Instrument operands of OKEY.
Also instrument OSLICESTR. Previously it was not needed
because of preceeding bounds checks (which were instrumented).
But the preceeding bounds checks have disappeared.
Change-Id: I3b0de213e23cbcf5b8ef800abeded5eeeb3f8287
Reviewed-on: https://go-review.googlesource.com/11417
Reviewed-by: Russ Cox <rsc@golang.org>
At some point it silently stopped recognizing test output.
Meanwhile two tests degraded...
Change-Id: I90a0325fc9aaa16c3ef16b9c4c642581da2bb10c
Reviewed-on: https://go-review.googlesource.com/11416
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
For debuggers and other program inspectors.
Fixes#9914.
Change-Id: I670728cea28c045e6eaba1808c550ee2f34d16ff
Reviewed-on: https://go-review.googlesource.com/11341
Reviewed-by: Austin Clements <austin@google.com>
The test is flaky on builders lately. I don't see any issues other than
usage of very small sleeps. So increase the sleeps. Also take opportunity
to refactor the code.
On my machine this change significantly reduces failure rate with GOMAXPROCS=2.
I can't reproduce the failure with GOMAXPROCS=1.
Fixes#10726
Change-Id: Iea6f10cf3ce1be5c112a2375d51c13687a8ab4c9
Reviewed-on: https://go-review.googlesource.com/9803
Reviewed-by: Austin Clements <austin@google.com>
When heapBitsSetType repeats a source bitmap with a scalar tail
(typ.ptrdata < typ.size), it lays out the tail upon reaching the end
of the source bitmap by simply increasing the number of bits claimed
to be in the incoming bit buffer. This causes later iterations to read
the appropriate number of zeros out of the bit buffer before starting
on the next repeat of the source bitmap.
Currently, however, later iterations of the loop continue to read bits
from the source bitmap *regardless of the number of bits currently in
the bit buffer*. The bit buffer can only hold 32 or 64 bits, so if the
scalar tail is large and the padding bits exceed the size of the bit
buffer, the read from the source bitmap on the next iteration will
shift the incoming bits into oblivion when it attempts to put them in
the bit buffer. When the buffer does eventually shift down to where
these bits were supposed to be, it will contain zeros. As a result,
words that should be marked as pointers on later repetitions are
marked as scalars, so the garbage collector does not trace them. If
this is the only reference to an object, it will be incorrectly freed.
Fix this by adding logic to drain the bit buffer down if it is large
instead of reading more bits from the source bitmap.
Fixes#11286.
Change-Id: I964432c4b9f1cec334fc8c3da0ff16460203feb6
Reviewed-on: https://go-review.googlesource.com/11360
Reviewed-by: Russ Cox <rsc@golang.org>
h_spans can be accessed concurrently without synchronization from
other threads, which means it needs the appropriate memory barriers on
weakly ordered machines. It happens to already have the necessary
memory barriers because all accesses to h_spans are currently
protected by the heap lock and the unlocks happen in exactly the
places where release barriers are needed, but it's easy to imagine
that this could change in the future. Document the fact that we're
depending on the barrier implied by the unlock.
Related to issue #9984.
Change-Id: I1bc3c95cd73361b041c8c95cd4bb92daf8c1f94a
Reviewed-on: https://go-review.googlesource.com/11361
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
This CL removes the single and racy use of mheap.arena_end outside
of the bookkeeping done in mHeap_init and mHeap_Alloc.
There should be no way for heapBitsForSpan to see a pointer to
an invalid span. This CL makes the check for this more precise by
checking that the pointer is between mheap_.arena_start and
mheap_.arena_used instead of mheap_.arena_end.
Change-Id: I1200b54353ee1eda002d92645fd8d26048600ceb
Reviewed-on: https://go-review.googlesource.com/11342
Reviewed-by: Austin Clements <austin@google.com>
In order to avoid a race with a concurrent write barrier or garbage
collector thread, any update to arena_used must be preceded by mapping
the corresponding heap bitmap and spans array memory. Otherwise, the
concurrent access may observe that a pointer falls within the heap
arena, but then attempt to access unmapped memory to look up its span
or heap bits.
Commit d57c889 fixed all of the places where we updated arena_used
immediately before mapping the heap bitmap and spans, but it missed
the one place where we update arena_used and depend on later code to
update it again and map the bitmap and spans. This creates a window
where the original race can still happen. This commit fixes this by
mapping the heap bitmap and spans before this arena_used update as
well. This code path is only taken when expanding the heap reservation
on 32-bit over a hole in the address space, so these extra mmap calls
should have negligible impact.
Fixes#10212, #11324.
Change-Id: Id67795e6c7563eb551873bc401e5cc997aaa2bd8
Reviewed-on: https://go-review.googlesource.com/11340
Run-TryBot: Austin Clements <austin@google.com>
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
The unsynchronized accesses to mheap_.arena_used in the concurrent
part of the garbage collector look like a problem waiting to happen.
In fact, they are safe, but the reason is somewhat subtle and
undocumented. This commit documents this reasoning.
Related to issue #9984.
Change-Id: Icdbf2329c1aa11dbe2396a71eb5fc2a85bd4afd5
Reviewed-on: https://go-review.googlesource.com/11254
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Currently its possible for the garbage collector to observe
uninitialized memory or stale heap bitmap bits on weakly ordered
architectures such as ARM and PPC. On such architectures, the stores
that zero newly allocated memory and initialize its heap bitmap may
move after a store in user code that makes the allocated object
observable by the garbage collector.
To fix this, add a "publication barrier" (also known as an "export
barrier") before returning from mallocgc. This is a store/store
barrier that ensures any write done by user code that makes the
returned object observable to the garbage collector will be ordered
after the initialization performed by mallocgc. No barrier is
necessary on the reading side because of the data dependency between
loading the pointer and loading the contents of the object.
Fixes one of the issues raised in #9984.
Change-Id: Ia3d96ad9c5fc7f4d342f5e05ec0ceae700cd17c8
Reviewed-on: https://go-review.googlesource.com/11083
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Minux Ma <minux@golang.org>
Reviewed-by: Martin Capitanio <capnm9@gmail.com>
Reviewed-by: Russ Cox <rsc@golang.org>
Some latency regressions have crept into our system over the past few
weeks. This CL fixes those by having the mark phase more aggressively
blacken objects so that the mark termination phase, a STW phase, has less
work to do. Three approaches were taken when the mark phase believes
it has no more work to do, ie all the work buffers are empty.
If things have gone well the mark phase is correct and there is
in fact little or no work. In that case the following items will
take very little time. If the mark phase is wrong this CL will
ferret that work out and give the mark phase a chance to deal with
it concurrently before mark termination begins.
When the mark phase first appears to be out of work, it does three things:
1) It switches from allocating white to allocating black to reduce the
number of unmarked objects reachable only from stacks.
2) It flushes and disables per-P GC work caches so all work must be in
globally visible work buffers.
3) It rescans the global roots---the BSS and data segments---so there
are fewer objects to blacken during mark termination. We do not rescan
stacks at this point, though that could be done in a later CL.
After these steps, it again drains the global work buffers.
On a lightly loaded machine the garbage benchmark has reduced the
number of GC cycles with latency > 10 ms from 83 out of 4083 cycles
down to 2 out of 3995 cycles. Maximum latency was reduced from
60+ msecs down to 20 ms.
Change-Id: I152285b48a7e56c5083a02e8e4485dd39c990492
Reviewed-on: https://go-review.googlesource.com/10590
Reviewed-by: Austin Clements <austin@google.com>
There were two issues.
1. Delayed EvGoSysExit could have been emitted during TraceStart,
while it had not yet emitted EvGoInSyscall.
2. Delayed EvGoSysExit could have been emitted during next tracing session.
Fixes#10476Fixes#11262
Change-Id: Iab68eb31cf38eb6eb6eee427f49c5ca0865a8c64
Reviewed-on: https://go-review.googlesource.com/9132
Reviewed-by: Russ Cox <rsc@golang.org>
In preparation for rename of cgocall_errno into cgocall and
asmcgocall_errno into asmcgocall in the fllowinng CL.
rsc requested CL 9387 to be split into two parts. This is first part.
Change-Id: I7434f0e4b44dd37017540695834bfcb1eebf0b2f
Reviewed-on: https://go-review.googlesource.com/11166
Reviewed-by: Ian Lance Taylor <iant@golang.org>
This fixes a hang during runtime.TestTraceStress.
It also fixes double-scan of stacks, which leads to
stack barrier installation failures.
Both of these have shown up as flaky failures on the dashboard.
Fixes#10941.
Change-Id: Ia2a5991ce2c9f43ba06ae1c7032f7c898dc990e0
Reviewed-on: https://go-review.googlesource.com/11089
Reviewed-by: Austin Clements <austin@google.com>
//go:systemstack means that the function must run on the system stack.
Add one use in runtime as a demonstration.
Fixes#9174.
Change-Id: I8d4a509cb313541426157da703f1c022e964ace4
Reviewed-on: https://go-review.googlesource.com/10840
Reviewed-by: Austin Clements <austin@google.com>
Run-TryBot: Austin Clements <austin@google.com>
Currently, when shrinkstack computes whether the halved stack
allocation will have enough room for the stack, it accounts for the
stack space that's actively in use but fails to leave extra room for
the stack guard space. As a result, *if* the minimum stack size is
small enough or the guard large enough, it may shrink the stack and
leave less than enough room to run nosplit functions. If the next
function called after the stack shrink is a nosplit function, it may
overflow the stack without noticing and overwrite non-stack memory.
We don't think this is happening under normal conditions right now.
The minimum stack allocation is 2K and the guard is 640 bytes. The
"worst case" stack shrink is from 4K (4048 bytes after stack barrier
array reservation) to 2K (2016 bytes after stack barrier array
reservation), which means the largest "used" size that will qualify
for shrinking is 4048/4 - 8 = 1004 bytes. After copying, that leaves
2016 - 1004 = 1012 bytes of available stack, which is significantly
more than the guard space.
If we were to reduce the minimum stack size to 1K or raise the guard
space above 1012 bytes, the logic in shrinkstack would no longer leave
enough space.
It's also possible to trigger this problem by setting
firstStackBarrierOffset to 0, which puts stack barriers in a debug
mode that steals away *half* of the stack for the stack barrier array
reservation. Then, the largest "used" size that qualifies for
shrinking is (4096/2)/4 - 8 = 504 bytes. After copying, that leaves
(2096/2) - 504 = 8 bytes of available stack; much less than the
required guard space. This causes failures like those in issue #11027
because func gc() shrinks its own stack and then immediately calls
casgstatus (a nosplit function), which overflows the stack and
overwrites a free list pointer in the neighboring span. However, since
this seems to require the special debug mode, we don't think it's
responsible for issue #11027.
To forestall all of these subtle issues, this commit modifies
shrinkstack to correctly account for the guard space when considering
whether to halve the stack allocation.
Change-Id: I7312584addc63b5bfe55cc384a1012f6181f1b9d
Reviewed-on: https://go-review.googlesource.com/10714
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
Issues #10240, #10541, #10941, #11023, #11027 and possibly others are
indicating memory corruption in the runtime. One of the easiest places
to both get corruption and detect it is in the allocator's free lists
since they appear throughout memory and follow strict invariants. This
commit adds a check when sweeping a span that its free list is sane
and, if not, it prints the corrupted free list and panics. Hopefully
this will help us collect more information on these failures.
Change-Id: I6d417bcaeedf654943a5e068bd76b58bb02d4a64
Reviewed-on: https://go-review.googlesource.com/10713
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
Run-TryBot: Austin Clements <austin@google.com>
A workaround for #10460.
Change-Id: I607a556561d509db6de047892f886fb565513895
Reviewed-on: https://go-review.googlesource.com/10819
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
While we're here, update the documentation and delete variables with no effect.
Change-Id: I4df0d266dff880df61b488ed547c2870205862f0
Reviewed-on: https://go-review.googlesource.com/10790
Reviewed-by: Austin Clements <austin@google.com>
A send on an unbuffered channel to a blocked receiver is the only
case in the runtime where one goroutine writes directly to the stack
of another. The garbage collector assumes that if a goroutine is
blocked, its stack contains no new pointers since the last time it ran.
The send on an unbuffered channel violates this, so it needs an
explicit write barrier. It has an explicit write barrier, but not one that
can handle a write to another stack. Use one that can (based on type bitmap
instead of heap bitmap).
To make this work, raise the limit for type bitmaps so that they are
used for all types up to 64 kB in size (256 bytes of bitmap).
(The runtime already imposes a limit of 64 kB for a channel element size.)
I have been unable to reproduce this problem in a simple test program.
Could help #11035.
Change-Id: I06ad994032d8cff3438c9b3eaa8d853915128af5
Reviewed-on: https://go-review.googlesource.com/10815
Reviewed-by: Austin Clements <austin@google.com>
This avoids a race with gcmarkwb_m that was leading to faults.
Fixes#10212.
Change-Id: I6fcf8d09f2692227063ce29152cb57366ea22487
Reviewed-on: https://go-review.googlesource.com/10816
Run-TryBot: Russ Cox <rsc@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
These were found by grepping the comments from the go code and feeding
the output to aspell.
Change-Id: Id734d6c8d1938ec3c36bd94a4dbbad577e3ad395
Reviewed-on: https://go-review.googlesource.com/10941
Reviewed-by: Aamir Khan <syst3m.w0rm@gmail.com>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Commit 1303957 was supposed to enable write barriers during the
concurrent scan phase, but it only enabled *calls* to the write
barrier during this phase. It failed to update the redundant list of
write-barrier-enabled phases in gcmarkwb_m, so it still wasn't greying
objects during the scan phase.
This commit fixes this by replacing the redundant list of phases in
gcmarkwb_m with simply checking writeBarrierEnabled. This is almost
certainly redundant with checks already done in callers, but the last
time we tried to remove these redundant checks everything got much
slower, so I'm leaving it alone for now.
Fixes#11105.
Change-Id: I00230a3cb80a008e749553a8ae901b409097e4be
Reviewed-on: https://go-review.googlesource.com/10801
Run-TryBot: Austin Clements <austin@google.com>
Reviewed-by: Minux Ma <minux@golang.org>
Stack barriers assume that writes through pointers to frames above the
current frame will get write barriers, and hence these frames do not
need to be re-scanned to pick up these changes. For normal writes,
this is true. However, there are places in the runtime that use
typedmemmove to potentially write through pointers to higher frames
(such as mapassign1). Currently, typedmemmove does not execute write
barriers if the destination is on the stack. If there's a stack
barrier between the current frame and the frame being modified with
typedmemmove, and the stack barrier is not otherwise hit, it's
possible that the garbage collector will never see the updated pointer
and incorrectly reclaim the object.
Fix this by making heapBitsBulkBarrier (which lies behind typedmemmove
and its variants) detect when the destination is in the stack and
unwind stack barriers up to the point, forcing mark termination to
later rescan the effected frame and collect these pointers.
Fixes#11084. Might be related to #10240, #10541, #10941, #11023,
#11027 and possibly others.
Change-Id: I323d6cd0f1d29fa01f8fc946f4b90e04ef210efd
Reviewed-on: https://go-review.googlesource.com/10791
Reviewed-by: Russ Cox <rsc@golang.org>
Currently, write barriers are only enabled after completion of the
concurrent scan phase, as we enter the concurrent mark phase. However,
stack barriers are installed during the scan phase and assume that
write barriers will track changes to frames above the stack
barriers. Since write barriers aren't enabled until after stack
barriers are installed, we may miss modifications to the stack that
happen after installing the stack barriers and before enabling write
barriers.
Fix this by enabling write barriers during the scan phase.
This commit intentionally makes the minimal change to do this (there's
only one line of code change; the rest are comment changes). At the
very least, we should consider eliminating the ragged barrier that's
intended to synchronize the enabling of write barriers, but now just
wastes time. I've included a large comment about extensions and
alternative designs.
Change-Id: Ib20fede794e4fcb91ddf36f99bd97344d7f96421
Reviewed-on: https://go-review.googlesource.com/10795
Reviewed-by: Russ Cox <rsc@golang.org>
Currently checkmarks mode fails to rescan stacks because it sees the
leftover state bits indicating that the stacks haven't changed since
the last scan. As a result, it won't detect lost marks caused by
failing to scan stacks correctly during regular garbage collection.
Fix this by marking all stacks dirty before performing the checkmark
phase.
Change-Id: I1f06882bb8b20257120a4b8e7f95bb3ffc263895
Reviewed-on: https://go-review.googlesource.com/10794
Reviewed-by: Russ Cox <rsc@golang.org>
All of the architectures except ppc64 have only "RET" for the return
mnemonic. ppc64 used to have only "RETURN", but commit cf06ea6
introduced RET as a synonym for RETURN to make ppc64 consistent with
the other architectures. However, that commit was never followed up to
make the code itself consistent by eliminating uses of RETURN.
This commit replaces all uses of RETURN in the ppc64 assembly with
RET.
This was done with
sed -i 's/\<RETURN\>/RET/' **/*_ppc64x.s
plus one manual change to syscall/asm.s.
Change-Id: I3f6c8d2be157df8841d48de988ee43f3e3087995
Reviewed-on: https://go-review.googlesource.com/10672
Reviewed-by: Rob Pike <r@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
Reviewed-by: Minux Ma <minux@golang.org>
gc should ideally consider this an error too; see golang/go#8560.
Change-Id: Ieee71c4ecaff493d7f83e15ba8c8a04ee90a4cf1
Reviewed-on: https://go-review.googlesource.com/10757
Reviewed-by: Robert Griesemer <gri@golang.org>
Currently the stack barriers are installed at the next frame boundary
after gp.sched.sp + 1024*2^n for n=0,1,2,... However, when a G is in a
system call, we set gp.sched.sp to 0, which causes stack barriers to
be installed at *every* frame. This easily overflows the slice we've
reserved for storing the stack barrier information, and causes a
"slice bounds out of range" panic in gcInstallStackBarrier.
Fix this by using gp.syscallsp instead of gp.sched.sp if it's
non-zero. This is the same logic that gentraceback uses to determine
the current SP.
Fixes#11049.
Change-Id: Ie40eeee5bec59b7c1aa715a7c17aa63b1f1cf4e8
Reviewed-on: https://go-review.googlesource.com/10755
Reviewed-by: Russ Cox <rsc@golang.org>
See golang.org/s/go15gomaxprocs for details.
Change-Id: I8de5df34fa01d31d78f0194ec78a2474c281243c
Reviewed-on: https://go-review.googlesource.com/10668
Reviewed-by: Rob Pike <r@golang.org>
Otherwise subsequent tests won't see any modified GOROOT.
With this CL I can move my GOROOT, set GOROOT to the new location, and
the runtime tests pass. Previously the crash_tests would instead look
for the GOROOT baked into the binary, instead of the env var:
--- FAIL: TestGcSys (0.01s)
crash_test.go:92: building source: exit status 2
go: cannot find GOROOT directory: /home/bradfitz/go
--- FAIL: TestGCFairness (0.01s)
crash_test.go:92: building source: exit status 2
go: cannot find GOROOT directory: /home/bradfitz/go
--- FAIL: TestGdbPython (0.07s)
runtime-gdb_test.go:64: building source exit status 2
go: cannot find GOROOT directory: /home/bradfitz/go
--- FAIL: TestLargeStringConcat (0.01s)
crash_test.go:92: building source: exit status 2
go: cannot find GOROOT directory: /home/bradfitz/go
Update #10029
Change-Id: If91be0f04d3acdcf39a9e773a4e7905a446bc477
Reviewed-on: https://go-review.googlesource.com/10685
Reviewed-by: Andrew Gerrand <adg@golang.org>
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
Currently the GODEBUG=gctrace=1 trace line includes "@n.nnns" to
indicate the time that the GC cycle ended relative to the time the
program started. This was meant to be consistent with the utilization
as of the end of the cycle, which is printed next on the trace line,
but it winds up just being confusing and unexpected.
Change the trace line to include the time that the GC cycle started
relative to the time the program started.
Change-Id: I7d64580cd696eb17540716d3e8a74a9d6ae50650
Reviewed-on: https://go-review.googlesource.com/10634
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
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 there's a race between stopg scanning another G's stack and
the G reaching a preemption point and scanning its own stack. When
this race occurs, the G's stack is scanned twice. Currently this is
okay, so this race is benign.
However, we will shortly be adding stack barriers during the first
stack scan, so scanning will no longer be idempotent. To prepare for
this, this change ensures that each stack is scanned only once during
each GC phase by checking the flag that indicates that the stack has
been scanned in this phase before scanning the stack.
Change-Id: Id9f4d5e2e5b839bc3f200ec1723a4a12dd677ab4
Reviewed-on: https://go-review.googlesource.com/10458
Reviewed-by: Rick Hudson <rlh@golang.org>
The stack barrier code will need a bookkeeping structure to keep track
of the overwritten return PCs. This commit introduces and allocates
this structure, but does not yet use the structure.
We don't want to allocate space for this structure during garbage
collection, so this commit allocates it along with the allocation of
the corresponding stack. However, we can't do a regular allocation in
newstack because mallocgc may itself grow the stack (which would lead
to a recursive allocation). Hence, this commit makes the bookkeeping
structure part of the stack allocation itself by stealing the
necessary space from the top of the stack allocation. Since the size
of this bookkeeping structure is logarithmic in the size of the stack,
this has minimal impact on stack behavior.
Change-Id: Ia14408be06aafa9ca4867f4e70bddb3fe0e96665
Reviewed-on: https://go-review.googlesource.com/10313
Reviewed-by: Russ Cox <rsc@golang.org>
Currently the runtime assumes that the allocation for the stack is
exactly [stack.lo, stack.hi). We're about to steal a small part of
this allocation for per-stack GC metadata. To prepare for this, this
commit adds a field to the G for the allocated size of the stack.
With this change, stack.lo and stack.hi continue to act as the true
bounds on the stack, but are no longer also used as the bounds on the
stack allocation.
(I also tried this the other way around, where stack.lo and stack.hi
remained the allocation bounds and I introduced a new top of stack.
However, there are far more places that assume stack.hi is the true
top of the stack than there are places that assume it's the top of the
allocation.)
Change-Id: Ifa9d956753be53d286d09cbc73d47fb34a18c0c6
Reviewed-on: https://go-review.googlesource.com/10312
Reviewed-by: Russ Cox <rsc@golang.org>
Currently signalstack takes a lower limit and a length and all calls
hard-code the passed length. Change the API to take a *stack and
compute the lower limit and length from the passed stack.
This will make it easier for the runtime to steal some space from the
top of the stack since it eliminates the hard-coded stack sizes.
Change-Id: I7d2a9f45894b221f4e521628c2165530bbc57d53
Reviewed-on: https://go-review.googlesource.com/10311
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
Currently we truncate gctrace clock and CPU times to millisecond
precision. As a result, many phases are typically printed as 0, which
is fine for user consumption, but makes gathering statistics and
reports over GC traces difficult.
In 1.4, the gctrace line printed times in microseconds. This was
better for statistics, but not as easy for users to read or interpret,
and it generally made the trace lines longer.
This change strikes a balance between these extremes by printing
milliseconds, but including the decimal part to two significant
figures down to microsecond precision. This remains easy to read and
interpret, but includes more precision when it's useful.
For example, where the code currently prints,
gc #29 @1.629s 0%: 0+2+0+12+0 ms clock, 0+2+0+0/12/0+0 ms cpu, 4->4->2 MB, 4 MB goal, 1 P
this prints,
gc #29 @1.629s 0%: 0.005+2.1+0+12+0.29 ms clock, 0.005+2.1+0+0/12/0+0.29 ms cpu, 4->4->2 MB, 4 MB goal, 1 P
Fixes#10970.
Change-Id: I249624779433927cd8b0947b986df9060c289075
Reviewed-on: https://go-review.googlesource.com/10554
Reviewed-by: Russ Cox <rsc@golang.org>
runtime.GC() is intentionally very weakly specified. However, it is so
weakly specified that it's difficult to know that it's being used
correctly for its one intended use case: to ensure garbage collection
has run in a test that is garbage-sensitive. In particular, it is
unclear whether it is synchronous or asynchronous. In the old STW
collector this was essentially self-evident; short of queuing up a
garbage collection to run later, it had to be synchronous. However,
with the concurrent collector, there's evidence that people are
inferring that it may be asynchronous (e.g., issue #10986), as this is
both unclear in the documentation and possible in the implementation.
In fact, runtime.GC() runs a fully synchronous STW collection. We
probably don't want to commit to this exact behavior. But we can
commit to the essential property that tests rely on: that runtime.GC()
does not return until the GC has finished.
Change-Id: Ifc3045a505e1898ecdbe32c1f7e80e2e9ffacb5b
Reviewed-on: https://go-review.googlesource.com/10488
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Rick Hudson <rlh@golang.org>
TestGoroutineParallelism can deadlock if the GC runs during the
test. Currently it tries to prevent this by forcing a GC before the
test, but this is best effort and fails completely if GOGC is very low
for testing.
This change replaces this best-effort fix with simply setting GOGC to
off for the duration of the test.
Change-Id: I8229310833f241b149ebcd32845870c1cb14e9f8
Reviewed-on: https://go-review.googlesource.com/10454
Reviewed-by: Russ Cox <rsc@golang.org>
Most runtime tests that invoke the compiler to build a sub-test binary
do so with a special environment constructed by testEnv that strips
out environment variables that should apply to the test but not to the
build.
Fix TestGdbPython to use this test environment when invoking go build,
like other tests do.
Change-Id: Iafdf89d4765c587cbebc427a5d61cb8a7e71b326
Reviewed-on: https://go-review.googlesource.com/10455
Reviewed-by: Russ Cox <rsc@golang.org>
Implement the changes from CL 10173 on OpenBSD.
Change-Id: I2db1cd8141fd392a34753a1b8113e2e0401173b9
Reviewed-on: https://go-review.googlesource.com/10342
Run-TryBot: Ian Lance Taylor <iant@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Ian proposed an improved way of handling signals masks in Go, motivated
by a problem where the Android java runtime expects certain signals to
be blocked for all JVM threads. Discussion here
https://groups.google.com/forum/#!topic/golang-dev/_TSCkQHJt6g
Ian's text is used in the following:
A Go program always needs to have the synchronous signals enabled.
These are the signals for which _SigPanic is set in sigtable, namely
SIGSEGV, SIGBUS, SIGFPE.
A Go program that uses the os/signal package, and calls signal.Notify,
needs to have at least one thread which is not blocking that signal,
but it doesn't matter much which one.
Unix programs do not change signal mask across execve. They inherit
signal masks across fork. The shell uses this fact to some extent;
for example, the job control signals (SIGTTIN, SIGTTOU, SIGTSTP) are
blocked for commands run due to backquote quoting or $().
Our current position on signal masks was not thought out. We wandered
into step by step, e.g., http://golang.org/cl/7323067 .
This CL does the following:
Introduce a new platform hook, msigsave, that saves the signal mask of
the current thread to m.sigsave.
Call msigsave from needm and newm.
In minit grab set up the signal mask from m.sigsave and unblock the
essential synchronous signals, and SIGILL, SIGTRAP, SIGPROF, SIGSTKFLT
(for systems that have it).
In unminit, restore the signal mask from m.sigsave.
The first time that os/signal.Notify is called, start a new thread whose
only purpose is to update its signal mask to make sure signals for
signal.Notify are unblocked on at least one thread.
The effect on Go programs will be that if they are invoked with some
non-synchronous signals blocked, those signals will normally be
ignored. Previously, those signals would mostly be ignored. A change
in behaviour will occur for programs started with any of these signals
blocked, if they receive the signal: SIGHUP, SIGINT, SIGQUIT, SIGABRT,
SIGTERM. Previously those signals would always cause a crash (unless
using the os/signal package); with this change, they will be ignored
if the program is started with the signal blocked (and does not use
the os/signal package).
./all.bash completes successfully on linux/amd64.
OpenBSD is missing the implementation.
Change-Id: I188098ba7eb85eae4c14861269cc466f2aa40e8c
Reviewed-on: https://go-review.googlesource.com/10173
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Given a call frame F of size N where the return values start at offset R,
callwritebarrier was instructing heapBitsBulkBarrier to scan the block
of memory [F+R, F+R+N). It should only scan [F+R, F+N). The extra N-R
bytes scanned might lead into the next allocated block in memory.
Because the scan was consulting the heap bitmap for type information,
scanning into the next block normally "just worked" in the sense of
not crashing.
Scanning the extra N-R bytes of memory is a problem mainly because
it causes the GC to consider pointers that might otherwise not be
considered, leading it to retain objects that should actually be freed.
This is very difficult to detect.
Luckily, juju turned up a case where the heap bitmap and the memory
were out of sync for the block immediately after the call frame, so that
heapBitsBulkBarrier saw an obvious non-pointer where it expected a
pointer, causing a loud crash.
Why is there a non-pointer in memory that the heap bitmap records as
a pointer? That is more difficult to answer. At least one way that it
could happen is that allocations containing no pointers at all do not
update the heap bitmap. So if heapBitsBulkBarrier walked out of the
current object and into a no-pointer object and consulted those bitmap
bits, it would be misled. This doesn't happen in general because all
the paths to heapBitsBulkBarrier first check for the no-pointer case.
This may or may not be what happened, but it's the only scenario
I've been able to construct.
I tried for quite a while to write a simple test for this and could not.
It does fix the juju crash, and it is clearly an improvement over the
old code.
Fixes#10844.
Change-Id: I53982c93ef23ef93155c4086bbd95a4c4fdaac9a
Reviewed-on: https://go-review.googlesource.com/10317
Reviewed-by: Austin Clements <austin@google.com>
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>
This is dead code. If you want to quiesce the system the
preferred way is to use forEachP(func(*p){}).
Change-Id: Ic7677a5dd55e3639b99e78ddeb2c71dd1dd091fa
Reviewed-on: https://go-review.googlesource.com/10267
Reviewed-by: Austin Clements <austin@google.com>
Prior to this CL whenever the GC marking was enabled and
a P was looking for work we supplied a G to help
the GC do its marking tasks. Once this G finished all
the marking available it would release the P to find another
available G. In the case where there was no work the P would drop
into findrunnable which would execute the mark helper G which would
immediately return and the P would drop into findrunnable again repeating
the process. Since the P was always given a G to run it never blocks.
This CL first checks if the GC mark helper G has available work and if
not the P immediately falls through to its blocking logic.
Fixes#10901
Change-Id: I94ac9646866ba64b7892af358888bc9950de23b5
Reviewed-on: https://go-review.googlesource.com/10189
Reviewed-by: Austin Clements <austin@google.com>
Currently setGCPercent sets heapminimum to heapminimum*GOGC/100. The
real intent is to set heapminimum to a scaled multiple of a fixed
default heap minimum, not to scale heapminimum based on its current
value. This turns out to be okay because setGCPercent is only called
once and heapminimum is initially set to this default heap minimum.
However, the code as written is confusing, especially since
setGCPercent is otherwise written so it could be called again to
change GOGC. Fix this by introducing a defaultHeapMinimum constant and
using this instead of the current value of heapminimum to compute the
scaled heap minimum.
As part of this, this commit improves the documentation on
heapminimum.
Change-Id: I4eb82c73dc2eb44a6e5a17c780a747a2e73d7493
Reviewed-on: https://go-review.googlesource.com/10181
Reviewed-by: Russ Cox <rsc@golang.org>
This is a duplicate of CL 9491.
That CL broke the build due to pprof shortcomings
and was reverted in CL 9565.
CL 9623 fixed pprof, so this can go in again.
Fixes#10659.
Change-Id: If470fc90b3db2ade1d161b4417abd2f5c6c330b8
Reviewed-on: https://go-review.googlesource.com/10212
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Currently, forEachP reuses the stopwait and stopnote fields from
stopTheWorld to track how many Ps have not responded to the safe-point
request and to sleep until all Ps have responded.
It was assumed this was safe because both stopTheWorld and forEachP
must occur under the worlsema and hence stopwait and stopnote cannot
be used for both purposes simultaneously and callers could always
determine the appropriate use based on sched.gcwaiting (which is only
set by stopTheWorld). However, this is not the case, since it's
possible for there to be a window between when an M observes that
gcwaiting is set and when it checks stopwait during which stopwait
could have changed meanings. When this happens, the M decrements
stopwait and may wakeup stopnote, but does not otherwise participate
in the forEachP protocol. As a result, stopwait is decremented too
many times, so it may reach zero before all Ps have run the safe-point
function, causing forEachP to wake up early. It will then either
observe that some P has not run the safe-point function and panic with
"P did not run fn", or the remaining P (or Ps) will run the safe-point
function before it wakes up and it will observe that stopwait is
negative and panic with "not stopped".
Fix this problem by giving forEachP its own safePointWait and
safePointNote fields.
One known sequence of events that can cause this race is as
follows. It involves three actors:
G1 is running on M1 on P1. P1 has an empty run queue.
G2/M2 is in a blocked syscall and has lost its P. (The details of this
don't matter, it just needs to be in a position where it needs to grab
an idle P.)
GC just started on G3/M3/P3. (These aren't very involved, they just
have to be separate from the other G's, M's, and P's.)
1. GC calls stopTheWorld(), which sets sched.gcwaiting to 1.
Now G1/M1 begins to enter a syscall:
2. G1/M1 invokes reentersyscall, which sets the P1's status to
_Psyscall.
3. G1/M1's reentersyscall observes gcwaiting != 0 and calls
entersyscall_gcwait.
4. G1/M1's entersyscall_gcwait blocks acquiring sched.lock.
Back on GC:
5. stopTheWorld cas's P1's status to _Pgcstop, does other stuff, and
returns.
6. GC does stuff and then calls startTheWorld().
7. startTheWorld() calls procresize(), which sets P1's status to
_Pidle and puts P1 on the idle list.
Now G2/M2 returns from its syscall and takes over P1:
8. G2/M2 returns from its blocked syscall and gets P1 from the idle
list.
9. G2/M2 acquires P1, which sets P1's status to _Prunning.
10. G2/M2 starts a new syscall and invokes reentersyscall, which sets
P1's status to _Psyscall.
Back on G1/M1:
11. G1/M1 finally acquires sched.lock in entersyscall_gcwait.
At this point, G1/M1 still thinks it's running on P1. P1's status is
_Psyscall, which is consistent with what G1/M1 is doing, but it's
_Psyscall because *G2/M2* put it in to _Psyscall, not G1/M1. This is
basically an ABA race on P1's status.
Because forEachP currently shares stopwait with stopTheWorld. G1/M1's
entersyscall_gcwait observes the non-zero stopwait set by forEachP,
but mistakes it for a stopTheWorld. It cas's P1's status from
_Psyscall (set by G2/M2) to _Pgcstop and proceeds to decrement
stopwait one more time than forEachP was expecting.
Fixes#10618. (See the issue for details on why the above race is safe
when forEachP is not involved.)
Prior to this commit, the command
stress ./runtime.test -test.run TestFutexsleep\|TestGoroutineProfile
would reliably fail after a few hundred runs. With this commit, it
ran for over 2 million runs and never crashed.
Change-Id: I9a91ea20035b34b6e5f07ef135b144115f281f30
Reviewed-on: https://go-review.googlesource.com/10157
Reviewed-by: Russ Cox <rsc@golang.org>
Currently, startTheWorld releases worldsema before starting the
world. Since startTheWorld can change gomaxprocs after allowing Ps to
run, this means that gomaxprocs can change while another P holds
worldsema.
Unfortunately, the garbage collector and forEachP assume that holding
worldsema protects against changes in gomaxprocs (which it *almost*
does). In particular, this is causing somewhat frequent "P did not run
fn" crashes in forEachP in the runtime tests because gomaxprocs is
changing between the several loops that forEachP does over all the Ps.
Fix this by only releasing worldsema after the world is started.
This relates to issue #10618. forEachP still fails under stress
testing, but much less frequently.
Change-Id: I085d627b70cca9ebe9af28fe73b9872f1bb224ff
Reviewed-on: https://go-review.googlesource.com/10156
Reviewed-by: Russ Cox <rsc@golang.org>
Currently, startTheWorld clears preemptoff for the current M before
starting the world. A few callers increment m.locks around
startTheWorld, presumably to prevent preemption any time during
starting the world. This is almost certainly pointless (none of the
other callers do this), but there's no harm in making startTheWorld
keep preemption disabled until it's all done, which definitely lets us
drop these m.locks manipulations.
Change-Id: I8a93658abd0c72276c9bafa3d2c7848a65b4691a
Reviewed-on: https://go-review.googlesource.com/10155
Reviewed-by: Russ Cox <rsc@golang.org>
There are several steps to stopping and starting the world and
currently they're open-coded in several places. The garbage collector
is the only thing that needs to stop and start the world in a
non-trivial pattern. Replace all other uses with calls to higher-level
functions that implement the entire pattern necessary to stop and
start the world.
This is a pure refectoring and should not change any code semantics.
In the following commits, we'll make changes that are easier to do
with this abstraction in place.
This commit renames the old starttheworld to startTheWorldWithSema.
This is a slight misnomer right now because the callers release
worldsema just before calling this. However, a later commit will swap
these and I don't want to think of another name in the mean time.
Change-Id: I5dc97f87b44fb98963c49c777d7053653974c911
Reviewed-on: https://go-review.googlesource.com/10154
Reviewed-by: Russ Cox <rsc@golang.org>
In order to avoid deadlocks, startGC avoids kicking off GC if locks
are held by the calling M. However, it currently fails to check
preemptoff, which is the other way to disable preemption.
Fix this by adding a check for preemptoff.
Change-Id: Ie1083166e5ba4af5c9d6c5a42efdfaaef41ca997
Reviewed-on: https://go-review.googlesource.com/10153
Reviewed-by: Russ Cox <rsc@golang.org>
It is misleading when stack trace say:
signal arrived during cgo execution
but we are not in cgo call.
Change-Id: I627e2f2bdc7755074677f77f21befc070a101914
Reviewed-on: https://go-review.googlesource.com/9190
Reviewed-by: Russ Cox <rsc@golang.org>
Currently, runqsteal steals Gs from another P into an intermediate
buffer and then copies those Gs into the current P's run queue. This
intermediate buffer itself was moved from the stack to the P in commit
c4fe503 to eliminate the cost of zeroing it on every steal.
This commit follows up c4fe503 by stealing directly into the current
P's run queue, which eliminates the copy and the need for the
intermediate buffer. The update to the tail pointer is only committed
once the entire steal operation has succeeded, so the semantics of
stealing do not change.
Change-Id: Icdd7a0eb82668980bf42c0154b51eef6419fdd51
Reviewed-on: https://go-review.googlesource.com/9998
Reviewed-by: Russ Cox <rsc@golang.org>
Run-TryBot: Austin Clements <austin@google.com>
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>
Preallocating them in reflect means that
(1) if you say _ = PtrTo(ArrayOf(1000000000, reflect.TypeOf(byte(0)))), you just allocated 1GB of data
(2) if you say it again, that's *another* GB of data.
The only use of t.zero in the runtime is for map elements.
Delay the allocation until the creation of a map with that element type,
and share the zeros.
The one downside of the shared zero is that it's not garbage collected,
but it's also never written, so the OS should be able to handle it fairly
efficiently.
Change-Id: I56b098a091abf3ac0945de28ebef9a6c08e76614
Reviewed-on: https://go-review.googlesource.com/10111
Reviewed-by: Keith Randall <khr@golang.org>
This reduces the depth of the inlining at a particular call site.
The inliner introduces many temporary variables, and the compiler can do
a better job with fewer. Being verbose in the bodies of these helper functions
seems like a reasonable tradeoff: the uses are still just as readable, and
they run faster in some important cases.
Change-Id: I5323976ed3704d0acd18fb31176cfbf5ba23a89c
Reviewed-on: https://go-review.googlesource.com/9883
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
One important use case is a pipeline computation that pass values
from one Goroutine to the next and then exits or is placed in a
wait state. If GOMAXPROCS > 1 a Goroutine running on P1 will enable
another Goroutine and then immediately make P1 available to execute
it. We need to prevent other Ps from stealing the G that P1 is about
to execute. Otherwise the Gs can thrash between Ps causing unneeded
synchronization and slowing down throughput.
Fix this by changing the stealing logic so that when a P attempts to
steal the only G on some other P's run queue, it will pause
momentarily to allow the victim P to schedule the G.
As part of optimizing stealing we also use a per P victim queue
move stolen gs. This eliminates the zeroing of a stack local victim
queue which turned out to be expensive.
This CL is a necessary but not sufficient prerequisite to changing
the default value of GOMAXPROCS to something > 1 which is another
CL/discussion.
For highly serialized programs, such as GoroutineRing below this can
make a large difference. For larger and more parallel programs such
as the x/benchmarks there is no noticeable detriment.
~/work/code/src/rsc.io/benchstat/benchstat old.txt new.txt
name old mean new mean delta
GoroutineRing 30.2µs × (0.98,1.01) 30.1µs × (0.97,1.04) ~ (p=0.941)
GoroutineRing-2 113µs × (0.91,1.07) 30µs × (0.98,1.03) -73.17% (p=0.004)
GoroutineRing-4 144µs × (0.98,1.02) 32µs × (0.98,1.01) -77.69% (p=0.000)
GoroutineRingBuf 32.7µs × (0.97,1.03) 32.5µs × (0.97,1.02) ~ (p=0.795)
GoroutineRingBuf-2 120µs × (0.92,1.08) 33µs × (1.00,1.00) -72.48% (p=0.004)
GoroutineRingBuf-4 138µs × (0.92,1.06) 33µs × (1.00,1.00) -76.21% (p=0.003)
The bench benchmarks show little impact.
old new
garbage 7032879 7011696
httpold 25509 25301
splayold 1022073 1019499
jsonold 28230624 28081433
Change-Id: I228c48fed8d85c9bbef16a7edc53ab7898506f50
Reviewed-on: https://go-review.googlesource.com/9872
Reviewed-by: Austin Clements <austin@google.com>
Running these tests on the system stack is problematic because they
allocate Ps, which are large enough to overflow the system stack if
they are stack-allocated. It used to be necessary to run these tests
on the system stack because they were written in C, but since this is
no longer the case, we can fix this problem by simply not running the
tests on the system stack.
This also means we no longer need the hack in one of these tests that
forces the allocated Ps to escape to the heap, so eliminate that as
well.
Change-Id: I9064f5f8fd7f7b446ff39a22a70b172cfcb2dc57
Reviewed-on: https://go-review.googlesource.com/9923
Reviewed-by: Rick Hudson <rlh@golang.org>
Run-TryBot: Austin Clements <austin@google.com>
The status buffer built by the exit function
was not nil-terminated.
Fixes#10789.
Change-Id: I2d34ac50a19d138176c4b47393497ba7070d5b61
Reviewed-on: https://go-review.googlesource.com/9953
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
Once added to the signal queue, the pointer passed to the
signal handler could no longer be valid. Instead of passing
the pointer to the note string, we recopy the value of the
note string to a static array in the signal queue.
Fixes#10784.
Change-Id: Iddd6837b58a14dfaa16b069308ae28a7b8e0965b
Reviewed-on: https://go-review.googlesource.com/9950
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
This:
1) Defines the ABI hash of a package (as the SHA1 of the __.PKGDEF)
2) Defines the ABI hash of a shared library (sort the packages by import
path, concatenate the hashes of the packages and SHA1 that)
3) When building a shared library, compute the above value and define a
global symbol that points to a go string that has the hash as its value.
4) When linking against a shared library, read the abi hash from the
library and put both the value seen at link time and a reference
to the global symbol into the moduledata.
5) During runtime initialization, check that the hash seen at link time
still matches the hash the global symbol points to.
Change-Id: Iaa54c783790e6dde3057a2feadc35473d49614a5
Reviewed-on: https://go-review.googlesource.com/8773
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Run-TryBot: Michael Hudson-Doyle <michael.hudson@canonical.com>
addmoduledata is called from a .init_array function and need to follow the
platform ABI. It contains accesses to global data which are rewritten to use
R15 by the assembler, and as R15 is callee-save we need to save it.
Change-Id: I03893efb1576aed4f102f2465421f256f3bb0f30
Reviewed-on: https://go-review.googlesource.com/9941
Reviewed-by: Ian Lance Taylor <iant@golang.org>
The current implementation of typedmemmove walks the ptrmask
in the type to find out where pointers are. This led to turning off
GC programs for the Go 1.5 dev cycle, so that there would always
be a ptrmask. Instead of also interpreting the GC programs,
interpret the heap bitmap, which we know must be available and
up to date. (There is no point to write barriers when writing outside
the heap.)
This CL is only about correctness. The next CL will optimize the code.
Change-Id: Id1305c7c071fd2734ab96634b0e1c745b23fa793
Reviewed-on: https://go-review.googlesource.com/9886
Reviewed-by: Austin Clements <austin@google.com>
We want typedmemmove to use the heap bitmap to determine
where pointers are, instead of reinterpreting the type information.
The heap bitmap is simpler to access.
In general, typedmemmove will need to be able to look up the bits
for any word and find valid pointer information, so fill even after the
dead marker. Not filling after the dead marker was an optimization
I introduced only a few days ago, when reintroducing the dead marker
code. At the time I said it probably wouldn't last, and it didn't.
Change-Id: I6ba01bff17ddee1ff429f454abe29867ec60606e
Reviewed-on: https://go-review.googlesource.com/9885
Reviewed-by: Austin Clements <austin@google.com>
Moving them up makes them properly aligned on 32-bit systems.
There are some odd fields above them right now
(like fixalloc and mutex maybe).
Change-Id: I57851a5bbb2e7cc339712f004f99bb6c0cce0ca5
Reviewed-on: https://go-review.googlesource.com/9889
Reviewed-by: Austin Clements <austin@google.com>
The new(uint64) was moving to the stack, which may not be aligned.
Change-Id: Iad070964202001b52029494d43e299fed980f939
Reviewed-on: https://go-review.googlesource.com/9787
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
Reviewed-by: David Chase <drchase@google.com>
Reintroduce an optimization discarded during the initial conversion
from 4-bit heap bitmaps to 2-bit heap bitmaps: when we reach the
place in the bitmap where there are no more pointers, mark that position
for the GC so that it can avoid scanning past that place.
During heapBitsSetType we can also avoid initializing heap bitmap
beyond that location, which gives a bit of a win compared to Go 1.4.
This particular optimization (not initializing the heap bitmap) may not last:
we might change typedmemmove to use the heap bitmap, in which
case it would all need to be initialized. The early stop in the GC scan
will stay no matter what.
Compared to Go 1.4 (github.com/rsc/go, branch go14bench):
name old mean new mean delta
SetTypeNode64 80.7ns × (1.00,1.01) 57.4ns × (1.00,1.01) -28.83% (p=0.000)
SetTypeNode64Dead 80.5ns × (1.00,1.01) 13.1ns × (0.99,1.02) -83.77% (p=0.000)
SetTypeNode64Slice 2.16µs × (1.00,1.01) 1.54µs × (1.00,1.01) -28.75% (p=0.000)
SetTypeNode64DeadSlice 2.16µs × (1.00,1.01) 1.52µs × (1.00,1.00) -29.74% (p=0.000)
Compared to previous CL:
name old mean new mean delta
SetTypeNode64 56.7ns × (1.00,1.00) 57.4ns × (1.00,1.01) +1.19% (p=0.000)
SetTypeNode64Dead 57.2ns × (1.00,1.00) 13.1ns × (0.99,1.02) -77.15% (p=0.000)
SetTypeNode64Slice 1.56µs × (1.00,1.01) 1.54µs × (1.00,1.01) -0.89% (p=0.000)
SetTypeNode64DeadSlice 1.55µs × (1.00,1.01) 1.52µs × (1.00,1.00) -2.23% (p=0.000)
This is the last CL in the sequence converting from the 4-bit heap
to the 2-bit heap, with all the same optimizations reenabled.
Compared to before that process began (compared to CL 9701 patch set 1):
name old mean new mean delta
BinaryTree17 5.87s × (0.94,1.09) 5.91s × (0.96,1.06) ~ (p=0.578)
Fannkuch11 4.32s × (1.00,1.00) 4.32s × (1.00,1.00) ~ (p=0.474)
FmtFprintfEmpty 89.1ns × (0.95,1.16) 89.0ns × (0.93,1.10) ~ (p=0.942)
FmtFprintfString 283ns × (0.98,1.02) 298ns × (0.98,1.06) +5.33% (p=0.000)
FmtFprintfInt 284ns × (0.98,1.04) 286ns × (0.98,1.03) ~ (p=0.208)
FmtFprintfIntInt 486ns × (0.98,1.03) 498ns × (0.97,1.06) +2.48% (p=0.000)
FmtFprintfPrefixedInt 400ns × (0.99,1.02) 408ns × (0.98,1.02) +2.23% (p=0.000)
FmtFprintfFloat 566ns × (0.99,1.01) 587ns × (0.98,1.01) +3.69% (p=0.000)
FmtManyArgs 1.91µs × (0.99,1.02) 1.94µs × (0.99,1.02) +1.81% (p=0.000)
GobDecode 15.5ms × (0.98,1.05) 15.8ms × (0.98,1.03) +1.94% (p=0.002)
GobEncode 11.9ms × (0.97,1.03) 12.0ms × (0.96,1.09) ~ (p=0.263)
Gzip 648ms × (0.99,1.01) 648ms × (0.99,1.01) ~ (p=0.992)
Gunzip 143ms × (1.00,1.00) 143ms × (1.00,1.01) ~ (p=0.585)
HTTPClientServer 89.2µs × (0.99,1.02) 90.3µs × (0.98,1.01) +1.24% (p=0.000)
JSONEncode 32.3ms × (0.97,1.06) 31.6ms × (0.99,1.01) -2.29% (p=0.000)
JSONDecode 106ms × (0.99,1.01) 107ms × (1.00,1.01) +0.62% (p=0.000)
Mandelbrot200 6.02ms × (1.00,1.00) 6.03ms × (1.00,1.01) ~ (p=0.250)
GoParse 6.57ms × (0.97,1.06) 6.53ms × (0.99,1.03) ~ (p=0.243)
RegexpMatchEasy0_32 162ns × (1.00,1.00) 161ns × (1.00,1.01) -0.80% (p=0.000)
RegexpMatchEasy0_1K 561ns × (0.99,1.02) 541ns × (0.99,1.01) -3.67% (p=0.000)
RegexpMatchEasy1_32 145ns × (0.95,1.04) 138ns × (1.00,1.00) -5.04% (p=0.000)
RegexpMatchEasy1_1K 864ns × (0.99,1.04) 887ns × (0.99,1.01) +2.57% (p=0.000)
RegexpMatchMedium_32 255ns × (0.99,1.04) 253ns × (0.99,1.01) -1.05% (p=0.012)
RegexpMatchMedium_1K 73.9µs × (0.98,1.04) 72.8µs × (1.00,1.00) -1.51% (p=0.005)
RegexpMatchHard_32 3.92µs × (0.98,1.04) 3.85µs × (1.00,1.01) -1.88% (p=0.002)
RegexpMatchHard_1K 120µs × (0.98,1.04) 117µs × (1.00,1.01) -2.02% (p=0.001)
Revcomp 936ms × (0.95,1.08) 922ms × (0.97,1.08) ~ (p=0.234)
Template 130ms × (0.98,1.04) 126ms × (0.99,1.01) -2.99% (p=0.000)
TimeParse 638ns × (0.98,1.05) 628ns × (0.99,1.01) -1.54% (p=0.004)
TimeFormat 674ns × (0.99,1.01) 668ns × (0.99,1.01) -0.80% (p=0.001)
The slowdown of the first few benchmarks seems to be due to the new
atomic operations for certain small size allocations. But the larger
benchmarks mostly improve, probably due to the decreased memory
pressure from having half as much heap bitmap.
CL 9706, which removes the (never used anymore) wbshadow mode,
gets back what is lost in the early microbenchmarks.
Change-Id: I37423a209e8ec2a2e92538b45cac5422a6acd32d
Reviewed-on: https://go-review.googlesource.com/9705
Reviewed-by: Rick Hudson <rlh@golang.org>
For the conversion of the heap bitmap from 4-bit to 2-bit fields,
I replaced heapBitsSetType with the dumbest thing that could possibly work:
two atomic operations (atomicand8+atomicor8) per 2-bit field.
This CL replaces that code with a proper implementation that
avoids the atomics whenever possible. Benchmarks vs base CL
(before the conversion to 2-bit heap bitmap) and vs Go 1.4 below.
Compared to Go 1.4, SetTypePtr (a 1-pointer allocation)
is 10ns slower because a race against the concurrent GC requires the
use of an atomicor8 that used to be an ordinary write. This slowdown
was present even in the base CL.
Compared to both Go 1.4 and base, SetTypeNode8 (a 10-word allocation)
is 10ns slower because it too needs a new atomic, because with the
denser representation, the byte on the end of the allocation is now shared
with the object next to it; this was not true with the 4-bit representation.
Excluding these two (fundamental) slowdowns due to the use of atomics,
the new code is noticeably faster than both Go 1.4 and the base CL.
The next CL will reintroduce the ``typeDead'' optimization.
Stats are from 5 runs on a MacBookPro10,2 (late 2012 Core i5).
Compared to base CL (** = new atomic)
name old mean new mean delta
SetTypePtr 14.1ns × (0.99,1.02) 14.7ns × (0.93,1.10) ~ (p=0.175)
SetTypePtr8 18.4ns × (1.00,1.01) 18.6ns × (0.81,1.21) ~ (p=0.866)
SetTypePtr16 28.7ns × (1.00,1.00) 22.4ns × (0.90,1.27) -21.88% (p=0.015)
SetTypePtr32 52.3ns × (1.00,1.00) 33.8ns × (0.93,1.24) -35.37% (p=0.001)
SetTypePtr64 79.2ns × (1.00,1.00) 55.1ns × (1.00,1.01) -30.43% (p=0.000)
SetTypePtr126 118ns × (1.00,1.00) 100ns × (1.00,1.00) -15.97% (p=0.000)
SetTypePtr128 130ns × (0.92,1.19) 98ns × (1.00,1.00) -24.36% (p=0.008)
SetTypePtrSlice 726ns × (0.96,1.08) 760ns × (1.00,1.00) ~ (p=0.152)
SetTypeNode1 14.1ns × (0.94,1.15) 12.0ns × (1.00,1.01) -14.60% (p=0.020)
SetTypeNode1Slice 135ns × (0.96,1.07) 88ns × (1.00,1.00) -34.53% (p=0.000)
SetTypeNode8 20.9ns × (1.00,1.01) 32.6ns × (1.00,1.00) +55.37% (p=0.000) **
SetTypeNode8Slice 414ns × (0.99,1.02) 244ns × (1.00,1.00) -41.09% (p=0.000)
SetTypeNode64 80.0ns × (1.00,1.00) 57.4ns × (1.00,1.00) -28.23% (p=0.000)
SetTypeNode64Slice 2.15µs × (1.00,1.01) 1.56µs × (1.00,1.00) -27.43% (p=0.000)
SetTypeNode124 119ns × (0.99,1.00) 100ns × (1.00,1.00) -16.11% (p=0.000)
SetTypeNode124Slice 3.40µs × (1.00,1.00) 2.93µs × (1.00,1.00) -13.80% (p=0.000)
SetTypeNode126 120ns × (1.00,1.01) 98ns × (1.00,1.00) -18.19% (p=0.000)
SetTypeNode126Slice 3.53µs × (0.98,1.08) 3.02µs × (1.00,1.00) -14.49% (p=0.002)
SetTypeNode1024 726ns × (0.97,1.09) 740ns × (1.00,1.00) ~ (p=0.451)
SetTypeNode1024Slice 24.9µs × (0.89,1.37) 23.1µs × (1.00,1.00) ~ (p=0.476)
Compared to Go 1.4 (** = new atomic)
name old mean new mean delta
SetTypePtr 5.71ns × (0.89,1.19) 14.68ns × (0.93,1.10) +157.24% (p=0.000) **
SetTypePtr8 19.3ns × (0.96,1.10) 18.6ns × (0.81,1.21) ~ (p=0.638)
SetTypePtr16 30.7ns × (0.99,1.03) 22.4ns × (0.90,1.27) -26.88% (p=0.005)
SetTypePtr32 51.5ns × (1.00,1.00) 33.8ns × (0.93,1.24) -34.40% (p=0.001)
SetTypePtr64 83.6ns × (0.94,1.12) 55.1ns × (1.00,1.01) -34.12% (p=0.001)
SetTypePtr126 137ns × (0.87,1.26) 100ns × (1.00,1.00) -27.10% (p=0.028)
SetTypePtrSlice 865ns × (0.80,1.23) 760ns × (1.00,1.00) ~ (p=0.243)
SetTypeNode1 15.2ns × (0.88,1.12) 12.0ns × (1.00,1.01) -20.89% (p=0.014)
SetTypeNode1Slice 156ns × (0.93,1.16) 88ns × (1.00,1.00) -43.57% (p=0.001)
SetTypeNode8 23.8ns × (0.90,1.18) 32.6ns × (1.00,1.00) +36.76% (p=0.003) **
SetTypeNode8Slice 502ns × (0.92,1.10) 244ns × (1.00,1.00) -51.46% (p=0.000)
SetTypeNode64 85.6ns × (0.94,1.11) 57.4ns × (1.00,1.00) -32.89% (p=0.001)
SetTypeNode64Slice 2.36µs × (0.91,1.14) 1.56µs × (1.00,1.00) -33.96% (p=0.002)
SetTypeNode124 130ns × (0.91,1.12) 100ns × (1.00,1.00) -23.49% (p=0.004)
SetTypeNode124Slice 3.81µs × (0.90,1.22) 2.93µs × (1.00,1.00) -23.09% (p=0.025)
There are fewer benchmarks vs Go 1.4 because unrolling directly
into the heap bitmap is not yet implemented, so those would not
be meaningful comparisons.
These benchmarks were not present in Go 1.4 as distributed.
The backport to Go 1.4 is in github.com/rsc/go's go14bench branch,
commit 71d5ee5.
Change-Id: I95ed05a22bf484b0fc9efad549279e766c98d2b6
Reviewed-on: https://go-review.googlesource.com/9704
Reviewed-by: Rick Hudson <rlh@golang.org>
Previous CLs changed the representation of the non-heap type bitmaps
to be 1-bit bitmaps (pointer or not). Before this CL, the heap bitmap
stored a 2-bit type for each word and a mark bit and checkmark bit
for the first word of the object. (There used to be additional per-word bits.)
Reduce heap bitmap to 2-bit, with 1 dedicated to pointer or not,
and the other used for mark, checkmark, and "keep scanning forward
to find pointers in this object." See comments for details.
This CL replaces heapBitsSetType with very slow but obviously correct code.
A followup CL will optimize it. (Spoiler: the new code is faster than Go 1.4 was.)
Change-Id: I999577a133f3cfecacebdec9cdc3573c235c7fb9
Reviewed-on: https://go-review.googlesource.com/9703
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
The type information in reflect.Type and the GC programs is now
1 bit per word, down from 2 bits.
The in-memory unrolled type bitmap representation are now
1 bit per word, down from 4 bits.
The conversion from the unrolled (now 1-bit) bitmap to the
heap bitmap (still 4-bit) is not optimized. A followup CL will
work on that, after the heap bitmap has been converted to 2-bit.
The typeDead optimization, in which a special value denotes
that there are no more pointers anywhere in the object, is lost
in this CL. A followup CL will bring it back in the final form of
heapBitsSetType.
Change-Id: If61e67950c16a293b0b516a6fd9a1c755b6d5549
Reviewed-on: https://go-review.googlesource.com/9702
Reviewed-by: Austin Clements <austin@google.com>
There was an old benchmark that measured this indirectly
via allocation, but I don't understand how to factor out the
allocation cost when interpreting the numbers.
Replace with a benchmark that only calls heapBitsSetType,
that does not allocate. This was not possible when the
benchmark was first written, because heapBitsSetType had
not been factored out of mallocgc.
Change-Id: I30f0f02362efab3465a50769398be859832e6640
Reviewed-on: https://go-review.googlesource.com/9701
Reviewed-by: Austin Clements <austin@google.com>
