the gap.
>
> TBR=petermarshall@chromium.org
>
> Bug: v8:9454
> Change-Id: I80d1fa3bbc24e97f7c97a373aaad66f105456f12
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1751795
> Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#63239}
TBR=ulan@chromium.org,hpayer@chromium.org,dinfuehr@chromium.org
Change-Id: I9c6a371ebe36a1873acbe0d6c6a75dd2f5a55f4e
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: v8:9454
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1760817
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63253}
Instead of inserting "deletion" entries into the store buffer, keep a
list of invalidated objects to filter out invalid old-to-new slots.
The first CL https://crrev.com/c/1704109 got reverted because both the
sweeper and the main task were modifying the invalidated slots data
structure concurrently. This CL changes this, such that the sweeper
only modifies the invalidated slots during the final atomic pause when
the main thread is not running. The sweeper does not need to clean this
data structure after the pause, since the "update pointers" phase
already removed all invalidated slots.
The second CL https://crrev.com/c/1733081 got reverted because the
sweeper might find more free space than the full GC before it. If an
object shrinks after the pause but before the sweep, the invalidated
object might span free memory and potentially new allocated objects.
Therefore shrink invalidated objects when processing swept pages on
the main thread. Also clean recorded slots in the gap.
TBR=petermarshall@chromium.org
Bug: v8:9454
Change-Id: I80d1fa3bbc24e97f7c97a373aaad66f105456f12
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1751795
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63239}
This reverts commit e2f98ec22c.
Reason for revert: Caused performance regression in ArrayLiteralInitialSpreadSmallHoley.
Original change's description:
> Use list of invalidated objects for old-to-new refs
>
> Instead of inserting "deletion" entries into the store buffer, keep
> a list of invalidated objects to filter out invalid old-to-new slots.
>
> The first CL https://crrev.com/c/1704109 got reverted because both the sweeper and the main task were modifying the invalidated slots data structure concurrently. This CL changes this, such that the sweeper only modifies the invalidated slots during the final atomic pause when the main thread is not running. The sweeper does not need to clean this data structure after the pause, since the "update pointers" phase already removed all invalidated slots.
>
> Bug: v8:9454
> Change-Id: Iffb5bf96de2c89eee1ee1231a3414a0f2a155cbc
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1733081
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Reviewed-by: Peter Marshall <petermarshall@chromium.org>
> Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#63087}
TBR=ulan@chromium.org,petermarshall@chromium.org,dinfuehr@chromium.org
# Not skipping CQ checks because original CL landed > 1 day ago.
Bug: v8:9454
Change-Id: I328b9f72df45fc9570d4a4d1b5389eac010638c7
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1743970
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63131}
Instead of inserting "deletion" entries into the store buffer, keep
a list of invalidated objects to filter out invalid old-to-new slots.
The first CL https://crrev.com/c/1704109 got reverted because both the sweeper and the main task were modifying the invalidated slots data structure concurrently. This CL changes this, such that the sweeper only modifies the invalidated slots during the final atomic pause when the main thread is not running. The sweeper does not need to clean this data structure after the pause, since the "update pointers" phase already removed all invalidated slots.
Bug: v8:9454
Change-Id: Iffb5bf96de2c89eee1ee1231a3414a0f2a155cbc
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1733081
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#63087}
This is a reland of a0728e869b
Original change's description:
> [d8] Remove maximum workers limitation
>
> This CL refactors the lifetime management of the v8::Worker C++ object
> and in the process lifts the 100 maximum worker limitation. To do this,
> it uses a Managed<v8::Worker> heap object and attaches the managed to
> the API worker object.
>
> R=mstarzinger@chromium.org
> BUG=v8:9524
>
> Change-Id: I279b7aeb6645a87f9108ee6f572105739721cef4
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1715453
> Commit-Queue: Ben Titzer <titzer@chromium.org>
> Reviewed-by: Clemens Hammacher <clemensh@chromium.org>
> Reviewed-by: Michael Starzinger <mstarzinger@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#62932}
Bug: v8:9524
Change-Id: I7d903fb12ddb00909a9429455f46c55db2fd02de
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1722562
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Clemens Hammacher <clemensh@chromium.org>
Commit-Queue: Ben Titzer <titzer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#62974}
When the main thread contributes to an item parallel job and runs
an item parallel task, it currently emits a background GC trace event.
That is confusing and may lead to incorrect accounting of main thread
GC time. This patch fixes it by introducing a 'Runner' parameter
to ItemParalllelJob::Task::RunInParallel and emitting a foreground
GC event if the runner is the main thread.
Bug: v8:9508
Change-Id: I755751bfe9eef427666d5f16fb50aa6093059e80
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1706485
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#62798}
This reverts commit dcac02ee81.
Reason for revert: TSAN discovered issue with cleaning invalidated slots in sweeper threads and inserting new slots in the main thread.
Original change's description:
> Use list of invalidated objects for old-to-new refs
>
> Instead of inserting "deletion" entries into the store buffer, keep
> a list of invalidated objects to filter out invalid old-to-new slots.
>
> Bug: v8:9454
> Change-Id: Icd21d8cb2159190457f54d0f8b56742ecc820419
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1695474
> Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Reviewed-by: Peter Marshall <petermarshall@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#62744}
TBR=ulan@chromium.org,petermarshall@chromium.org,dinfuehr@chromium.org
Change-Id: I4278e9100c76657663e0a6a62f5d86bb3a343c0e
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: v8:9454
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1704109
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#62746}
Instead of inserting "deletion" entries into the store buffer, keep
a list of invalidated objects to filter out invalid old-to-new slots.
Bug: v8:9454
Change-Id: Icd21d8cb2159190457f54d0f8b56742ecc820419
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1695474
Commit-Queue: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#62744}
If the embedder specifies an initial heap size, then we can take it
as a hint to skip full GCs below that threshold.
Bug: v8:9306
Change-Id: I42a4c597bf75c6ba9845ed7a6bd9946012979005
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1646515
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#62030}
The new API function is called ConfigureDefaultsFromHeapSize and
accepts two parameters: the initial and the maximum heap size.
Based on the given limits the function computes the default size
for the young and the old generation.
The patch also cleans up the existing functions to make them
consistent in terms of units and heap structure.
Bug: v8:9306
Change-Id: If2200a9cdb45b0b818a373207efe4e6426f7b688
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1631593
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Jakob Gruber <jgruber@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#62017}
The size is now computed as a fraction of the old space size:
- for low memory devices (<512MB) the fraction is 1 / 256.
- for all other devices the fraction is 1 / 128.
The values were chosen to minimize the difference between the new
and the old heuristics.
Bug: v8:9306
Change-Id: I3246fe2d6fc589af6220e2566e3f10fb13470b82
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1632158
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Commit-Queue: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61947}
Rework limit computation:
- Model controller as static classes based on traits.
- Compute growing factors for both controllers and pick the
larger growing factor for both controllers.
- Factor out limit computation in its own function.
Bug: chromium:948807
Change-Id: Id466a66d7aa573de91ad388ea9218e9f6721d19a
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1627534
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61801}
This CL was generated by an automatic clang AST rewriter using this
matcher expression:
callExpr(
callee(
cxxMethodDecl(
hasName("operator->"),
ofClass(isSameOrDerivedFrom("v8::internal::Object"))
)
),
argumentCountIs(1)
)
The "->" at the expression location was then rewritten to ".".
R=jkummerow@chromium.orgTBR=mstarzinger@chromium.org,verwaest@chromium.org,yangguo@chromium.org
Bug: v8:9183, v8:3770
No-Try: true
No-Tree-Checks: true
Change-Id: I0a7ecabdeafe51d0cf427f5280af0c7cab96869e
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1624209
Reviewed-by: Clemens Hammacher <clemensh@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Commit-Queue: Yang Guo <yangguo@chromium.org>
Commit-Queue: Clemens Hammacher <clemensh@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61764}
