Right now we only kind of sort of trace GC STW events. We emit events
around mark termination, but those start well after stopping the world
and end before starting it again, and we don't emit any events for
sweep termination.
Fix this by generalizing EvGCScanStart/EvGCScanDone. These were
already re-purposed to indicate mark termination (despite the names).
This commit renames them to EvGCSTWStart/EvGCSTWDone, adds an argument
to indicate the STW reason, and shuffles the runtime to generate them
right before stopping the world and right after starting the world,
respectively.
These events will make it possible to generate precise minimum mutator
utilization (MMU) graphs and could be useful in detecting
non-preemptible goroutines (e.g., #20792).
Change-Id: If95783f370781d8ef66addd94886028103a7c26f
Reviewed-on: https://go-review.googlesource.com/55411
Reviewed-by: Rick Hudson <rlh@golang.org>
Generated with
github.com/catapult/tracing/bin/vulcanize_trace_viewer
catapult @ ab4d571fa
Renamed trace_viewer_lean.html to trace_viewer_full.html
to make it clear we are using the full version of trace viewer
(waiting for https://github.com/catapult-project/catapult/issues/2247
to be fixed).
Update #15302
Change-Id: Ice808bb27ab79a1dec9fc863e0c5a761027ebfbe
Reviewed-on: https://go-review.googlesource.com/58750
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
All of these are uints of different sizes, so checking >= 0 or < 0 are
effectively no-ops.
Found with staticcheck.
Change-Id: I16ac900eb7007bc8f9018b302136d42e483a4180
Reviewed-on: https://go-review.googlesource.com/56950
Reviewed-by: Matt Layher <mdlayher@gmail.com>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Run-TryBot: Matt Layher <mdlayher@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Currently all trace slices get shifted to start at time 0. This makes
it very difficult to find specific points in time unless they fall in
the first slice.
For example, right now when you click "View trace
(6.005646218s-8.155419698s)" on the trace tool's main page, the trace
view puts the first event in that slice at time 0. If you're looking
for something that happened at time 7s, you have to look at time
0.9943537s in the trace view. And if you want to subtract times taken
from different slices, you have to figure out what those time really
correspond to.
Fix this by telling the trace viewer not to shift the times when it
imports the trace. In the above example, this makes the view of that
second trace slice start at time 6.005646218s, so you don't have to do
any gymnastics to find or calculate times in later slices.
Change-Id: I04e0afda60f5573fdd8ad96238c24013297ef263
Reviewed-on: https://go-review.googlesource.com/54633
Reviewed-by: Hyang-Ah Hana Kim <hyangah@gmail.com>
This updates the HTML served for the trace viewer to follow the latest
revision of the example from the upstream tracing project.
The main thing this adds is CSS for the trace viewer (which was
actually in the example at the originally referenced revision, so I'm
not sure why it got dropped). In particular, this expands the trace
viewer to use the entire browser client area, which fixes several
problems with the current page:
1. The details pane gets cut off at a strange place and can get a
scroll bar even if there's plenty of room below it on the page. This
fixes the bottom of the details pane to the bottom of the window.
2. If the track view is very tall (lots of procs), there's no way to
view the top tracks and the details pane at the same time. This fixes
this problem by limiting the height of the track view to something
less than the height of the window so it gets a scroll bar of its own
if necessary.
3. Dragging the divider between the track pane and the details pane
actually moves the bottom of the details pane without moving the
divider. Fixing the height of the trace viewer fixes this problem.
Change-Id: Ia811e72a7413417ca21c45e932c9db2724974633
Reviewed-on: https://go-review.googlesource.com/54632
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Hyang-Ah Hana Kim <hyangah@gmail.com>
This displays the swept and reclaimed bytes for sweep events in the
lower panel of the trace viewer.
Change-Id: If1665a1c02bbc47700e0d9f515e574f013f3f285
Reviewed-on: https://go-review.googlesource.com/40812
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Hyang-Ah Hana Kim <hyangah@gmail.com>
There's no guarantee that all in-progress mark assists will finish
before the trace does. Don't crash if that happens.
I haven't added a test because there's quite a bit of ceremony involved
and the bug is fairly straightforward.
Change-Id: Ia1369a8e2260fc6a328ad204a1eab1063d2e2c90
Reviewed-on: https://go-review.googlesource.com/37540
Reviewed-by: Austin Clements <austin@google.com>
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
During the mark phase of garbage collection, goroutines that allocate
may be recruited to assist. This change creates trace events for mark
assists and displays them similarly to sweep assists in the trace
viewer.
Mark assists are different than sweeps in that they can be preempted, so
displaying them in the trace viewer is a little tricky -- we may need to
synthesize multiple slices for one mark assist. This could have been
done in the parser instead, but I thought it might be preferable to keep
the parser as true to the event stream as possible.
Change-Id: I381dcb1027a187a354b1858537851fa68a620ea7
Reviewed-on: https://go-review.googlesource.com/36015
Run-TryBot: Heschi Kreinick <heschi@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
Reviewed-by: Hyang-Ah Hana Kim <hyangah@gmail.com>
Currently, trace processing interleaves state/statistics updates and
emitting trace viewer objects. As a result, if events are being
filtered, either by time or by goroutines, we'll miss those
state/statistics updates. At best, this leads to bad statistics;
however, since we're now strictly checking G state transitions, it
usually leads to a failure to process the trace if there is any
filtering.
Fix this by separating state updates from emitting trace object. State
updates are done before filtering, so we always have correct state
information and statistics. Trace objects are only emitted if we pass
the filter. To determine when we need to emit trace counters, rather
than duplicating the knowledge of which events might modify
statistics, we keep track of the previously emitted counters and emit
a trace counter object whenever these have changed.
Fixes#17719.
Change-Id: Ic66e3ddaef60d1acaaf2ff4c62baa5352799cf99
Reviewed-on: https://go-review.googlesource.com/32810
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Currently when a goroutine blocks on a GC assist, it emits a generic
EvGoBlock event. Since assist blocking events and, in particular, the
length of the blocked assist queue, are important for diagnosing GC
behavior, this commit adds a new EvGoBlockGC event for blocking on a
GC assist. The trace viewer uses this event to report a "waiting on
GC" count in the "Goroutines" row. This makes sense because, unlike
other blocked goroutines, these goroutines do have work to do, so
being blocked on a GC assist is quite similar to being in the
"runnable" state, which we also report in the trace viewer.
Change-Id: Ic21a326992606b121ea3d3d00110d8d1fdc7a5ef
Reviewed-on: https://go-review.googlesource.com/30704
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Currently the trace tool tracks an overall counts of goroutine states,
but not the states of any individual goroutine. We're about to add
more sophisticated blocked-state tracking, so add this tracking and
base the state counts off the tracked goroutine states.
Change-Id: I943ed61782436cf9540f4ee26c5561715c5b4a1d
Reviewed-on: https://go-review.googlesource.com/30703
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Currently mark workers are shown in the trace as regular goroutines
labeled "runtime.gcBgMarkWorker". That's somewhat unhelpful to an end
user because of the opaque label and particularly unhelpful to runtime
developers because it doesn't distinguish the different types of mark
workers.
Fix this by introducing a variant of the GoStart event called
GoStartLabel that lets the runtime indicate a label for a goroutine
execution span and using this to label mark worker executions as "GC
(<mode>)" in the trace viewer.
Since this bumps the trace version to 1.8, we also add test data for
1.7 traces.
Change-Id: Id7b9c0536508430c661ffb9e40e436f3901ca121
Reviewed-on: https://go-review.googlesource.com/30702
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
When starting tracing, EvGoCreate events are added for existing
goroutines that may have been blocking in syscall. EvGoCreate
increments the runnable goroutine count. This change makes the
following EvGoInSyscall event decrement the runnable goroutine count
because we now know that goroutine is in syscall, and not runnable.
Made generateTrace return an error, at any given time, the number
of runnable/running/insyscall goroutines becomes non-negative.
Added a basic test that checks the number of runnable/running
goroutines don't include the goroutines in syscall - the test failed
before this change.
Change-Id: Ib732c382e7bd17158a437576f9d589ab89097ce6
Reviewed-on: https://go-review.googlesource.com/25552
Run-TryBot: Hyang-Ah Hana Kim <hyangah@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Currently these are labeled "MARK", which was accurate in the STW
collector, but these really indicate mark termination now, since
marking happens for the full duration of the concurrent GC. Re-label
them as "MARK TERMINATION" to clarify this.
Change-Id: Ie98bd961195acde49598b4fa3f9e7d90d757c0a6
Reviewed-on: https://go-review.googlesource.com/30018
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Currently, the process-wide GC state is attributed to the P that
happened to perform the allocation that exceeded the GC trigger. This
is pretty arbitrary and makes it hard to see when GC is running since
the GC spans are intermingled with a lot of other trace noise.
The current display is particularly confusing because it creates three
sub-rows in the P row that can overlap each other. Usually a P has
just two sub-rows: one showing the current G and another showing that
G's activity. However, because GC is attributed to a proc, it winds up
as a third row that neither subsumes nor is subsumed by any other row.
This in turn screws up the trace's layout and results in overlapping
events.
Fix these problems by creating a new dedicated row like the existing
"Network" and "Timer" rows and displaying process-wide GC events in
this row. Mark termination and sweep events still appear in their
respective P rows because these are meaningfully attributed.
Change-Id: Ie1a1c6cf8c446e4b043f10f3968f91ff1b546d15
Reviewed-on: https://go-review.googlesource.com/30017
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Trace viewer cannot handle traces larger than 256MB (limit on js string size):
https://github.com/catapult-project/catapult/issues/627
And even that is problematic (chrome hangs and crashes).
Split large traces into 100MB parts. Somewhat clumsy, but I don't see any other
solution (other than rewriting trace viewer). At least it works reliably now.
Fixes#15482
Change-Id: I993b5f43d22072c6f5bd041ab5888ce176f272b2
Reviewed-on: https://go-review.googlesource.com/22731
Reviewed-by: Hyang-Ah Hana Kim <hyangah@gmail.com>
This is a subset of https://golang.org/cl/20022 with only the copyright
header lines, so the next CL will be smaller and more reviewable.
Go policy has been single space after periods in comments for some time.
The copyright header template at:
https://golang.org/doc/contribute.html#copyright
also uses a single space.
Make them all consistent.
Change-Id: Icc26c6b8495c3820da6b171ca96a74701b4a01b0
Reviewed-on: https://go-review.googlesource.com/20111
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Use runtime.GOROOT instead of os.Getenv("GOROOT") to reference
trace-viewer html file. GOROOT env var is not necessary set,
runtime.GOROOT has a default value for such case.
Change-Id: I906a720f6822915bd9575756e6cbf6d622857c2b
Reviewed-on: https://go-review.googlesource.com/13593
Reviewed-by: Russ Cox <rsc@golang.org>
Integrate the latest trace-viewer changes.
It now handles nanoseconds without any issues (thanks to @egonelbre!).
So change timestamps from microseconds to nanoseconds.
Change-Id: I010f27effde7e80c9992e6f276f6912354d27df4
Reviewed-on: https://go-review.googlesource.com/11244
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Reviewed-by: Egon Elbre <egonelbre@gmail.com>
If you have more than 10 procs, then currently they are sorted alphabetically as
0, 10, 11, ..., 19, 2, 20, ...
Assign explicit order to procs so that they are sorted numerically.
Change-Id: I6d978d2cd439aa2fcbcf147842a643f9073eef75
Reviewed-on: https://go-review.googlesource.com/11750
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
In generateTrace we check that event timestamp is within the interesting range.
Then later in traceContext.time we double check event time.
However, for some events (e.g. emitSlice) we convert time of ev.Link (slice end) rather than ev itself (slice begin).
Slice end can be outside of the interesting time range, and so traceContext.time crashes.
Remove the check in traceContext.time, check in generateTrace loop is sufficient.
Change-Id: If94e93b5653c5816c0a8dcdd920f15df97616835
Reviewed-on: https://go-review.googlesource.com/11100
Reviewed-by: Andrew Gerrand <adg@golang.org>
Update to tip to fix#11003 (not possible to select events in chromium).
Fixed#11003
Change-Id: Ibba5d39ca809cfd5cb79c9e6d152b00899d49e08
Reviewed-on: https://go-review.googlesource.com/11062
Reviewed-by: Andrew Gerrand <adg@golang.org>
This allows to test goroutine analysis code in runtime/pprof tests.
Also fix a nil-deref crash in goroutine analysis code that happens on runtime/pprof tests.
Change-Id: Id7884aa29f7fe4a8d7042482a86fe434e030461e
Reviewed-on: https://go-review.googlesource.com/7301
Run-TryBot: Dmitry Vyukov <dvyukov@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Andrew Gerrand <adg@golang.org>
Augment ProcStart events with OS thread id.
This helps in scheduler locality analysis.
Change-Id: I93fea75d3072cf68de66110d0b59d07101badcb5
Reviewed-on: https://go-review.googlesource.com/7302
Reviewed-by: Keith Randall <khr@golang.org>
Stip uninteresting bottom and top frames from trace stacks.
This makes both binary and json trace files smaller,
and also makes stacks shorter and more readable in the viewer.
Change-Id: Ib9c80ccc280504f0e235f867f53f1d2652c41583
Reviewed-on: https://go-review.googlesource.com/5523
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Dmitry Vyukov <dvyukov@google.com>
Trace command allows to visualize and analyze traces.
Run as:
$ go tool trace binary trace.file
The commands opens web browser with the main page,
which contains links for trace visualization,
blocking profiler, network IO profiler and per-goroutine
traces.
Also move trace parser from runtime/pprof/trace_parser_test.go
to internal/trace/parser.go, so that it can be shared between
tests and the command.
Change-Id: Ic97ed59ad6e4c7e1dc9eca5e979701a2b4aed7cf
Reviewed-on: https://go-review.googlesource.com/3601
Reviewed-by: Andrew Gerrand <adg@golang.org>
