| Age | Commit message (Collapse) | Author |
|---|
|
|
|
Change marshal.Marshallable method signatures to return the remaining buffer.
This makes it easier to implement these method manually. Without this, we would
have to manually do buffer shifting which is error prone.
tools/go_marshal/test:benchmark test does not show change in performance.
Additionally fixed some marshalling bugs in fsimpl/fuse.
Updated multiple callpoints to get rid of redundant slice indexing work and
simplified code using this new signature.
Updates #6450
PiperOrigin-RevId: 407857019
|
|
|
|
Consider the following benchmark, which is equivalent to
BenchmarkSleeperWaitOnSingleSelect with names changed to more closely reflect
the behavior of BenchmarkGoWaitOnSingleSelect:
var (
empty Sleeper
emptyCond Waker
full Sleeper
fullCond Waker
)
empty.AddWaker(&emptyCond)
full.AddWaker(&fullCond)
go func() {
for i := 0; i < b.N; i++ {
empty.Fetch(true)
fullCond.Assert()
}
}()
for i := 0; i < b.N; i++ {
emptyCond.Assert()
full.Fetch(true)
}
The unfairness arises because runtime.chansend and runtime.chanrecv don't
actually work this way. If runtime.chansend blocks, it has already enqueued the
element to be sent on runtime.hchan.sendq, which runtime.chanrecv dequeues
before calling goready(); in sleep-like terms, by the time empty.Fetch()
returns, fullCond.Assert() has already happened and been fetched by the other
goroutine. The same property applies to runtime.chanrecv/runtime.hchan.recvq.
This property has no correspondence to the actual usage of the sleep package,
so change the channel benchmarks to explicitly exchange control using buffered
channels instead. Also remove some stale comments and align the syncevent
benchmarks with the sleep ones.
BenchmarkSleeperWaitOnSingleSelect
BenchmarkSleeperWaitOnSingleSelect-12 2118603 472.5 ns/op
BenchmarkGoWaitOnSingleSelect
BenchmarkGoWaitOnSingleSelect-12 2224262 517.7 ns/op
BenchmarkSleeperWaitOnMultiSelect
BenchmarkSleeperWaitOnMultiSelect-12 2630569 459.8 ns/op
BenchmarkGoWaitOnMultiSelect
BenchmarkGoWaitOnMultiSelect-12 807918 1312 ns/op
BenchmarkWaiterPingPong
BenchmarkWaiterPingPong-12 2955579 385.8 ns/op
BenchmarkSleeperPingPong
BenchmarkSleeperPingPong-12 2454367 474.3 ns/op
BenchmarkChannelPingPong
BenchmarkChannelPingPong-12 2302662 513.5 ns/op
BenchmarkWaiterPingPongMulti
BenchmarkWaiterPingPongMulti-12 3023676 388.8 ns/op
BenchmarkSleeperPingPongMulti
BenchmarkSleeperPingPongMulti-12 2574064 471.5 ns/op
BenchmarkChannelPingPongMulti
BenchmarkChannelPingPongMulti-12 1000000 1088 ns/op
PiperOrigin-RevId: 407760956
|
|
|
|
In a subsequent change, the Sleeper API will be plumbed through and used for
arbitrary task wakeups. This requires a non-static association of Wakers and
Sleepers, which means that a fixed ID no longer works. This is a relatively
simple change that removes the ID from the Waker association, and simply uses
the Waker pointer itself.
That change also makes minor improvements to the tests to ensure that the
benchmarks are more representative by removing goroutine start from the hot
path (and uses Wakers for required synchronization), adds assertion checks to
AddWaker, and clears relevant fields during Done (to allow assertions to pass).
PiperOrigin-RevId: 407719630
|
|
|
|
Move ConverIntr out of syserr package and delete an unused function.
PiperOrigin-RevId: 407676258
|
|
|
|
PiperOrigin-RevId: 407638912
|
|
|
|
Lock inference will apply annotations to all fields that seem to be
protected. This is currently disabled for all code by default, but it
can be enabled as annotations are applied more broadly.
PiperOrigin-RevId: 407501915
|
|
|
|
PiperOrigin-RevId: 407392578
|
|
|
|
* Support sync.Locker.
* Prevent runaway recursion when locks are acquired in a loop.
* Allowing ignoring of anonymous functions (inherited from parent function).
* Add support for aliases.
PiperOrigin-RevId: 407221521
|
|
|
|
PiperOrigin-RevId: 407188968
|
|
|
|
These fields do not need to synchronize reads/writes with the rest of
the connection.
PiperOrigin-RevId: 407183693
|
|
|
|
PiperOrigin-RevId: 407177936
|
|
|
|
This change fixes a bug when reaping tuples of NAT-ed connections.
Previously when reaping a tuple, the other direction's tuple ID was
calculated by taking the reaping tuple's ID and inverting it. This
works when a connection is not NATed but doesn't work when NAT is
performed as the other direction's tuple may use different
addresses.
PiperOrigin-RevId: 407160930
|
|
|
|
It's safe to call SetAttr and Allocate on fsgofer because the
file path is not used to open the file, if needed.
Fixes #3654
PiperOrigin-RevId: 407149393
|
|
copy and setup PERMANENT (static) ARP entries
from CNI namespace to the sandbox
Fixes #3301
|
|
|
|
An ICMP error may not hold the full packet that triggered the ICMP
response. As long as the IP header and the transport header is
parsable, we should be able to successfully NAT as that is all that
we need to identify the connection.
PiperOrigin-RevId: 406966048
|
|
|
|
Reported-by: syzbot+f9ecb181a4b3abdde9b9@syzkaller.appspotmail.com
Reported-by: syzbot+8c5cb9d7a044a91a513b@syzkaller.appspotmail.com
PiperOrigin-RevId: 406951359
|
|
|
|
This function doesn't belong in the global context package. Move to a more
suitable package to break the dependency cycle.
PiperOrigin-RevId: 406942122
|
|
|
|
PiperOrigin-RevId: 406938082
|
|
mips was supported, but mipsle had been forgotten.
Fixes google/gvisor#6804
|
|
This is part of cgroupv2 patch set. Here we add a Cgroup interface that
both v1 and v2 need to conform to, and port cgroupv1 to use that first.
Signed-off-by: Daniel Dao <dqminh89@gmail.com>
|
|
Grammar correction.
|
|
|
|
Change the linuxerr.ErrorFromErrno to return an error type and not
a *errors.Error type. The latter results in problems comparing to nil
as <nil><nil> != <nil><*errors.Error>.
In a follow up, there will be a change to remove *errors.Error.Errno(),
which will also encourage users to not use Errnos to reference linuxerr.
PiperOrigin-RevId: 406444419
|
|
|
|
...so a NAT-ed connection's socket can handle ICMP errors.
Updates #5916.
PiperOrigin-RevId: 406270868
|
|
|
|
kernel/time.Timer allocation is expensive and not sync.Poolable (since
time.Timer only supports notification through a channel, requiring a goroutine
to receive from the channel, and sync.Pool doesn't invoke any kind of cleanup
on discarded items in the pool so it would leak timer goroutines). Using the
existing Task.blockingTimer for nanosleep(), and applicable cases in
clock_nanosleep(), at least avoids Timer allocation in common cases.
PiperOrigin-RevId: 406248394
|
|
|
|
PiperOrigin-RevId: 406027220
|
|
|
|
Reported-by: syzbot+39d434b96cf7c29a66ad@syzkaller.appspotmail.com
Reported-by: syzbot+7c38bce6353d91facca3@syzkaller.appspotmail.com
PiperOrigin-RevId: 406024052
|
|
|
|
When transmitting packets we only need to notify if the peer is not
already processing packets. sharedData region is used to enable/disable
notifications and the peer will disable notifications when its actively
processing packets and enable notifications just before it goes to
sleep waiting on packets. This allows more efficient transmit as the
sharedmem endpoint does not need to notify on eventFD and incur an
expensive host systemcall when the peer is already awake.
PiperOrigin-RevId: 406018843
|
