runtime/internal/sys will hold system-, architecture- and config-
specific constants.
Updates #11647
Change-Id: I6db29c312556087a42e8d2bdd9af40d157c56b54
Reviewed-on: https://go-review.googlesource.com/16817
Reviewed-by: Russ Cox <rsc@golang.org>
Abandon (but still support) the old numbering system.
GOTRACEBACK=none is old 0
GOTRACEBACK=single is the new behavior
GOTRACEBACK=all is old 1
GOTRACEBACK=system is old 2
GOTRACEBACK=crash is unchanged
See doc comment change in runtime1.go for details.
Filed #13107 to decide whether to change default back to GOTRACEBACK=all for Go 1.6 release.
If you run into programs where printing only the current goroutine omits
needed information, please add details in a comment on that issue.
Fixes#12366.
Change-Id: I82ca8b99b5d86dceb3f7102d38d2659d45dbe0db
Reviewed-on: https://go-review.googlesource.com/16512
Reviewed-by: Austin Clements <austin@google.com>
Shared libraries on ppc64le will require a larger minimum stack frame (because
the ABI mandates that the TOC pointer is available at 24(R1)). So to prepare
for this, make a constant for the fixed part of a stack and use that where
necessary.
Change-Id: I447949f4d725003bb82e7d2cf7991c1bca5aa887
Reviewed-on: https://go-review.googlesource.com/15523
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Run-TryBot: Michael Hudson-Doyle <michael.hudson@canonical.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Currently the runtime can install stack barriers in any frame.
However, the frame of cgocallback_gofunc is special: it's the one
function that switches from a regular G stack to the system stack on
return. Hence, the return PC slot in its frame on the G stack is
actually used to save getg().sched.pc (so tracebacks appear to unwind
to the last Go function running on that G), and not as an actual
return PC for cgocallback_gofunc.
Because of this, if we install a stack barrier in cgocallback_gofunc's
return PC slot, when cgocallback_gofunc does return, it will move the
stack barrier stub PC in to getg().sched.pc and switch back to the
system stack. The rest of the runtime doesn't know how to deal with a
stack barrier stub in sched.pc: nothing knows how to match it up with
the G's stack barrier array and, when the runtime removes stack
barriers, it doesn't know to undo the one in sched.pc. Hence, if the C
code later returns back in to Go code, it will attempt to return
through the stack barrier saved in sched.pc, which may no longer have
correct unwinding information.
Fix this by blacklisting cgocallback_gofunc's frame so the runtime
won't install a stack barrier in it's return PC slot.
Fixes#12238.
Change-Id: I46aa2155df2fd050dd50de3434b62987dc4947b8
Reviewed-on: https://go-review.googlesource.com/13944
Reviewed-by: Russ Cox <rsc@golang.org>
Right now we find out implicitly if stack barriers are in place,
or defers. This change makes sure we find out about short
unwinds always.
Change-Id: Ibdde1ba9c79eb792660dcb7aa6f186e4e4d559b3
Reviewed-on: https://go-review.googlesource.com/13966
Reviewed-by: Austin Clements <austin@google.com>
This commit implements stack barriers to minimize the amount of
stack re-scanning that must be done during mark termination.
Currently the GC scans stacks of active goroutines twice during every
GC cycle: once at the beginning during root discovery and once at the
end during mark termination. The second scan happens while the world
is stopped and guarantees that we've seen all of the roots (since
there are no write barriers on writes to local stack
variables). However, this means pause time is proportional to stack
size. In particularly recursive programs, this can drive pause time up
past our 10ms goal (e.g., it takes about 150ms to scan a 50MB heap).
Re-scanning the entire stack is rarely necessary, especially for large
stacks, because usually most of the frames on the stack were not
active between the first and second scans and hence any changes to
these frames (via non-escaping pointers passed down the stack) were
tracked by write barriers.
To efficiently track how far a stack has been unwound since the first
scan (and, hence, how much needs to be re-scanned), this commit
introduces stack barriers. During the first scan, at exponentially
spaced points in each stack, the scan overwrites return PCs with the
PC of the stack barrier function. When "returned" to, the stack
barrier function records how far the stack has unwound and jumps to
the original return PC for that point in the stack. Then the second
scan only needs to proceed as far as the lowest barrier that hasn't
been hit.
For deeply recursive programs, this substantially reduces mark
termination time (and hence pause time). For the goscheme example
linked in issue #10898, prior to this change, mark termination times
were typically between 100 and 500ms; with this change, mark
termination times are typically between 10 and 20ms. As a result of
the reduced stack scanning work, this reduces overall execution time
of the goscheme example by 20%.
Fixes#10898.
The effect of this on programs that are not deeply recursive is
minimal:
name old time/op new time/op delta
BinaryTree17 3.16s ± 2% 3.26s ± 1% +3.31% (p=0.000 n=19+19)
Fannkuch11 2.42s ± 1% 2.48s ± 1% +2.24% (p=0.000 n=17+19)
FmtFprintfEmpty 50.0ns ± 3% 49.8ns ± 1% ~ (p=0.534 n=20+19)
FmtFprintfString 173ns ± 0% 175ns ± 0% +1.49% (p=0.000 n=16+19)
FmtFprintfInt 170ns ± 1% 175ns ± 1% +2.97% (p=0.000 n=20+19)
FmtFprintfIntInt 288ns ± 0% 295ns ± 0% +2.73% (p=0.000 n=16+19)
FmtFprintfPrefixedInt 242ns ± 1% 252ns ± 1% +4.13% (p=0.000 n=18+18)
FmtFprintfFloat 324ns ± 0% 323ns ± 0% -0.36% (p=0.000 n=20+19)
FmtManyArgs 1.14µs ± 0% 1.12µs ± 1% -1.01% (p=0.000 n=18+19)
GobDecode 8.88ms ± 1% 8.87ms ± 0% ~ (p=0.480 n=19+18)
GobEncode 6.80ms ± 1% 6.85ms ± 0% +0.82% (p=0.000 n=20+18)
Gzip 363ms ± 1% 363ms ± 1% ~ (p=0.077 n=18+20)
Gunzip 90.6ms ± 0% 90.0ms ± 1% -0.71% (p=0.000 n=17+18)
HTTPClientServer 51.5µs ± 1% 50.8µs ± 1% -1.32% (p=0.000 n=18+18)
JSONEncode 17.0ms ± 0% 17.1ms ± 0% +0.40% (p=0.000 n=18+17)
JSONDecode 61.8ms ± 0% 63.8ms ± 1% +3.11% (p=0.000 n=18+17)
Mandelbrot200 3.84ms ± 0% 3.84ms ± 1% ~ (p=0.583 n=19+19)
GoParse 3.71ms ± 1% 3.72ms ± 1% ~ (p=0.159 n=18+19)
RegexpMatchEasy0_32 100ns ± 0% 100ns ± 1% -0.19% (p=0.033 n=17+19)
RegexpMatchEasy0_1K 342ns ± 1% 331ns ± 0% -3.41% (p=0.000 n=19+19)
RegexpMatchEasy1_32 82.5ns ± 0% 81.7ns ± 0% -0.98% (p=0.000 n=18+18)
RegexpMatchEasy1_1K 505ns ± 0% 494ns ± 1% -2.16% (p=0.000 n=18+18)
RegexpMatchMedium_32 137ns ± 1% 137ns ± 1% -0.24% (p=0.048 n=20+18)
RegexpMatchMedium_1K 41.6µs ± 0% 41.3µs ± 1% -0.57% (p=0.004 n=18+20)
RegexpMatchHard_32 2.11µs ± 0% 2.11µs ± 1% +0.20% (p=0.037 n=17+19)
RegexpMatchHard_1K 63.9µs ± 2% 63.3µs ± 0% -0.99% (p=0.000 n=20+17)
Revcomp 560ms ± 1% 522ms ± 0% -6.87% (p=0.000 n=18+16)
Template 75.0ms ± 0% 75.1ms ± 1% +0.18% (p=0.013 n=18+19)
TimeParse 358ns ± 1% 364ns ± 0% +1.74% (p=0.000 n=20+15)
TimeFormat 360ns ± 0% 372ns ± 0% +3.55% (p=0.000 n=20+18)
Change-Id: If8a9bfae6c128d15a4f405e02bcfa50129df82a2
Reviewed-on: https://go-review.googlesource.com/10314
Reviewed-by: Russ Cox <rsc@golang.org>
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Currently runtime.callers invokes gentraceback with the pc and sp of
the G it is called from, but always passes g0 even if it was called
from a regular g. Right now this has no ill effects because
runtime.callers does not use either callback argument or the
_TraceJumpStack flag, but it makes the code fragile and will break
some upcoming changes.
Fix this by lifting the getg() call outside of the systemstack in
runtime.callers.
Change-Id: I4e1e927961c0e0cd4dcf28693be47df7bae9e122
Reviewed-on: https://go-review.googlesource.com/10292
Reviewed-by: Daniel Morsing <daniel.morsing@gmail.com>
Reviewed-by: Rick Hudson <rlh@golang.org>
Small types record the location of pointers in their memory layout
by using a simple bitmap. In Go 1.4 the bitmap held 4-bit entries,
and in Go 1.5 the bitmap holds 1-bit entries, but in both cases using
a bitmap for a large type containing arrays does not make sense:
if someone refers to the type [1<<28]*byte in a program in such
a way that the type information makes it into the binary, it would be
a waste of space to write a 128 MB (for 4-bit entries) or even 32 MB
(for 1-bit entries) bitmap full of 1s into the binary or even to keep
one in memory during the execution of the program.
For large types containing arrays, it is much more compact to describe
the locations of pointers using a notation that can express repetition
than to lay out a bitmap of pointers. Go 1.4 included such a notation,
called ``GC programs'' but it was complex, required recursion during
decoding, and was generally slow. Dmitriy measured the execution of
these programs writing directly to the heap bitmap as being 7x slower
than copying from a preunrolled 4-bit mask (and frankly that code was
not terribly fast either). For some tests, unrollgcprog1 was seen costing
as much as 3x more than the rest of malloc combined.
This CL introduces a different form for the GC programs. They use a
simple Lempel-Ziv-style encoding of the 1-bit pointer information,
in which the only operations are (1) emit the following n bits
and (2) repeat the last n bits c more times. This encoding can be
generated directly from the Go type information (using repetition
only for arrays or large runs of non-pointer data) and it can be decoded
very efficiently. In particular the decoding requires little state and
no recursion, so that the entire decoding can run without any memory
accesses other than the reads of the encoding and the writes of the
decoded form to the heap bitmap. For recursive types like arrays of
arrays of arrays, the inner instructions are only executed once, not
n times, so that large repetitions run at full speed. (In contrast, large
repetitions in the old programs repeated the individual bit-level layout
of the inner data over and over.) The result is as much as 25x faster
decoding compared to the old form.
Because the old decoder was so slow, Go 1.4 had three (or so) cases
for how to set the heap bitmap bits for an allocation of a given type:
(1) If the type had an even number of words up to 32 words, then
the 4-bit pointer mask for the type fit in no more than 16 bytes;
store the 4-bit pointer mask directly in the binary and copy from it.
(1b) If the type had an odd number of words up to 15 words, then
the 4-bit pointer mask for the type, doubled to end on a byte boundary,
fit in no more than 16 bytes; store that doubled mask directly in the
binary and copy from it.
(2) If the type had an even number of words up to 128 words,
or an odd number of words up to 63 words (again due to doubling),
then the 4-bit pointer mask would fit in a 64-byte unrolled mask.
Store a GC program in the binary, but leave space in the BSS for
the unrolled mask. Execute the GC program to construct the mask the
first time it is needed, and thereafter copy from the mask.
(3) Otherwise, store a GC program and execute it to write directly to
the heap bitmap each time an object of that type is allocated.
(This is the case that was 7x slower than the other two.)
Because the new pointer masks store 1-bit entries instead of 4-bit
entries and because using the decoder no longer carries a significant
overhead, after this CL (that is, for Go 1.5) there are only two cases:
(1) If the type is 128 words or less (no condition about odd or even),
store the 1-bit pointer mask directly in the binary and use it to
initialize the heap bitmap during malloc. (Implemented in CL 9702.)
(2) There is no case 2 anymore.
(3) Otherwise, store a GC program and execute it to write directly to
the heap bitmap each time an object of that type is allocated.
Executing the GC program directly into the heap bitmap (case (3) above)
was disabled for the Go 1.5 dev cycle, both to avoid needing to use
GC programs for typedmemmove and to avoid updating that code as
the heap bitmap format changed. Typedmemmove no longer uses this
type information; as of CL 9886 it uses the heap bitmap directly.
Now that the heap bitmap format is stable, we reintroduce GC programs
and their space savings.
Benchmarks for heapBitsSetType, before this CL vs this CL:
name old mean new mean delta
SetTypePtr 7.59ns × (0.99,1.02) 5.16ns × (1.00,1.00) -32.05% (p=0.000)
SetTypePtr8 21.0ns × (0.98,1.05) 21.4ns × (1.00,1.00) ~ (p=0.179)
SetTypePtr16 24.1ns × (0.99,1.01) 24.6ns × (1.00,1.00) +2.41% (p=0.001)
SetTypePtr32 31.2ns × (0.99,1.01) 32.4ns × (0.99,1.02) +3.72% (p=0.001)
SetTypePtr64 45.2ns × (1.00,1.00) 47.2ns × (1.00,1.00) +4.42% (p=0.000)
SetTypePtr126 75.8ns × (0.99,1.01) 79.1ns × (1.00,1.00) +4.25% (p=0.000)
SetTypePtr128 74.3ns × (0.99,1.01) 77.6ns × (1.00,1.01) +4.55% (p=0.000)
SetTypePtrSlice 726ns × (1.00,1.01) 712ns × (1.00,1.00) -1.95% (p=0.001)
SetTypeNode1 20.0ns × (0.99,1.01) 20.7ns × (1.00,1.00) +3.71% (p=0.000)
SetTypeNode1Slice 112ns × (1.00,1.00) 113ns × (0.99,1.00) ~ (p=0.070)
SetTypeNode8 23.9ns × (1.00,1.00) 24.7ns × (1.00,1.01) +3.18% (p=0.000)
SetTypeNode8Slice 294ns × (0.99,1.02) 287ns × (0.99,1.01) -2.38% (p=0.015)
SetTypeNode64 52.8ns × (0.99,1.03) 51.8ns × (0.99,1.01) ~ (p=0.069)
SetTypeNode64Slice 1.13µs × (0.99,1.05) 1.14µs × (0.99,1.00) ~ (p=0.767)
SetTypeNode64Dead 36.0ns × (1.00,1.01) 32.5ns × (0.99,1.00) -9.67% (p=0.000)
SetTypeNode64DeadSlice 1.43µs × (0.99,1.01) 1.40µs × (1.00,1.00) -2.39% (p=0.001)
SetTypeNode124 75.7ns × (1.00,1.01) 79.0ns × (1.00,1.00) +4.44% (p=0.000)
SetTypeNode124Slice 1.94µs × (1.00,1.01) 2.04µs × (0.99,1.01) +4.98% (p=0.000)
SetTypeNode126 75.4ns × (1.00,1.01) 77.7ns × (0.99,1.01) +3.11% (p=0.000)
SetTypeNode126Slice 1.95µs × (0.99,1.01) 2.03µs × (1.00,1.00) +3.74% (p=0.000)
SetTypeNode128 85.4ns × (0.99,1.01) 122.0ns × (1.00,1.00) +42.89% (p=0.000)
SetTypeNode128Slice 2.20µs × (1.00,1.01) 2.36µs × (0.98,1.02) +7.48% (p=0.001)
SetTypeNode130 83.3ns × (1.00,1.00) 123.0ns × (1.00,1.00) +47.61% (p=0.000)
SetTypeNode130Slice 2.30µs × (0.99,1.01) 2.40µs × (0.98,1.01) +4.37% (p=0.000)
SetTypeNode1024 498ns × (1.00,1.00) 537ns × (1.00,1.00) +7.96% (p=0.000)
SetTypeNode1024Slice 15.5µs × (0.99,1.01) 17.8µs × (1.00,1.00) +15.27% (p=0.000)
The above compares always using a cached pointer mask (and the
corresponding waste of memory) against using the programs directly.
Some slowdown is expected, in exchange for having a better general algorithm.
The GC programs kick in for SetTypeNode128, SetTypeNode130, SetTypeNode1024,
along with the slice variants of those.
It is possible that the cutoff of 128 words (bits) should be raised
in a followup CL, but even with this low cutoff the GC programs are
faster than Go 1.4's "fast path" non-GC program case.
Benchmarks for heapBitsSetType, Go 1.4 vs this CL:
name old mean new mean delta
SetTypePtr 6.89ns × (1.00,1.00) 5.17ns × (1.00,1.00) -25.02% (p=0.000)
SetTypePtr8 25.8ns × (0.97,1.05) 21.5ns × (1.00,1.00) -16.70% (p=0.000)
SetTypePtr16 39.8ns × (0.97,1.02) 24.7ns × (0.99,1.01) -37.81% (p=0.000)
SetTypePtr32 68.8ns × (0.98,1.01) 32.2ns × (1.00,1.01) -53.18% (p=0.000)
SetTypePtr64 130ns × (1.00,1.00) 47ns × (1.00,1.00) -63.67% (p=0.000)
SetTypePtr126 241ns × (0.99,1.01) 79ns × (1.00,1.01) -67.25% (p=0.000)
SetTypePtr128 2.07µs × (1.00,1.00) 0.08µs × (1.00,1.00) -96.27% (p=0.000)
SetTypePtrSlice 1.05µs × (0.99,1.01) 0.72µs × (0.99,1.02) -31.70% (p=0.000)
SetTypeNode1 16.0ns × (0.99,1.01) 20.8ns × (0.99,1.03) +29.91% (p=0.000)
SetTypeNode1Slice 184ns × (0.99,1.01) 112ns × (0.99,1.01) -39.26% (p=0.000)
SetTypeNode8 29.5ns × (0.97,1.02) 24.6ns × (1.00,1.00) -16.50% (p=0.000)
SetTypeNode8Slice 624ns × (0.98,1.02) 285ns × (1.00,1.00) -54.31% (p=0.000)
SetTypeNode64 135ns × (0.96,1.08) 52ns × (0.99,1.02) -61.32% (p=0.000)
SetTypeNode64Slice 3.83µs × (1.00,1.00) 1.14µs × (0.99,1.01) -70.16% (p=0.000)
SetTypeNode64Dead 134ns × (0.99,1.01) 32ns × (1.00,1.01) -75.74% (p=0.000)
SetTypeNode64DeadSlice 3.83µs × (0.99,1.00) 1.40µs × (1.00,1.01) -63.42% (p=0.000)
SetTypeNode124 240ns × (0.99,1.01) 79ns × (1.00,1.01) -67.05% (p=0.000)
SetTypeNode124Slice 7.27µs × (1.00,1.00) 2.04µs × (1.00,1.00) -71.95% (p=0.000)
SetTypeNode126 2.06µs × (0.99,1.01) 0.08µs × (0.99,1.01) -96.23% (p=0.000)
SetTypeNode126Slice 64.4µs × (1.00,1.00) 2.0µs × (1.00,1.00) -96.85% (p=0.000)
SetTypeNode128 2.09µs × (1.00,1.01) 0.12µs × (1.00,1.00) -94.15% (p=0.000)
SetTypeNode128Slice 65.4µs × (1.00,1.00) 2.4µs × (0.99,1.03) -96.39% (p=0.000)
SetTypeNode130 2.11µs × (1.00,1.00) 0.12µs × (1.00,1.00) -94.18% (p=0.000)
SetTypeNode130Slice 66.3µs × (1.00,1.00) 2.4µs × (0.97,1.08) -96.34% (p=0.000)
SetTypeNode1024 16.0µs × (1.00,1.01) 0.5µs × (1.00,1.00) -96.65% (p=0.000)
SetTypeNode1024Slice 512µs × (1.00,1.00) 18µs × (0.98,1.04) -96.45% (p=0.000)
SetTypeNode124 uses a 124 data + 2 ptr = 126-word allocation.
Both Go 1.4 and this CL are using pointer bitmaps for this case,
so that's an overall 3x speedup for using pointer bitmaps.
SetTypeNode128 uses a 128 data + 2 ptr = 130-word allocation.
Both Go 1.4 and this CL are running the GC program for this case,
so that's an overall 17x speedup when using GC programs (and
I've seen >20x on other systems).
Comparing Go 1.4's SetTypeNode124 (pointer bitmap) against
this CL's SetTypeNode128 (GC program), the slow path in the
code in this CL is 2x faster than the fast path in Go 1.4.
The Go 1 benchmarks are basically unaffected compared to just before this CL.
Go 1 benchmarks, before this CL vs this CL:
name old mean new mean delta
BinaryTree17 5.87s × (0.97,1.04) 5.91s × (0.96,1.04) ~ (p=0.306)
Fannkuch11 4.38s × (1.00,1.00) 4.37s × (1.00,1.01) -0.22% (p=0.006)
FmtFprintfEmpty 90.7ns × (0.97,1.10) 89.3ns × (0.96,1.09) ~ (p=0.280)
FmtFprintfString 282ns × (0.98,1.04) 287ns × (0.98,1.07) +1.72% (p=0.039)
FmtFprintfInt 269ns × (0.99,1.03) 282ns × (0.97,1.04) +4.87% (p=0.000)
FmtFprintfIntInt 478ns × (0.99,1.02) 481ns × (0.99,1.02) +0.61% (p=0.048)
FmtFprintfPrefixedInt 399ns × (0.98,1.03) 400ns × (0.98,1.05) ~ (p=0.533)
FmtFprintfFloat 563ns × (0.99,1.01) 570ns × (1.00,1.01) +1.37% (p=0.000)
FmtManyArgs 1.89µs × (0.99,1.01) 1.92µs × (0.99,1.02) +1.88% (p=0.000)
GobDecode 15.2ms × (0.99,1.01) 15.2ms × (0.98,1.05) ~ (p=0.609)
GobEncode 11.6ms × (0.98,1.03) 11.9ms × (0.98,1.04) +2.17% (p=0.000)
Gzip 648ms × (0.99,1.01) 648ms × (1.00,1.01) ~ (p=0.835)
Gunzip 142ms × (1.00,1.00) 143ms × (1.00,1.01) ~ (p=0.169)
HTTPClientServer 90.5µs × (0.98,1.03) 91.5µs × (0.98,1.04) +1.04% (p=0.045)
JSONEncode 31.5ms × (0.98,1.03) 31.4ms × (0.98,1.03) ~ (p=0.549)
JSONDecode 111ms × (0.99,1.01) 107ms × (0.99,1.01) -3.21% (p=0.000)
Mandelbrot200 6.01ms × (1.00,1.00) 6.01ms × (1.00,1.00) ~ (p=0.878)
GoParse 6.54ms × (0.99,1.02) 6.61ms × (0.99,1.03) +1.08% (p=0.004)
RegexpMatchEasy0_32 160ns × (1.00,1.01) 161ns × (1.00,1.00) +0.40% (p=0.000)
RegexpMatchEasy0_1K 560ns × (0.99,1.01) 559ns × (0.99,1.01) ~ (p=0.088)
RegexpMatchEasy1_32 138ns × (0.99,1.01) 138ns × (1.00,1.00) ~ (p=0.380)
RegexpMatchEasy1_1K 877ns × (1.00,1.00) 878ns × (1.00,1.00) ~ (p=0.157)
RegexpMatchMedium_32 251ns × (0.99,1.00) 251ns × (1.00,1.01) +0.28% (p=0.021)
RegexpMatchMedium_1K 72.6µs × (1.00,1.00) 72.6µs × (1.00,1.00) ~ (p=0.539)
RegexpMatchHard_32 3.84µs × (1.00,1.00) 3.84µs × (1.00,1.00) ~ (p=0.378)
RegexpMatchHard_1K 117µs × (1.00,1.00) 117µs × (1.00,1.00) ~ (p=0.067)
Revcomp 904ms × (0.99,1.02) 904ms × (0.99,1.01) ~ (p=0.943)
Template 125ms × (0.99,1.02) 127ms × (0.99,1.01) +1.79% (p=0.000)
TimeParse 627ns × (0.99,1.01) 622ns × (0.99,1.01) -0.88% (p=0.000)
TimeFormat 655ns × (0.99,1.02) 655ns × (0.99,1.02) ~ (p=0.976)
For the record, Go 1 benchmarks, Go 1.4 vs this CL:
name old mean new mean delta
BinaryTree17 4.61s × (0.97,1.05) 5.91s × (0.98,1.03) +28.35% (p=0.000)
Fannkuch11 4.40s × (0.99,1.03) 4.41s × (0.99,1.01) ~ (p=0.212)
FmtFprintfEmpty 102ns × (0.99,1.01) 84ns × (0.99,1.02) -18.38% (p=0.000)
FmtFprintfString 302ns × (0.98,1.01) 303ns × (0.99,1.02) ~ (p=0.203)
FmtFprintfInt 313ns × (0.97,1.05) 270ns × (0.99,1.01) -13.69% (p=0.000)
FmtFprintfIntInt 524ns × (0.98,1.02) 477ns × (0.99,1.00) -8.87% (p=0.000)
FmtFprintfPrefixedInt 424ns × (0.98,1.02) 386ns × (0.99,1.01) -8.96% (p=0.000)
FmtFprintfFloat 652ns × (0.98,1.02) 594ns × (0.97,1.05) -8.97% (p=0.000)
FmtManyArgs 2.13µs × (0.99,1.02) 1.94µs × (0.99,1.01) -8.92% (p=0.000)
GobDecode 17.1ms × (0.99,1.02) 14.9ms × (0.98,1.03) -13.07% (p=0.000)
GobEncode 13.5ms × (0.98,1.03) 11.5ms × (0.98,1.03) -15.25% (p=0.000)
Gzip 656ms × (0.99,1.02) 647ms × (0.99,1.01) -1.29% (p=0.000)
Gunzip 143ms × (0.99,1.02) 144ms × (0.99,1.01) ~ (p=0.204)
HTTPClientServer 88.2µs × (0.98,1.02) 90.8µs × (0.98,1.01) +2.93% (p=0.000)
JSONEncode 32.2ms × (0.98,1.02) 30.9ms × (0.97,1.04) -4.06% (p=0.001)
JSONDecode 121ms × (0.98,1.02) 110ms × (0.98,1.05) -8.95% (p=0.000)
Mandelbrot200 6.06ms × (0.99,1.01) 6.11ms × (0.98,1.04) ~ (p=0.184)
GoParse 6.76ms × (0.97,1.04) 6.58ms × (0.98,1.05) -2.63% (p=0.003)
RegexpMatchEasy0_32 195ns × (1.00,1.01) 155ns × (0.99,1.01) -20.43% (p=0.000)
RegexpMatchEasy0_1K 479ns × (0.98,1.03) 535ns × (0.99,1.02) +11.59% (p=0.000)
RegexpMatchEasy1_32 169ns × (0.99,1.02) 131ns × (0.99,1.03) -22.44% (p=0.000)
RegexpMatchEasy1_1K 1.53µs × (0.99,1.01) 0.87µs × (0.99,1.02) -43.07% (p=0.000)
RegexpMatchMedium_32 334ns × (0.99,1.01) 242ns × (0.99,1.01) -27.53% (p=0.000)
RegexpMatchMedium_1K 125µs × (1.00,1.01) 72µs × (0.99,1.03) -42.53% (p=0.000)
RegexpMatchHard_32 6.03µs × (0.99,1.01) 3.79µs × (0.99,1.01) -37.12% (p=0.000)
RegexpMatchHard_1K 189µs × (0.99,1.02) 115µs × (0.99,1.01) -39.20% (p=0.000)
Revcomp 935ms × (0.96,1.03) 926ms × (0.98,1.02) ~ (p=0.083)
Template 146ms × (0.97,1.05) 119ms × (0.99,1.01) -18.37% (p=0.000)
TimeParse 660ns × (0.99,1.01) 624ns × (0.99,1.02) -5.43% (p=0.000)
TimeFormat 670ns × (0.98,1.02) 710ns × (1.00,1.01) +5.97% (p=0.000)
This CL is a bit larger than I would like, but the compiler, linker, runtime,
and package reflect all need to be in sync about the format of these programs,
so there is no easy way to split this into independent changes (at least
while keeping the build working at each change).
Fixes#9625.
Fixes#10524.
Change-Id: I9e3e20d6097099d0f8532d1cb5b1af528804989a
Reviewed-on: https://go-review.googlesource.com/9888
Reviewed-by: Austin Clements <austin@google.com>
Run-TryBot: Russ Cox <rsc@golang.org>
Since we now have stack information for code running on the
systemstack, we can traceback over it. To make cpu profiles useful,
add a case in gentraceback to jump over systemstack switches.
Fixes#10609.
Change-Id: I21f47fcc802c07c5d4a1ada56374314e388a6dc7
Reviewed-on: https://go-review.googlesource.com/9506
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Sequence of operations:
- Go code does a systemstack call
- during the systemstack call, receive a signal
- signal requests a traceback of all goroutines
The orignal G is still marked as _Grunning, so the traceback code
refuses to print its stack.
Fix by allowing traceback of Gs whose caller is on the same M as G is.
G can't be modifying its stack if that is the case.
Fixes#10546
Change-Id: I2bcea48c0197fbf78ab6fa080027cd80181083ad
Reviewed-on: https://go-review.googlesource.com/9435
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
This CL revises CL 7504 to use explicitly uintptr types for the
struct fields that are going to be updated sometimes without
write barriers. The result is that the fields are now updated *always*
without write barriers.
This approach has two important properties:
1) Now the GC never looks at the field, so if the missing reference
could cause a problem, it will do so all the time, not just when the
write barrier is missed at just the right moment.
2) Now a write barrier never happens for the field, avoiding the
(correct) detection of inconsistent write barriers when GODEBUG=wbshadow=1.
Change-Id: Iebd3962c727c0046495cc08914a8dc0808460e0e
Reviewed-on: https://go-review.googlesource.com/9019
Reviewed-by: Austin Clements <austin@google.com>
Run-TryBot: Russ Cox <rsc@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
This fixes runtime's TestBreakpoint on ppc64:
the Breakpoint frame was not showing up in the trace.
It seems like f.frame should be either the frame size
including the saved LR (if any) or the frame size
not including the saved LR.
On ppc64, f.frame is the frame size not including the saved LR.
On arm, f.frame is the frame size not including the saved LR,
except when that's -4, f.frame is 0 instead.
The code here in the runtime expects that f.frame is the frame
size including the saved LR.
Since all three disagree and nothing else uses f.frame anymore,
stop using it here too. Use funcspdelta, which tells us the exact
difference between the FP and SP. If it's zero, LR has not been
saved yet, so the one saved for sigpanic should be recorded.
This fixes TestBreakpoint on both ppc64 and ppc64le.
I don't really understand how it ever worked there.
Change-Id: I2d2c580d5c0252cc8471e828980aeedcab76858d
Reviewed-on: https://go-review.googlesource.com/6430
Reviewed-by: Minux Ma <minux@golang.org>
This makes Go's CPU profiling code somewhat more idiomatic; e.g.,
using := instead of forward declaring variables, using "int" for
element counts instead of "uintptr", and slices instead of C-style
pointer+length. This makes the code easier to read and eliminates a
lot of type conversion clutter.
Additionally, in sigprof we can collect just maxCPUProfStack stack
frames, as cpuprof won't use more than that anyway.
Change-Id: I0235b5ae552191bcbb453b14add6d8c01381bd06
Reviewed-on: https://go-review.googlesource.com/6072
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Fixes#9791
g.issystem flag setup races with other code wherever we set it.
Even if we set both in parent goroutine and in the system goroutine,
it is still possible that some other goroutine crashes
before the flag is set. We could pass issystem flag to newproc1,
but we start all goroutines with go nowadays.
Instead look at g.startpc to distinguish system goroutines (similar to topofstack).
Change-Id: Ia3467968dee27fa07d9fecedd4c2b00928f26645
Reviewed-on: https://go-review.googlesource.com/4113
Reviewed-by: Keith Randall <khr@golang.org>
The test for the framepointer experiment flag is cheaper and more
branch-predictable than the other parts of this conditional, so move
it first. This is also more readable.
(Originally, the flag check required parsing the experiments string,
which is why it was done last. Now that flag is cached.)
Change-Id: I84e00fa7e939e9064f0fa0a4a6fe00576dd61457
Reviewed-on: https://go-review.googlesource.com/3782
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Previously, we checked for a saved frame pointer by looking for a
2*ptrSize gap between the argument pointer and the locals pointer.
The intent of this check was to look for a two stack slot gap (caller
IP and saved frame pointer), but stack slots are regSize, not ptrSize.
Correct this by checking instead for a 2*regSize gap.
On most platforms, this made no difference because ptrSize==regSize.
However, on amd64p32 (nacl), the saved frame pointer check incorrectly
fired when there was no saved frame pointer because the one stack slot
for the caller IP left an 8 byte gap, which is 2*ptrSize (but not
2*regSize) on amd64p32.
Fixes#9760.
Change-Id: I6eedcf681fe5bf2bf924dde8a8f2d9860a4d758e
Reviewed-on: https://go-review.googlesource.com/3781
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
This adds a "framepointer" GOEXPERIMENT that that makes the amd64
toolchain maintain base pointer chains in the same way that gcc
-fno-omit-frame-pointer does. Go doesn't use these saved base
pointers, but this does enable external tools like Linux perf and
VTune to unwind Go stacks when collecting system-wide profiles.
This requires support in the compilers to not clobber BP, support in
liblink for generating the BP-saving function prologue and unwinding
epilogue, and support in the runtime to save BPs across preemption, to
skip saved BPs during stack unwinding and, and to adjust saved BPs
during stack moving.
As with other GOEXPERIMENTs, everything from the toolchain to the
runtime must be compiled with this experiment enabled. To do this,
run make.bash (or all.bash) with GOEXPERIMENT=framepointer.
Change-Id: I4024853beefb9539949e5ca381adfdd9cfada544
Reviewed-on: https://go-review.googlesource.com/2992
Reviewed-by: Russ Cox <rsc@golang.org>
They are no longer needed now that C is gone.
goatoi -> atoi
gofuncname/funcname -> funcname/cfuncname
goroundupsize -> already existing roundupsize
Change-Id: I278bc33d279e1fdc5e8a2a04e961c4c1573b28c7
Reviewed-on: https://go-review.googlesource.com/2154
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Reviewed-by: Minux Ma <minux@golang.org>
Rename "gothrow" to "throw" now that the C version of "throw"
is no longer needed.
This change is purely mechanical except in panic.go where the
old version of "throw" has been deleted.
sed -i "" 's/[[:<:]]gothrow[[:>:]]/throw/g' runtime/*.go
Change-Id: Icf0752299c35958b92870a97111c67bcd9159dc3
Reviewed-on: https://go-review.googlesource.com/2150
Reviewed-by: Minux Ma <minux@golang.org>
Reviewed-by: Dave Cheney <dave@cheney.net>
Calls to goproc/deferproc used to push & pop two extra arguments,
the argument size and the function to call. Now, we allocate space
for those arguments in the outargs section so we don't have to
modify the SP.
Defers now use the stack pointer (instead of the argument pointer)
to identify which frame they are associated with.
A followon CL might simplify funcspdelta and some of the stack
walking code.
Fixes issue #8641
Change-Id: I835ec2f42f0392c5dec7cb0fe6bba6f2aed1dad8
Reviewed-on: https://go-review.googlesource.com/1601
Reviewed-by: Russ Cox <rsc@golang.org>
Scalararg and ptrarg are not "signal safe".
Go code filling them out can be interrupted by a signal,
and then the signal handler runs, and if it also ends up
in Go code that uses scalararg or ptrarg, now the old
values have been smashed.
For the pieces of code that do need to run in a signal handler,
we introduced onM_signalok, which is really just onM
except that the _signalok is meant to convey that the caller
asserts that scalarg and ptrarg will be restored to their old
values after the call (instead of the usual behavior, zeroing them).
Scalararg and ptrarg are also untyped and therefore error-prone.
Go code can always pass a closure instead of using scalararg
and ptrarg; they were only really necessary for C code.
And there's no more C code.
For all these reasons, delete scalararg and ptrarg, converting
the few remaining references to use closures.
Once those are gone, there is no need for a distinction between
onM and onM_signalok, so replace both with a single function
equivalent to the current onM_signalok (that is, it can be called
on any of the curg, g0, and gsignal stacks).
The name onM and the phrase 'm stack' are misnomers,
because on most system an M has two system stacks:
the main thread stack and the signal handling stack.
Correct the misnomer by naming the replacement function systemstack.
Fix a few references to "M stack" in code.
The main motivation for this change is to eliminate scalararg/ptrarg.
Rick and I have already seen them cause problems because
the calling sequence m.ptrarg[0] = p is a heap pointer assignment,
so it gets a write barrier. The write barrier also uses onM, so it has
all the same problems as if it were being invoked by a signal handler.
We worked around this by saving and restoring the old values
and by calling onM_signalok, but there's no point in keeping this nice
home for bugs around any longer.
This CL also changes funcline to return the file name as a result
instead of filling in a passed-in *string. (The *string signature is
left over from when the code was written in and called from C.)
That's arguably an unrelated change, except that once I had done
the ptrarg/scalararg/onM cleanup I started getting false positives
about the *string argument escaping (not allowed in package runtime).
The compiler is wrong, but the easiest fix is to write the code like
Go code instead of like C code. I am a bit worried that the compiler
is wrong because of some use of uninitialized memory in the escape
analysis. If that's the reason, it will go away when we convert the
compiler to Go. (And if not, we'll debug it the next time.)
LGTM=khr
R=r, khr
CC=austin, golang-codereviews, iant, rlh
https://golang.org/cl/174950043
The conversion was done with an automated tool and then
modified only as necessary to make it compile and run.
[This CL is part of the removal of C code from package runtime.
See golang.org/s/dev.cc for an overview.]
LGTM=r
R=r, dave
CC=austin, dvyukov, golang-codereviews, iant, khr
https://golang.org/cl/166520043
Gentraceback may grow the stack.
One of the gentraceback wrappers may grow the stack.
One of the gentraceback callback calls may grow the stack.
Various stack pointers are stored in various stack locations
as type uintptr during the execution of these calls.
If the stack does grow, these stack pointers will not be
updated and will start trying to decode stack memory that
is no longer valid.
It may be possible to change the type of the stack pointer
variables to be unsafe.Pointer, but that's pretty subtle and
may still have problems, even if we catch every last one.
An easier, more obviously correct fix is to require that
gentraceback of the currently running goroutine must run
on the g0 stack, not on the goroutine's own stack.
Not doing this causes faults when you set
StackFromSystem = 1
StackFaultOnFree = 1
The new check in gentraceback will catch future lapses.
The more general problem is calling getcallersp but then
calling a function that might relocate the stack, which would
invalidate the result of getcallersp. Add note to stubs.go
declaration of getcallersp explaining the problem, and
check all existing calls to getcallersp. Most needed fixes.
This affects Callers, Stack, and nearly all the runtime
profiling routines. It does not affect stack copying directly
nor garbage collection.
LGTM=khr
R=khr, bradfitz
CC=golang-codereviews, r
https://golang.org/cl/167060043
Originally traceback was only used for printing the stack
when an unexpected signal came in. In that case, the
initial PC is taken from the signal and should be used
unaltered. For the callers, the PC is the return address,
which might be on the line after the call; we subtract 1
to get to the CALL instruction.
Traceback is now used for a variety of things, and for
almost all of those the initial PC is a return address,
whether from getcallerpc, or gp->sched.pc, or gp->syscallpc.
In those cases, we need to subtract 1 from this initial PC,
but the traceback code had a hard rule "never subtract 1
from the initial PC", left over from the signal handling days.
Change gentraceback to take a flag that specifies whether
we are tracing a trap.
Change traceback to default to "starting with a return PC",
which is the overwhelmingly common case.
Add tracebacktrap, like traceback but starting with a trap PC.
Use tracebacktrap in signal handlers.
Fixes#7690.
LGTM=iant, r
R=r, iant
CC=golang-codereviews
https://golang.org/cl/167810044
Our traceback code needs to know the PC of several special
functions, including goexit, mcall, etc. Make sure that
these PCs are initialized before any traceback occurs.
Fixes#8766
LGTM=rsc
R=golang-codereviews, rsc, khr, bradfitz
CC=golang-codereviews
https://golang.org/cl/145570043
The current Windows build failure happens because by
default runtime frames are excluded from stack traces.
Apparently the Windows breakpoint path dies with an
ordinary panic, while the Unix path dies with a throw.
Breakpoint is a strange function and I don't mind that it's
a little different on the two operating systems.
The panic squelches runtime frames but the throw shows them,
because throw is considered something that shouldn't have
happened at all, so as much detail as possible is wanted.
The runtime exclusion is meant to prevents printing too much noise
about internal runtime details. But exported functions are
not internal details, so show exported functions.
If the program dies because you called runtime.Breakpoint,
it's okay to see that frame.
This makes the Breakpoint test show Breakpoint in the
stack trace no matter how it is handled.
Should fix Windows build.
Tested on Unix by changing Breakpoint to fault instead
of doing a breakpoint.
TBR=brainman
CC=golang-codereviews
https://golang.org/cl/143300043
This makes the GC and the stack copying agree about how
to interpret the defer structures. Previously, only the stack
copying treated them precisely.
This removes an untyped memory allocation and fixes
at least three copystack bugs.
To make sure the GC can find the deferred argument
frame until it has been copied, keep a Defer on the defer list
during its execution.
In addition to making it possible to remove the untyped
memory allocation, keeping the Defer on the list fixes
two races between copystack and execution of defers
(in both gopanic and Goexit). The problem is that once
the defer has been taken off the list, a stack copy that
happens before the deferred arguments have been copied
back to the stack will not update the arguments correctly.
The new tests TestDeferPtrsPanic and TestDeferPtrsGoexit
(variations on the existing TestDeferPtrs) pass now but
failed before this CL.
In addition to those fixes, keeping the Defer on the list
helps correct a dangling pointer error during copystack.
The traceback routines walk the Defer chain to provide
information about where a panic may resume execution.
When the executing Defer was not on the Defer chain
but instead linked from the Panic chain, the traceback
had to walk the Panic chain too. But Panic structs are
on the stack and being updated by copystack.
Traceback's use of the Panic chain while copystack is
updating those structs means that it can follow an
updated pointer and find itself reading from the new stack.
The new stack is usually all zeros, so it sees an incorrect
early end to the chain. The new TestPanicUseStack makes
this happen at tip and dies when adjustdefers finds an
unexpected argp. The new StackCopyPoison mode
causes an earlier bad dereference instead.
By keeping the Defer on the list, traceback can avoid
walking the Panic chain at all, making it okay for copystack
to update the Panics.
We'd have the same problem for any Defers on the stack.
There was only one: gopanic's dabort. Since we are not
taking the executing Defer off the chain, we can use it
to do what dabort was doing, and then there are no
Defers on the stack ever, so it is okay for traceback to use
the Defer chain even while copystack is executing:
copystack cannot modify the Defer chain.
LGTM=khr
R=khr
CC=dvyukov, golang-codereviews, iant, rlh
https://golang.org/cl/141490043
The merged traceback was wrong for LR machines,
because traceback didn't pass lr to gentraceback.
Now that we have a test looking at traceback output
for a trap (the test of runtime.Breakpoint),
we caught this.
While we're here, fix a 'set and not used' warning.
Fixes arm build.
TBR=r
R=r
CC=golang-codereviews
https://golang.org/cl/143040043
The goal here is to commit fully to having precise information
about stack frames. If we need information we don't have,
crash instead of assuming we should scan conservatively.
Since the stack copying assumes fully precise information,
any crashes during garbage collection that are introduced by
this CL are crashes that could have happened during stack
copying instead. Those are harder to find because stacks are
copied much less often than the garbage collector is invoked.
In service of that goal, remove ARGSIZE macros from
asm_*.s, change switchtoM to have no arguments
(it doesn't have any live arguments), and add
args and locals information to some frames that
can call back into Go.
LGTM=khr
R=khr, rlh
CC=golang-codereviews
https://golang.org/cl/137540043
makeFuncStub and methodValueStub are used by reflect as
generic function implementations. Each call might have
different arguments. Extract those arguments from the
closure data instead of assuming it is the same each time.
Because the argument map is now being extracted from the
function itself, we don't need the special cases in reflect.Call
anymore, so delete those.
Fixes an occasional crash seen when stack copying does
not update makeFuncStub's arguments correctly.
Will also help make it safe to require stack maps in the
garbage collector.
Derived from CL 142000044 by khr.
LGTM=khr
R=khr
CC=golang-codereviews
https://golang.org/cl/143890044
Commit to stack copying for stack growth.
We're carrying around a surprising amount of cruft from older schemes.
I am confident that precise stack scans and stack copying are here to stay.
Delete fallback code for when precise stack info is disabled.
Delete fallback code for when copying stacks is disabled.
Delete fallback code for when StackCopyAlways is disabled.
Delete Stktop chain - there is only one stack segment now.
Delete M.moreargp, M.moreargsize, M.moreframesize, M.cret.
Delete G.writenbuf (unrelated, just dead).
Delete runtime.lessstack, runtime.oldstack.
Delete many amd64 morestack variants.
Delete initialization of morestack frame/arg sizes (shortens split prologue!).
Replace G's stackguard/stackbase/stack0/stacksize/
syscallstack/syscallguard/forkstackguard with simple stack
bounds (lo, hi).
Update liblink, runtime/cgo for adjustments to G.
LGTM=khr
R=khr, bradfitz
CC=golang-codereviews, iant, r
https://golang.org/cl/137410043
This CL contains compiler+runtime changes that detect C code
running on Go (not g0, not gsignal) stacks, and it contains
corrections for what it detected.
The detection works by changing the C prologue to use a different
stack guard word in the G than Go prologue does. On the g0 and
gsignal stacks, that stack guard word is set to the usual
stack guard value. But on ordinary Go stacks, that stack
guard word is set to ^0, which will make any stack split
check fail. The C prologue then calls morestackc instead
of morestack, and morestackc aborts the program with
a message about running C code on a Go stack.
This check catches all C code running on the Go stack
except NOSPLIT code. The NOSPLIT code is allowed,
so the check is complete. Since it is a dynamic check,
the code must execute to be caught. But unlike the static
checks we've been using in cmd/ld, the dynamic check
works with function pointers and other indirect calls.
For example it caught sigpanic being pushed onto Go
stacks in the signal handlers.
Fixes#8667.
LGTM=khr, iant
R=golang-codereviews, khr, iant
CC=golang-codereviews, r
https://golang.org/cl/133700043
