This fixes the corner-case where the method in question failed to lookup
the very last deoptimization bailout without subsequent entries within
the relocation info. Also enable a test covering this.
R=tebbi@chromium.org
TEST=cctest/test-cpu-profiler/CollectDeoptEvents
Review-Url: https://codereview.chromium.org/2565733002
Cr-Commit-Position: refs/heads/master@{#41623}
The new SourcePosition class allows for precise tracking of source positions including the stack of inlinings. This CL makes the cpu profiler use this new information. Before, the cpu profiler used the deoptimization data to reconstruct the inlining stack. However, optimizing compilers (especially Turbofan) can hoist out checks such that the inlining stack of the deopt reason and the inlining stack of the position the deoptimizer jumps to can be different (the old cpu profiler tests and the ones introduced in this cl produce such situations for turbofan). In this case, relying on the deoptimization info produces paradoxical results, where the reported position is before the function responsible is called. Even worse, https://codereview.chromium.org/2451853002/ combines the precise position with the wrong inlining stack from the deopt info, leading to completely wrong results.
Other changes in this CL:
- DeoptInlinedFrame is no longer needed, because we can compute the correct inlining stack up front.
- I changed the cpu profiler tests back to test situations where deopt checks are hoisted out in Turbofan and made them robust enough to handle the differences between Crankshaft and Turbofan.
- I reversed the order of SourcePosition::InliningStack to make it match the cpu profiler convention.
- I removed CodeDeoptEvent::position, as it is no longer used.
R=alph@chromium.org
BUG=v8:5432
Review-Url: https://codereview.chromium.org/2503393002
Cr-Commit-Position: refs/heads/master@{#41168}
SourcePosition::InliningId() refers to a the new table DeoptimizationInputData::InliningPositions(), which provides the following data for every inlining id:
- The inlined SharedFunctionInfo as an offset into DeoptimizationInfo::LiteralArray
- The SourcePosition of the inlining. Recursively, this yields the full inlining stack.
Before the Code object is created, the same information can be found in CompilationInfo::inlined_functions().
If SourcePosition::InliningId() is SourcePosition::kNotInlined, it refers to the outer (non-inlined) function.
So every SourcePosition has full information about its inlining stack, as long as the corresponding Code object is known. The internal represenation of a source position is a positive 64bit integer.
All compilers create now appropriate source positions for inlined functions. In the case of Turbofan, this required using AstGraphBuilderWithPositions for inlined functions too. So this class is now moved to a header file.
At the moment, the additional information in source positions is only used in --trace-deopt and --code-comments. The profiler needs to be updated, at the moment it gets the correct script offsets from the deopt info, but the wrong script id from the reconstructed deopt stack, which can lead to wrong outputs. This should be resolved by making the profiler use the new inlining information for deopts.
I activated the inlined deoptimization tests in test-cpu-profiler.cc for Turbofan, changing them to a case where the deopt stack and the inlining position agree. It is currently still broken for other cases.
The following additional changes were necessary:
- The source position table (internal::SourcePositionTableBuilder etc.) supports now 64bit source positions. Encoding source positions in a single 64bit int together with the difference encoding in the source position table results in very little overhead for the inlining id, since only 12% of the source positions in Octane have a changed inlining id.
- The class HPositionInfo was effectively dead code and is now removed.
- SourcePosition has new printing and information facilities, including computing a full inlining stack.
- I had to rename compiler/source-position.{h,cc} to compiler/compiler-source-position-table.{h,cc} to avoid clashes with the new src/source-position.cc file.
- I wrote the new wrapper PodArray for ByteArray. It is a template working with any POD-type. This is used in DeoptimizationInputData::InliningPositions().
- I removed HInlinedFunctionInfo and HGraph::inlined_function_infos, because they were only used for the now obsolete Crankshaft inlining ids.
- Crankshaft managed a list of inlined functions in Lithium: LChunk::inlined_functions. This is an analog structure to CompilationInfo::inlined_functions. So I removed LChunk::inlined_functions and made Crankshaft use CompilationInfo::inlined_functions instead, because this was necessary to register the offsets into the literal array in a uniform way. This is a safe change because LChunk::inlined_functions has no other uses and the functions in CompilationInfo::inlined_functions have a strictly longer lifespan, being created earlier (in Hydrogen already).
BUG=v8:5432
Review-Url: https://codereview.chromium.org/2451853002
Cr-Commit-Position: refs/heads/master@{#40975}
With this CL, we set the is_source_positions_enabled flag on CompilationInfo when
- a command line flag is enabled that requires Turbofan to preserve source position
information (e.g. --trace-deopt), and
- when profiling is enabled.
This also removes the --turbo-source-positions flag.
The goal is to eventually only track source position information when needed.
R=mstarzinger@chromium.org
BUG=v8:5439
Review-Url: https://codereview.chromium.org/2484163003
Cr-Commit-Position: refs/heads/master@{#40836}
These are added to the sampler stack trace when RCS are
enabled.
Resource name for a RCS frame is reported as "V8Runtime".
Counter names match ones from src/counters.h
BUG=chromium:660428
Review-Url: https://codereview.chromium.org/2461003002
Cr-Commit-Position: refs/heads/master@{#40658}
A new V8 API object v8::TracingCpuProfiler is introduced.
Client can create it on an isolate to enable JS CPU profiles collected
during tracing session.
Once the v8.cpu_profile2 tracing category is enabled the profiler emits
CpuProfile and CpuProfileChunk events with the profile data.
BUG=chromium:406277
Review-Url: https://codereview.chromium.org/2396733002
Cr-Commit-Position: refs/heads/master@{#40054}
When we OSR using Turbofan, we would set the function to be optimized
on the next call, irrespective of the runtime profiler's previous
decisions - such as compiling for baseline. It seems more prudent to
always make these decisions in the runtime profiler where the data is
available.
Review-Url: https://codereview.chromium.org/2369043002
Cr-Commit-Position: refs/heads/master@{#39782}
GetFunctionNameStr and GetScriptResourceNameStr can be called from a thread
other than isolate VM thread unlike their conterparts GetFunctionName
and GetScriptResourceName.
BUG=406277
Review-Url: https://codereview.chromium.org/2328673003
Cr-Commit-Position: refs/heads/master@{#39313}
Now callers of Heap::CollectGarbage* functions need to
specify the reason as an enum value instead of a string.
Subsequent CL will add stats counter for GC reason.
BUG=
Review-Url: https://codereview.chromium.org/2310143002
Cr-Commit-Position: refs/heads/master@{#39239}
The test was calling OptimizeFunctionOnNextCall on a function before
ever executing it - crankshaft therefore didn't have any type info and
was generating a soft deoptimization bailout. Make sure we execute the
function before calling OptimizeFunctionOnNextCall to avoid this issue.
BUG=
Review-Url: https://codereview.chromium.org/2168603003
Cr-Commit-Position: refs/heads/master@{#38171}
So far TurboFan wasn't adding the deoptimization reasons for eager/soft
deoptimization exits that can be used by either the DevTools profiler or
the --trace-deopt flag. This adds basic support for deopt reasons on
Deoptimize, DeoptimizeIf and DeoptimizeUnless nodes and threads through
the reasons to the code generation.
Also moves the DeoptReason to it's own file (to resolve include cycles)
and drops unused reasons.
R=jarin@chromium.org
Review-Url: https://codereview.chromium.org/2161543002
Cr-Commit-Position: refs/heads/master@{#37823}
Isolate is not going to retain a CPU profiler.
The client will be creating an instance of profiler when needed.
Deprectate v8::Isolate::GetCpuProfiler()
BUG=v8:4789
Review-Url: https://codereview.chromium.org/2117343006
Cr-Commit-Position: refs/heads/master@{#37613}
We want to eventually move the profiling functionality out of V8 as library,
this patch exposes TickSample and its APIs in v8-profiler.h so that when
embedders use library, they can have more details.
Minor change: Rename tick-sample.[h|cc] to simulator-helper.[h|cc].
BUG=v8:4789
LOG=N
Review-Url: https://codereview.chromium.org/2105943002
Cr-Commit-Position: refs/heads/master@{#37564}
Currently there are two logic in Ticker, one is to try to request a
pre-allocated TickSample from CpuProfiler and then initialize it, and if the
request fails, it will initialize a local TickSample. The other is it will pass
an initialized TickSample to Profiler to log into v8.log.
This patch splits Ticker into two samplers, the first one remains in log.cc to
collect samples and pass to Profiler for logging, the second one will be called
by ProfilerEventsProcessor, and only use the circular queue only.
BUG=v8:4789
LOG=N
Review-Url: https://codereview.chromium.org/2108393002
Cr-Commit-Position: refs/heads/master@{#37506}
Currently CpuProfiler is a subclass of CodeEventListener, it listens code events
from Logger, constructs and stores CodeEventsContainer. This patch is part of
the effort to split the logic of CodeEventListener as ProfilerListener out of
the profiling functionality logic in CpuProfiler. A ProfilerListener will listen
to code events, construct code event to CodeEventsContainer and pass it to code
event handler.
The reason we refactor CpuProfiler is that eventually we want to move
CpuProfiler as part of sampler library and code event listener should stay
inside V8.
Main changes:
1. Refactored CpuProfiler into two parts, the CpuProfiler with profling
functionality and the ProfilerListener listening to code events from Logger.
2. Created CodeEventObserver and made CpuProfiler inherit from it.
ProfilerListener will have a list of observers and call CodeEventHandler once a
code event is created.
3. Moved code entry list from CodeEntry to ProfilerListener.
Minor changes:
1. Moved static code entry as part of CodeEntry.
2. Added ProfilerListener to Logger.
BUG=v8:4789
Committed: https://crrev.com/cb59fc1facc9b390e2c7544b4da56a4e0a9b3222
Review-Url: https://codereview.chromium.org/2053523003
Cr-Original-Commit-Position: refs/heads/master@{#37112}
Cr-Commit-Position: refs/heads/master@{#37195}
Reason for revert:
MIPS compilation error.
Original issue's description:
> Refactor CpuProfiler.
>
> Currently CpuProfiler is a subclass of CodeEventListener, it listens code events
> from Logger, constructs and stores CodeEventsContainer. This patch is part of
> the effort to split the logic of CodeEventListener as ProfilerListener out of
> the profiling functionality logic in CpuProfiler. A ProfilerListener will listen
> to code events, construct code event to CodeEventsContainer and pass it to code
> event handler.
>
> The reason we refactor CpuProfiler is that eventually we want to move
> CpuProfiler as part of sampler library and code event listener should stay
> inside V8.
>
> Main changes:
> 1. Refactored CpuProfiler into two parts, the CpuProfiler with profling
> functionality and the ProfilerListener listening to code events from Logger.
> 2. Created CodeEventObserver and made CpuProfiler inherit from it.
> ProfilerListener will have a list of observers and call CodeEventHandler once a
> code event is created.
> 3. Moved code entry list from CodeEntry to ProfilerListener.
>
> Minor changes:
> 1. Moved static code entry as part of CodeEntry.
> 2. Added ProfilerListener to Logger.
>
> BUG=v8:4789
>
> Committed: https://crrev.com/cb59fc1facc9b390e2c7544b4da56a4e0a9b3222
> Cr-Commit-Position: refs/heads/master@{#37112}
TBR=alph@chromium.org,jochen@chromium.org,yangguo@chromium.org
# Skipping CQ checks because original CL landed less than 1 days ago.
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=v8:4789
Review-Url: https://codereview.chromium.org/2079273003
Cr-Commit-Position: refs/heads/master@{#37113}
Currently CpuProfiler is a subclass of CodeEventListener, it listens code events
from Logger, constructs and stores CodeEventsContainer. This patch is part of
the effort to split the logic of CodeEventListener as ProfilerListener out of
the profiling functionality logic in CpuProfiler. A ProfilerListener will listen
to code events, construct code event to CodeEventsContainer and pass it to code
event handler.
The reason we refactor CpuProfiler is that eventually we want to move
CpuProfiler as part of sampler library and code event listener should stay
inside V8.
Main changes:
1. Refactored CpuProfiler into two parts, the CpuProfiler with profling
functionality and the ProfilerListener listening to code events from Logger.
2. Created CodeEventObserver and made CpuProfiler inherit from it.
ProfilerListener will have a list of observers and call CodeEventHandler once a
code event is created.
3. Moved code entry list from CodeEntry to ProfilerListener.
Minor changes:
1. Moved static code entry as part of CodeEntry.
2. Added ProfilerListener to Logger.
BUG=v8:4789
Review-Url: https://codereview.chromium.org/2053523003
Cr-Commit-Position: refs/heads/master@{#37112}
The patch introduces a dedicated dispatching class for JIT code events. It is
set as a helper on the isolate.
This allows classes across v8 to break their dependency on Logger and CpuProfiler.
These two became just regular clients of the dispatcher.
BUG=v8:4789
Review-Url: https://codereview.chromium.org/2061623002
Cr-Commit-Position: refs/heads/master@{#37005}
This patch does five things:
1. Extracts sampler as libsampler to provide sampling functionality support.
2. Makes SampleStack virtual so embedders can override the behaviour of sample collecting.
3. Removes sampler.[h|cc].
4. Moves sampling thread into log.cc as workaround to keep the --prof functionality.
5. Creates SamplerManager to manage the relationship between samplers and threads.
The reason we port hashmap.h is that in debug mode, STL containers are using
mutexes from a mutex pool, which may lead to deadlock when using asynchronously
signal handler.
Currently libsampler is used in V8 temporarily.
BUG=v8:4789
LOG=n
Committed: https://crrev.com/06cc9b7c176a6223971deaa9fbcafe1a05058c7b
Cr-Commit-Position: refs/heads/master@{#36527}
Review-Url: https://codereview.chromium.org/1922303002
Cr-Commit-Position: refs/heads/master@{#36532}
Reason for revert:
V8 Linux64 TSAN failure because ThreadSanitizer indicated data race.
Original issue's description:
> Create libsampler as V8 sampler library.
>
> This patch does five things:
>
> 1. Extracts sampler as libsampler to provide sampling functionality support.
> 2. Makes SampleStack virtual so embedders can override the behaviour of sample collecting.
> 3. Removes sampler.[h|cc].
> 4. Moves sampling thread into log.cc as workaround to keep the --prof functionality.
> 5. Creates SamplerManager to manage the relationship between samplers and threads.
>
> The reason we port hashmap.h is that in debug mode, STL containers are using
> mutexes from a mutex pool, which may lead to deadlock when using asynchronously
> signal handler.
>
> Currently libsampler is used in V8 temporarily.
>
> BUG=v8:4789
> LOG=n
>
> Committed: https://crrev.com/06cc9b7c176a6223971deaa9fbcafe1a05058c7b
> Cr-Commit-Position: refs/heads/master@{#36527}
TBR=jochen@chromium.org,alph@chromium.org,fmeawad@chromium.org,yangguo@chromium.org
# Skipping CQ checks because original CL landed less than 1 days ago.
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=v8:4789
Review-Url: https://codereview.chromium.org/2000323007
Cr-Commit-Position: refs/heads/master@{#36529}
This patch does five things:
1. Extracts sampler as libsampler to provide sampling functionality support.
2. Makes SampleStack virtual so embedders can override the behaviour of sample collecting.
3. Removes sampler.[h|cc].
4. Moves sampling thread into log.cc as workaround to keep the --prof functionality.
5. Creates SamplerManager to manage the relationship between samplers and threads.
The reason we port hashmap.h is that in debug mode, STL containers are using
mutexes from a mutex pool, which may lead to deadlock when using asynchronously
signal handler.
Currently libsampler is used in V8 temporarily.
BUG=v8:4789
LOG=n
Review-Url: https://codereview.chromium.org/1922303002
Cr-Commit-Position: refs/heads/master@{#36527}
This completely removes any potential for a side-channel between the
various compiler backends and the profiler. The CompilationInfo is no
longer passed.
R=yangguo@chromium.org
Review-Url: https://codereview.chromium.org/1970193002
Cr-Commit-Position: refs/heads/master@{#36230}
Add support to log source position offsets to the profiler. As part of
this change PositionsRecorder is split into two, with the subset needed
by log.cc moved into log.h and the remainder kept in assembler.h as
AssemblerPositionsRecorder. The interpreter's source position table
builder is updated to log positions when the profiler is active.
BUG=v8:4766
LOG=N
Review URL: https://codereview.chromium.org/1737043002
Cr-Commit-Position: refs/heads/master@{#34416}
Adds support for cpu profiler logging to the interpreter. Modifies the
the API to be passed AbstractCode objects instead of Code objects, and
adds extra functions to AbstractCode which is required by log.cc and
cpu-profiler.cc.
The main change in sampler.cc is to determine if a stack frame is an
interpreter stack frame, and if so, use the bytecode address as the pc
for that frame. This allows sampling of bytecode functions. This
requires adding support to SafeStackIterator to determine if a frame is
interpreted, which we do by checking the PC against pre-stored addresses
for the start and end of interpreter entry builtins.
Also removes CodeDeleteEvents which are dead code and haven't
been reported for some time.
Still to do is tracking source positions which will be done in a
followup CL.
BUG=v8:4766
LOG=N
Review URL: https://codereview.chromium.org/1728593002
Cr-Commit-Position: refs/heads/master@{#34321}
Recent flake happened bacause all the samples landed into native code.
The patch makes sure we collect enough JS samples.
BUG=v8:4751
LOG=N
Review URL: https://codereview.chromium.org/1695663002
Cr-Commit-Position: refs/heads/master@{#33953}
Do not rely on elapsed time to collect enough samples.
Use CollectSample API function instead.
Remove checks for extra functions present in a profile, as
there in fact can be lots of native support functions.
BUG=v8:2999
LOG=N
Review URL: https://codereview.chromium.org/1665303004
Cr-Commit-Position: refs/heads/master@{#33822}
There might be several ExternalCallbackScope's created
during the native callback. Remove the assert that is not
aligned with that.
Moreover this iterator must work for any kind of
stacks including corrupted ones.
BUG=v8:4705
LOG=N
Review URL: https://codereview.chromium.org/1663193003
Cr-Commit-Position: refs/heads/master@{#33751}
It allows embedder to inject a stack sample on demand.
BUG=chromium:579191
LOG=N
Review URL: https://codereview.chromium.org/1631043002
Cr-Commit-Position: refs/heads/master@{#33527}
Tick event processor should not stay in a tight loop
when there's nothing to do. It can go sleep until next sample event.
LOG=N
BUG=v8:3967
Review URL: https://codereview.chromium.org/1118533003
Cr-Commit-Position: refs/heads/master@{#28211}
Add a finalize incremental marking mode for CollectAllGarbage to finalize incremental marking when incremental marking is in progress, but we want a full gc at a given CollectAllGarbage call site.
Default mode for CollectAllGarbage is finalize incremental marking and perform a full GC.
BUG=
Review URL: https://codereview.chromium.org/1082973003
Cr-Commit-Position: refs/heads/master@{#27831}
