This reverts commit 5f28539599.
Reason for revert: presubmit failure
Original change's description:
> Move logging and diagnostics related source files
>
> This also introduces a COMMON_OWNERS file, which is derived from the
> current top-level OWNERS file. It is to be used for parts of the
> codebase that is not sensitive to domain-specific expertise.
>
> NOPRESUBMIT=true
> TBR=verwaest@chromium.org
>
> Bug: v8:9247
> Change-Id: I34a5eaa7cb1509a80d15094a2aceedd62665b17c
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1613987
> Reviewed-by: Yang Guo <yangguo@chromium.org>
> Reviewed-by: Michael Starzinger <mstarzinger@chromium.org>
> Reviewed-by: Ross McIlroy <rmcilroy@chromium.org>
> Commit-Queue: Yang Guo <yangguo@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#61600}
TBR=rmcilroy@chromium.org,yangguo@chromium.org,mstarzinger@chromium.org,verwaest@chromium.org
Change-Id: I3827c3af4fd63b18aa48c49617f318a01746e813
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: v8:9247
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1617247
Reviewed-by: Yang Guo <yangguo@chromium.org>
Commit-Queue: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61601}
This also introduces a COMMON_OWNERS file, which is derived from the
current top-level OWNERS file. It is to be used for parts of the
codebase that is not sensitive to domain-specific expertise.
NOPRESUBMIT=true
TBR=verwaest@chromium.org
Bug: v8:9247
Change-Id: I34a5eaa7cb1509a80d15094a2aceedd62665b17c
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1613987
Reviewed-by: Yang Guo <yangguo@chromium.org>
Reviewed-by: Michael Starzinger <mstarzinger@chromium.org>
Reviewed-by: Ross McIlroy <rmcilroy@chromium.org>
Commit-Queue: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61600}
Permit individual calls to CpuProfiler::StartSampling to provide their
own requested sampling interval, to be snapped to the profiler's
sampling interval. Use the greatest common divisor of all sample rates
to determine what sample rate should be chosen for the sampling thread,
and dispatch samples to attached profilers based on their requested
sample periodicity.
Change-Id: I0b076d09761d7176f31725e112578b68ab5da54c
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1484461
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Andrew Comminos <acomminos@fb.com>
Cr-Commit-Position: refs/heads/master@{#61548}
Previously we would attribute some frames of inline stacks to the wrong
line number.
For inlined frames, the source position table contains the line number
of the most-inlined frame (innermost). It's quite possible that this
function is within another script though, in which case the line number
will be wrong. Fix that here by taking the script from the
InliningStack, rather than assuming it is the same script as the
original code entry.
Bug: v8:7203, chromium:953309
Change-Id: Ia8795dbdd97d2f24f4bc685565d1e3a94e6067b3
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1403114
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Tobias Tebbi <tebbi@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61467}
Helps make configuring profilers more scalable as our number of
parameters grows.
Change-Id: I81263a30c221edaa3934a92eb000b71ddfbdea60
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1601585
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Andrew Comminos <acomminos@fb.com>
Cr-Commit-Position: refs/heads/master@{#61402}
To prevent OOMs for leaked CPU profilers, add the option to limit the
maximum number of samples that are included in a CPU profile.
Bug: chromium:956688
Change-Id: I119d0622e7d39c187f8e09e2d49dec91fd724ecb
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1588412
Commit-Queue: Andrew Comminos <acomminos@fb.com>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61352}
Our {Vector} template provides both {start} and {begin} methods. They
return exactly the same value. Since the {begin} method is needed for
iteration, and is also what standard containers provide, this CL
switches all uses of the {start} method to use {begin} instead.
Patchset 1 was auto-generated by using this clang AST matcher:
callExpr(
callee(
cxxMethodDecl(
hasName("start"),
ofClass(hasName("v8::internal::Vector")))
),
argumentCountIs(0))
Patchset 2 was created by running clang-format. Patchset 3 then
removes the now unused {Vector::start} method.
R=jkummerow@chromium.orgTBR=mstarzinger@chromium.org,yangguo@chromium.org,verwaest@chromium.org
Bug: v8:9183
Change-Id: Id9f01c92870872556e2bb3f6d5667463b0e3e5c6
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1587381
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Commit-Queue: Clemens Hammacher <clemensh@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61081}
Adds a new flag to CpuProfiler to control whether or not "debug" names
(potentially inferred from scope) are used for captured frames
associated with a SharedFunctionInfo instance.
Bug: v8:9135
Change-Id: Ia1db20e389f3d0beb60eb47798820fb11d501c88
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1583042
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#61015}
This reverts commit fa6ec3cb08.
Reason for revert: v8:9169, v8:9170
https://ci.chromium.org/p/v8/builders/ci/V8%20Linux/31457https://ci.chromium.org/p/v8/builders/ci/V8%20Linux64/31417https://ci.chromium.org/p/v8/builders/ci/V8%20Win32%20-%20debug/19919
Original change's description:
> [cpu-profiler] Split out debug mode for CPU profiler naming
>
> Adds a new flag to CpuProfiler to control whether or not "debug" names
> (potentially inferred from scope) are used for captured frames
> associated with a SharedFunctionInfo instance.
>
> Bug: v8:9135
> Change-Id: I104f3246431dc6336de4e4688c0d98c86e0bb776
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1566169
> Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
> Reviewed-by: Alexei Filippov <alph@chromium.org>
> Reviewed-by: Peter Marshall <petermarshall@chromium.org>
> Commit-Queue: Peter Marshall <petermarshall@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#60972}
TBR=ulan@chromium.org,alph@chromium.org,yangguo@chromium.org,petermarshall@chromium.org,acomminos@fb.com
Change-Id: I573194b5affd31fd0748b9ef3c45052e8ab420f5
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: v8:9135
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1581639
Reviewed-by: Sigurd Schneider <sigurds@chromium.org>
Commit-Queue: Sigurd Schneider <sigurds@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60973}
Adds a new flag to CpuProfiler to control whether or not "debug" names
(potentially inferred from scope) are used for captured frames
associated with a SharedFunctionInfo instance.
Bug: v8:9135
Change-Id: I104f3246431dc6336de4e4688c0d98c86e0bb776
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1566169
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60972}
Adds CpuProfiler::SetUsePreciseSampling, which provides a hint whether
to sacrifice CPU cycles to reduce the level of sampling interval
variance. On Windows, this controls whether or not busy waiting is
performed for sample rates < 100ms. Defaults to enabled (old behaviour).
Bug: v8:3967
Change-Id: Iee84c3ae8132541c78b1f78bf294ec7c718bb19b
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1510577
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60866}
Adds the notion of a "source type" to CpuProfileNode instances, hinting
at the underlying source of the function or state that resulted in the
generation of the node.
Bug: v8:9001
Change-Id: Ie14c54d41b99eb02f54b423fa5d939e9d7f63785
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1510576
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Ulan Degenbaev <ulan@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60590}
Previously when lazy source positions were enabled, source positions
were immediately collected whenever an exception was thrown for every
frame in the stack trace.
This change makes source position collection trigger only when the
source positions of a stack frame are actually accessed with the
exception of the top frame which is still eagerly collected for now.
Additionally when stack overflows occur during source position
collection, the bytecode is marked with exception in the
source_position_table field so it can be distinguished from the case
where source position collection has never been attempted (undefined)
or is not desired because the bytecode is for natives
(empty_byte_array).
Bug: v8:8510
Change-Id: If7ee68edbacc9e2adadf00fe5ec822a8dbe1c79a
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1520721
Reviewed-by: Jaroslav Sevcik <jarin@chromium.org>
Reviewed-by: Jakob Gruber <jgruber@chromium.org>
Reviewed-by: Ross McIlroy <rmcilroy@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Dan Elphick <delphick@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60504}
Consumers can use this to derive the full stack from sampled leaf nodes
without having to flatten the tree.
Bug: v8:8999
Change-Id: I42c638dd2c757837b0c03514c204be0182653291
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1525877
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60309}
Enable cross-origin frame filtering by exposing this bit from
ScriptOriginOptions.
Bug: v8:8956
Change-Id: I109eec9db8b3d42d68d32abc5edd437b1c91a9b8
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/1493294
Commit-Queue: Yang Guo <yangguo@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#60205}
I missed this one in my previous CL.
R=jarin@chromium.org
Change-Id: Ie4b912ee7e3367da48c0d4b092ad09e3f81de788
Reviewed-on: https://chromium-review.googlesource.com/c/1477677
Reviewed-by: Jaroslav Sevcik <jarin@chromium.org>
Commit-Queue: Georg Neis <neis@chromium.org>
Cr-Commit-Position: refs/heads/master@{#59743}
Fixes cctest/test-cpu-profiler/DetailedSourcePositionAPI by ensuring
that source positions are available when starting an optimize job when
NeedsDetailedOptimizedCodeLineInfo is set. Also collects source
positions when inlining functions and adds a new test for this.
Bug: v8:8510
Change-Id: I9d84e37f3c8b638db080f6ec4b6633cdd7e3ee2f
Reviewed-on: https://chromium-review.googlesource.com/c/1472634
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Michael Starzinger <mstarzinger@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Reviewed-by: Ross McIlroy <rmcilroy@chromium.org>
Commit-Queue: Dan Elphick <delphick@chromium.org>
Cr-Commit-Position: refs/heads/master@{#59685}
Signal a condition variable when profiling thread shutdown should occur,
waking up a profiling thread that's currently waiting for the next tick.
Mitigates the case where if a high sample interval is specified (e.g.
60s), the main thread is blocked until the next sample occurs due to a
Sleep() call.
Bug: v8:8843
Change-Id: Ied6b0bfb5c47a072ade17870911b961f5091f613
Reviewed-on: https://chromium-review.googlesource.com/c/1470953
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#59648}
Sets an atomic field on each sampler when it requests a sample, to be
checked when the SIGPROF handler is executed. A counter is not used
since signals may be coalesced.
Prior to this change, all samplers attached to an isolate received
samples when other samplers sent SIGPROF to the VM thread. This change
alters the behaviour of different CpuProfiler instances on the same
isolate to be in line with the Windows / Fuchsia behaviour.
Bug: v8:8835
Change-Id: I0caaa845b596efc9d8b1cd7716c067d9a6359c57
Reviewed-on: https://chromium-review.googlesource.com/c/1468941
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#59545}
The line number is associated with each sample along with pointer
to the ProfileNode and timeDelta. Once collected line numbers are
streamed as an array of integers in "ProfileChunk" trace events.
If all the line numbers are zero, the array may be omitted. Otherwise
the array length matches length of samples and timeDeltas arrays.
BUG=chromium:925089
Change-Id: I1ef5cd1b208b03bb127f4d17b1efa74c01959542
Reviewed-on: https://chromium-review.googlesource.com/c/1459739
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#59514}
Fixes a segfault that occurs when v8::CpuProfilers are restarted caused
by the reuse of a stale CodeEventObserver.
Bug: chromium:929928
Change-Id: I5d5f7eaf5cd903910130cdb0cfec8c3fd6608edd
Reviewed-on: https://chromium-review.googlesource.com/c/1459740
Reviewed-by: Alexei Filippov <alph@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#59506}
Everything was including log.h through heap-inl.h, so remove that
include by moving the one user into heap.cc, and then fix all the
include errors.
This reduces the log.h include ball from ~550 to ~100.
Change-Id: I6d09bc2f365b48645fcfdc695a68ea12539a745d
Reviewed-on: https://chromium-review.googlesource.com/c/1424198
Commit-Queue: Georg Neis <neis@chromium.org>
Reviewed-by: Georg Neis <neis@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: Jakob Gruber <jgruber@chromium.org>
Reviewed-by: Michael Starzinger <mstarzinger@chromium.org>
Cr-Commit-Position: refs/heads/master@{#58981}
After moving to its own header, this CL cleans up some parts of the
interface. It fixes names and const-declarations of simple accessors,
and adds a named constructor to make it explicit that an EnumSet should
be constructed from an integral value.
Also refactor the use in cctest.h to have less statically declared
constants. Instead, just create the set of extensions in the individual
tests.
R=titzer@chromium.org
Bug: v8:8562
Change-Id: I6178d1aba25afa1d7f54c29ccf81505c165e7cd3
Reviewed-on: https://chromium-review.googlesource.com/c/1409366
Commit-Queue: Clemens Hammacher <clemensh@chromium.org>
Reviewed-by: Ben Titzer <titzer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#58862}
These flakes can't be reproduced locally so we need more information
when they fail. Add some logging so that we can figure out why they
are breaking.
Bug: v8:8649, v8:8648
Change-Id: I2fb1384bb7592c6fc68c08952505e79329f00bec
Reviewed-on: https://chromium-review.googlesource.com/c/1400418
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#58641}
Previously we stored the source position table, which stored a mapping
of pc offsets to line numbers, and the inline_locations, which stored a
mapping of pc offsets to stacks of {CodeEntry, line_number} pairs. This
was slightly wasteful because we had two different tables which were
both keyed on the pc offset and contained some overlapping information.
This CL combines the two tables in a way. The source position table now
maps a pc offset to a pair of {line_number, inlining_id}. If the
inlining_id is valid, then it can be used to look up the inlining stack
which is stored in inline_locations, but is now keyed by inlining_id
rather than pc offset. This also has the nice effect of de-duplicating
inline stacks which we previously duplicated.
The new structure is similar to how this data is stored by the compiler,
except that we convert 'source positions' (char offset in a file) into
line numbers as we go, because we only care about attributing ticks to
a given line.
Also remove the helper RecordInliningInfo() as this is only actually
used to add inline stacks by one caller (where it is now inlined). The
other callers would always bail out or are only called from
test-cpu-profiler.
Remove AddInlineStack and replace it with SetInlineStacks which adds all
of the stacks at once. We need to do it this way because the source pos
table is passed into the constructor of CodeEntry, so we need to create
it before the CodeEntry, but the inline stacks are not (they are part of
rare_data which is not always present), so we need to add them after
construction. Given that we calculate both the source pos table and the
inline stacks before construction, it's just easier to add them all at
once.
Also add a print() method to CodeEntry to make future debugging easier
as I'm constantly rewriting this locally.
Bug: v8:8575, v8:7719, v8:7203
Change-Id: I39324d6ea13d116d5da5d0a0d243cae76a749c79
Reviewed-on: https://chromium-review.googlesource.com/c/1392195
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Tobias Tebbi <tebbi@chromium.org>
Cr-Commit-Position: refs/heads/master@{#58554}
Currently in both kCallerLineNumbers and kLeafNodeLineNumbers modes, we
correctly capture inline stacks. In leaf number mode, this is simple as
we simply add the path onto the existing tree. For caller line numbers
mode this is more complex, because each path through various inlined
function should be represented in the tree, even when there are
multiple callsites to the same function inlined.
Currently we don't correctly show line numbers for inlined functions.
We do actually have this information though, which is generated by
turbofan and stored in the source_position_table data structure on the
code object.
This also changes the behavior of the SourcePositionTable class. A
problem we uncovered is that the PC that the sampler provides for every
frame except the leaf is the return address of the calling frame. This
address is *after* the call has already happened. It can be attributed
to the next line of the function, rather than the calling line, which
is wrong. We fix that here by using lower_bound in GetSourceLineNumber.
The same problem happens in GetInlineStack - the PC of the caller is
actually the instruction after the call. The information turbofan
generates assumes that the instruction after the call is not part of
the call (fair enough). To fix this we do the same thing as above - use
lower_bound and then iterate back by one.
TBR=alph@chromium.org
Bug: v8:8575, v8:8606
Change-Id: Idc4bd4bdc8fb70b70ecc1a77a1e3744a86f83483
Reviewed-on: https://chromium-review.googlesource.com/c/1374290
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Tobias Tebbi <tebbi@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#58545}
Do less work in MultipleProfilers. Reduces runtime from ~8 mins to ~40
seconds.
Bug: v8:8474
Change-Id: I72b3266941ce40c8d064deaf00fb06f8d9fa8a70
Reviewed-on: https://chromium-review.googlesource.com/c/1341956
Reviewed-by: Camillo Bruni <cbruni@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#57613}
This test is only flaky because the js code being profiled causes a
'fast-c-call' which is a call from JS to C without an exit frame.
The profiler stumbles on these and reads the stack of C++ frames when
it shouldn't, causing ASAN errors. This is not actually related to
the multiple isolates, so I'm changing the test to profile different
JS code that does not cause these types of calls. There is already a
test for fast-c-calls - NativeFrameStackTrace (which currently fails).
Bug: v8:8464
Change-Id: I32818f0894e5680cf5a39779a2779eda36dfe9f1
Reviewed-on: https://chromium-review.googlesource.com/c/1337571
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#57547}
This allows Node.js to enable detailed source positions for optimized code
early on, without having to pass a flag string.
R=petermarshall@chromium.org
Change-Id: Ie74ea41f600cf6e31acbe802116df4976ccf1c75
Reviewed-on: https://chromium-review.googlesource.com/c/1319757
Commit-Queue: Yang Guo <yangguo@chromium.org>
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#57380}
We don't have any tests which run multiple isolates concurrently and
starts a profiler in each of them. This test is a basic starting point
so that we can check for flakiness caused by races or interrupts.
The profiling mechanisms should be totally separate for two isolates,
so this should (theoretically) not cause any problems.
A use case for multiple isolates is for workers or in Node via cloud
functions, so we should get some more coverage here.
Change-Id: I0ca6d1296bc7bae7238c51b4487259d09e38d690
Reviewed-on: https://chromium-review.googlesource.com/c/1309823
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#57207}
This reverts commit 5847574eb9.
Reason for revert: Break mjsunit tests in Lite mode. You'll have to find a solution for tests using assertOptimized().
Original change's description:
> [Lite] Disable optimization for Lite mode.
>
> BUG=v8:8293
>
> Change-Id: I6b2e02420ab69fb1d2e24945d48b08d2bc24b0d0
> Reviewed-on: https://chromium-review.googlesource.com/c/1280526
> Commit-Queue: Ross McIlroy <rmcilroy@chromium.org>
> Reviewed-by: Dan Elphick <delphick@chromium.org>
> Cr-Commit-Position: refs/heads/master@{#56795}
TBR=rmcilroy@chromium.org,delphick@chromium.org
Change-Id: I09f6c17cc325f50560329c46f06ad847f0bb021d
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: v8:8293
Reviewed-on: https://chromium-review.googlesource.com/c/1290111
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Commit-Queue: Jakob Kummerow <jkummerow@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56796}
Currently ProfilerListener channels the code events to Processor
via CpuProfiler - we don't need this indirection and can just hook
it up directly. This also makes it easier to test because we don't need
a CpuProfiler object just to test the Processor.
Drive-by cleanup:
- Remove NUMBER_OF_TYPES from CodeEventRecord as it is not used.
- Remove Isolate* parameter from AddDeoptStack and AddCurrentStack as
a Processor object is only ever for one Isolate. Store the Isolate*
on the ProfilerEventsProcessor object itself.
- Remove the default case from switch in ProcessCodeEvent().
Bug: v8:5193
Change-Id: I26c1a46b0eec34b5248b707d1997c3a9409a9604
Reviewed-on: https://chromium-review.googlesource.com/c/1286341
Reviewed-by: Yang Guo <yangguo@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56740}
This is preparation to allow for a non-sampling events processor which
receives ticks from a source not driven by a timer. This will allow us
to have more deterministic testing of the CPU profiler.
It also allows different implementations for a wall time and CPU time
triggered sampler.
Change-Id: I2e9db9580ec70f05094e59c2c1e5efc28c8f7da8
Reviewed-on: https://chromium-review.googlesource.com/c/1280436
Reviewed-by: Yang Guo <yangguo@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#56717}
Previously we used the start address of the AbstractCode object. This
doesn't make sense for off-heap builtins, where the code isn't contained
in the object itself. It also hides other potential problems - sometimes
the sample.pc is inside the AbstractCode object header - this is
never valid.
There were a few changes necessary to make this happen:
- Change the interface of CodeMoveEvent. Now 'to' and 'from' are both
AbstractCode objects, which is nice because many users were taking
'to' and adding the header offset to it to try and find the
instruction start address. This isn't valid for off-heap builtins.
- Fix a bug in CodeMap::MoveCode where we didn't update the CodeEntry
object to reflect the new instruction_start.
- Rename the 'start' field in all of the CodeEventRecord sub-classes
to make it clear that this is the address of the first instruction.
- Fix the confusion in RecordTickSample between 'tos' and 'pc' which
caused pc_offset to be calculated incorrectly.
Bug: v8:7983
Change-Id: I3e9dddf74e4b2e96a5f031d216ef7008d6f184d1
Reviewed-on: https://chromium-review.googlesource.com/1148457
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Jakob Gruber <jgruber@chromium.org>
Reviewed-by: Michael Lippautz <mlippautz@chromium.org>
Cr-Commit-Position: refs/heads/master@{#54749}
The current profiling mode (called kLeafNodeLineNumbers in this CL)
produces a tree, with each node representing a stack frame that is seen
in one or more samples taken during profiling. These nodes refer to a
particular function in a stack trace, but not to a particular line or
callsite within that function.
This CL adds a new more (called kCallerLineNumbers) which produces a
different profile tree, where each stack trace seen during profiling,
including the line number, has a unique path in the tree.
The profile tree was previously keyed on CodeEntry*. Now it is keyed on
the pair of CodeEntry* and line_number, meaning it has distinct nodes
for those combinations which exist, and each distinct stack trace that
was sampled is represented in the tree.
For optimized code where we have inline frames, there are no line
numbers for the inline frames in the stack trace, causing duplicate
branches in the tree with kNoLineNumberInfo as the reported line number.
This will be addressed in follow-ups.
Bug: v8:7018
Cq-Include-Trybots: luci.chromium.try:linux_chromium_rel_ng
Change-Id: I512e221508f5b50ec028306d212263b514a9fb24
Reviewed-on: https://chromium-review.googlesource.com/1013493
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Yang Guo <yangguo@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53298}
This map is often quite small and holds small items (ints) so wastes
quite a bit of overhead in the backing tree representation.
This CL changes the std::map to a sorted vector of pairs. This reduces
the size significantly (2.13 MiB -> 598 KiB on the node server example).
Bug: v8:7719
Change-Id: Ic829693f007732ae145fae02850a1ed913cd941e
Reviewed-on: https://chromium-review.googlesource.com/1064233
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Reviewed-by: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53278}
ProfilerListener which holds CodeEntries has been moved from Logger to
CpuProfiler. This way we can clear entries when all the profiles
produced by a particular CpuProfiler are deleted.
BUG=v8:7719
Change-Id: I31d47dc7da44648c8fb8e87b47e2e6260d3dc5c3
Reviewed-on: https://chromium-review.googlesource.com/1043050
Reviewed-by: Peter Marshall <petermarshall@chromium.org>
Commit-Queue: Alexei Filippov <alph@chromium.org>
Cr-Commit-Position: refs/heads/master@{#53004}
When running this test locally, the OptimizeFunctionOnNextCall
call fails, because the line above has no semicolon, and automatic
insertion doesn't help, probably because of the % sign. The test still
runs, but the first call after level1() fails, meaning the inlining
does not happen.
Change-Id: Icd2d08e676ea3cade63d4e12277748a447e410fc
Reviewed-on: https://chromium-review.googlesource.com/1030210
Reviewed-by: Camillo Bruni <cbruni@chromium.org>
Commit-Queue: Peter Marshall <petermarshall@chromium.org>
Cr-Commit-Position: refs/heads/master@{#52808}
