There's a call to Now once per packet.
Move to mono.Now.
Though the current implementation provides high precision,
we document it to be coarse, to preserve the ability
to switch to a coarse monotonic time later.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
The handoff between tstun.Wrap's Read and poll methods
is one of the per-packet hotspots. It shows up in pprof.
Making outbound buffered increases throughput.
It is hard to measure exactly how much, because the numbers
are highly variable, but I'd estimate it at about 1%,
using the best observed max throughput across three runs.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
The handoff between tstun.Wrap's Read and poll methods
is one of the per-packet hotspots. It shows up in pprof.
Making outbound buffered increases throughput.
It is hard to measure exactly how much, because the numbers
are highly variable, but I'd estimate it at about 1%,
using the best observed max throughput across three runs.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
To remove some multi-case selects, we intentionally allowed
sends on closed channels (cc23049cd2).
However, we also introduced concurrent sends and closes,
which is a data race.
This commit fixes the data race. The mutexes here are uncontended,
and thus very cheap.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
Calculate whether the packet is injected directly,
rather than via an else branch.
Unify the exit paths. It is easier here than duplicating them.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
Every TUN Read went through several multi-case selects.
We know from past experience with wireguard-go that these are slow
and cause scheduler churn.
The selects served two purposes: they separated errors from data and
gracefully handled shutdown. The first is fairly easy to replace by sending
errors and data over a single channel. The second, less so.
We considered a few approaches: Intricate webs of channels,
global condition variables. They all get ugly fast.
Instead, let's embrace the ugly and handle shutdown ungracefully.
It's horrible, but the horror is simple and localized.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
Pull in the latest version of wireguard-windows.
Switch to upstream wireguard-go.
This requires reverting all of our import paths.
Unfortunately, this has to happen at the same time.
The wireguard-go change is very low risk,
as that commit matches our fork almost exactly.
(The only changes are import paths, CI files, and a go.mod entry.)
So if there are issues as a result of this commit,
the first place to look is wireguard-windows changes.
Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
Whenever we dropped a packet due to ACLs, wireguard-go was logging:
Failed to write packet to TUN device: packet dropped by filter
Instead, just lie to wireguard-go and pretend everything is okay.
Fixes#1229
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
We had a long-standing bug in which our TUN events channel
was being received from simultaneously in two places.
The first is wireguard-go.
At wgengine/userspace.go:366, we pass e.tundev to wireguard-go,
which starts a goroutine (RoutineTUNEventReader)
that receives from that channel and uses events to adjust the MTU
and bring the device up/down.
At wgengine/userspace.go:374, we launch a goroutine that
receives from e.tundev, logs MTU changes, and triggers
state updates when up/down changes occur.
Events were getting delivered haphazardly between the two of them.
We don't really want wireguard-go to receive the up/down events;
we control the state of the device explicitly by calling device.Up.
And the userspace.go loop MTU logging duplicates logging that
wireguard-go does when it received MTU updates.
So this change splits the single TUN events channel into up/down
and other (aka MTU), and sends them to the parties that ought
to receive them.
I'm actually a bit surprised that this hasn't caused more visible trouble.
If a down event went to wireguard-go but the subsequent up event
went to userspace.go, we could end up with the wireguard-go device disappearing.
I believe that this may also (somewhat accidentally) be a fix for #1790.
Signed-off-by: Josh Bleecher Snyder <josharian@gmail.com>
This tries to generate traffic at a rate that will saturate the
receiver, without overdoing it, even in the event of packet loss. It's
unrealistically more aggressive than TCP (which will back off quickly
in case of packet loss) but less silly than a blind test that just
generates packets as fast as it can (which can cause all the CPU to be
absorbed by the transmitter, giving an incorrect impression of how much
capacity the total system has).
Initial indications are that a syscall about every 10 packets (TCP bulk
delivery) is roughly the same speed as sending every packet through a
channel. A syscall per packet is about 5x-10x slower than that.
The whole tailscale wireguard-go + magicsock + packet filter
combination is about 4x slower again, which is better than I thought
we'd do, but probably has room for improvement.
Note that in "full" tailscale, there is also a tundev read/write for
every packet, effectively doubling the syscall overhead per packet.
Given these numbers, it seems like read/write syscalls are only 25-40%
of the total CPU time used in tailscale proper, so we do have
significant non-syscall optimization work to do too.
Sample output:
$ GOMAXPROCS=2 go test -bench . -benchtime 5s ./cmd/tailbench
goos: linux
goarch: amd64
pkg: tailscale.com/cmd/tailbench
cpu: Intel(R) Core(TM) i7-4785T CPU @ 2.20GHz
BenchmarkTrivialNoAlloc/32-2 56340248 93.85 ns/op 340.98 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTrivialNoAlloc/124-2 57527490 99.27 ns/op 1249.10 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTrivialNoAlloc/1024-2 52537773 111.3 ns/op 9200.39 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTrivial/32-2 41878063 135.6 ns/op 236.04 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTrivial/124-2 41270439 138.4 ns/op 896.02 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTrivial/1024-2 36337252 154.3 ns/op 6635.30 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkBlockingChannel/32-2 12171654 494.3 ns/op 64.74 MB/s 0 %lost 1791 B/op 0 allocs/op
BenchmarkBlockingChannel/124-2 12149956 507.8 ns/op 244.17 MB/s 0 %lost 1792 B/op 1 allocs/op
BenchmarkBlockingChannel/1024-2 11034754 528.8 ns/op 1936.42 MB/s 0 %lost 1792 B/op 1 allocs/op
BenchmarkNonlockingChannel/32-2 8960622 2195 ns/op 14.58 MB/s 8.825 %lost 1792 B/op 1 allocs/op
BenchmarkNonlockingChannel/124-2 3014614 2224 ns/op 55.75 MB/s 11.18 %lost 1792 B/op 1 allocs/op
BenchmarkNonlockingChannel/1024-2 3234915 1688 ns/op 606.53 MB/s 3.765 %lost 1792 B/op 1 allocs/op
BenchmarkDoubleChannel/32-2 8457559 764.1 ns/op 41.88 MB/s 5.945 %lost 1792 B/op 1 allocs/op
BenchmarkDoubleChannel/124-2 5497726 1030 ns/op 120.38 MB/s 12.14 %lost 1792 B/op 1 allocs/op
BenchmarkDoubleChannel/1024-2 7985656 1360 ns/op 752.86 MB/s 13.57 %lost 1792 B/op 1 allocs/op
BenchmarkUDP/32-2 1652134 3695 ns/op 8.66 MB/s 0 %lost 176 B/op 3 allocs/op
BenchmarkUDP/124-2 1621024 3765 ns/op 32.94 MB/s 0 %lost 176 B/op 3 allocs/op
BenchmarkUDP/1024-2 1553750 3825 ns/op 267.72 MB/s 0 %lost 176 B/op 3 allocs/op
BenchmarkTCP/32-2 11056336 503.2 ns/op 63.60 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTCP/124-2 11074869 533.7 ns/op 232.32 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkTCP/1024-2 8934968 671.4 ns/op 1525.20 MB/s 0 %lost 0 B/op 0 allocs/op
BenchmarkWireGuardTest/32-2 1403702 4547 ns/op 7.04 MB/s 14.37 %lost 467 B/op 3 allocs/op
BenchmarkWireGuardTest/124-2 780645 7927 ns/op 15.64 MB/s 1.537 %lost 420 B/op 3 allocs/op
BenchmarkWireGuardTest/1024-2 512671 11791 ns/op 86.85 MB/s 0.5206 %lost 411 B/op 3 allocs/op
PASS
ok tailscale.com/wgengine/bench 195.724s
Updates #414.
Signed-off-by: Avery Pennarun <apenwarr@tailscale.com>
For discovery when an explicit hostname/IP is known. We'll still
also send it via control for finding peers by a list.
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
The tstun packagen contains both constructors for generic tun
Devices, and a wrapper that provides additional functionality.
Signed-off-by: David Anderson <danderson@tailscale.com>
This adds a new IP Protocol type, TSMP on protocol number 99 for
sending inter-tailscale messages over WireGuard, currently just for
why a peer rejects TCP SYNs (ACL rejection, shields up, and in the
future: nothing listening, something listening on that port but wrong
interface, etc)
Updates #1094
Updates tailscale/corp#1185
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
Lazy wg configuration now triggers if a peer has only endpoint
addresses (/32 for IPv4, /128 for IPv6). Subnet routers still
trigger eager configuration to avoid the need for a CIDR match
in the hot packet path.
Signed-off-by: David Anderson <danderson@tailscale.com>
wireguard-go uses 3 goroutines per peer (with reasonably large stacks
& buffers).
Rather than tell wireguard-go about all our peers, only tell it about
peers we're actively communicating with. That means we need hooks into
magicsock's packet receiving path and tstun's packet sending path to
lazily create a wireguard peer on demand from the network map.
This frees up lots of memory for iOS (where we have almost nothing
left for larger domains with many users).
We should ideally do this in wireguard-go itself one day, but that'd
be a pretty big change.
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
sync.Pools should almost always be packate globals, even though in this
case we only have exactly 1 TUN device anyway, so it matters less.
Still, it's unusual to see a Pool that's not a package global, so move it.
This log line looks buggy, even though lacking a filter is expected during bringup.
We already know if we forget to SetFilter: it breaks the magicsock test,
so no useful information is lost.
Resolves#559.
Signed-off-by: Dmytro Shynkevych <dmytro@tailscale.com>
If there's been 5 minutes of inactivity, stop doing STUN lookups. That
means NAT mappings will expire, but they can resume later when there's
activity again.
We'll do this for all platforms later.
Updates tailscale/corp#320
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
Right now, filtering and packet injection in wgengine depend
on a patch to wireguard-go that probably isn't suitable for upstreaming.
This need not be the case: wireguard-go/tun.Device is an interface.
For example, faketun.go implements it to mock a TUN device for testing.
This patch implements the same interface to provide filtering
and packet injection at the tunnel device level,
at which point the wireguard-go patch should no longer be necessary.
This patch has the following performance impact on i7-7500U @ 2.70GHz,
tested in the following namespace configuration:
┌────────────────┐ ┌─────────────────────────────────┐ ┌────────────────┐
│ $ns1 │ │ $ns0 │ │ $ns2 │
│ client0 │ │ tailcontrol, logcatcher │ │ client1 │
│ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ │
│ │vethc│───────┼────┼──│vethrc│ │vethrs│──────┼─────┼──│veths│ │
│ ├─────┴─────┐ │ │ ├──────┴────┐ ├──────┴────┐ │ │ ├─────┴─────┐ │
│ │10.0.0.2/24│ │ │ │10.0.0.1/24│ │10.0.1.1/24│ │ │ │10.0.1.2/24│ │
│ └───────────┘ │ │ └───────────┘ └───────────┘ │ │ └───────────┘ │
└────────────────┘ └─────────────────────────────────┘ └────────────────┘
Before:
---------------------------------------------------
| TCP send | UDP send |
|------------------------|------------------------|
| 557.0 (±8.5) Mbits/sec | 3.03 (±0.02) Gbits/sec |
---------------------------------------------------
After:
---------------------------------------------------
| TCP send | UDP send |
|------------------------|------------------------|
| 544.8 (±1.6) Mbits/sec | 3.13 (±0.02) Gbits/sec |
---------------------------------------------------
The impact on receive performance is similar.
Signed-off-by: Dmytro Shynkevych <dmytro@tailscale.com>
Josh Bleecher Snyder
Brad Fitzpatrick
Josh Bleecher Snyder
Avery Pennarun
David Anderson
Naman Sood
Dmytro Shynkevych
Dmytro Shynkevych