The routecheck package parallels the netcheck package, where the former checks routes and routers while the latter checks networks. Like netcheck, it compiles reports for other systems to consume. Historically, the client has never known whether a peer is actually reachable. Most of the time this doesn’t matter, since the client will want to establish a WireGuard tunnel to any given destination. However, if the client needs to choose between two or more nodes, then it should try to choose a node that it can reach. Suggested exit nodes are one such example, where the client filters out any nodes that aren’t connected to the control plane. Sometimes an exit node will get disconnected from the control plane: when the network between the two is unreliable or when the exit node is too busy to keep its control connection alive. In these cases, Control disables the Node.Online flag for the exit node and broadcasts this across the tailnet. Arguably, the client should never have relied on this flag, since it only makes sense in the admin console. This patch implements an initial routecheck client that can probe every node that your client knows about. You should not ping scan your visible tailnet, this method is for debugging only. This patch also introduces a new OnNetMapToggle hook, which fires when the netmap transitions from nil to non-nil, or vice versa. This happens either when the client receives its first MapResponse after connecting to the control plane, or when it clears the netmap while it is disconnecting. Routecheck uses this to wait for a valid netmap so it knows which peers to probe. Updates #17366 Updates tailscale/corp#33033 Signed-off-by: Simon Law <sfllaw@tailscale.com>
62 lines
1.5 KiB
Go
62 lines
1.5 KiB
Go
// Copyright (c) Tailscale Inc & contributors
|
||
// SPDX-License-Identifier: BSD-3-Clause
|
||
|
||
package routecheck
|
||
|
||
import (
|
||
"context"
|
||
"net/netip"
|
||
"time"
|
||
|
||
"tailscale.com/tailcfg"
|
||
"tailscale.com/util/clientmetric"
|
||
)
|
||
|
||
var (
|
||
metricReport = clientmetric.NewCounter("routecheck_report")
|
||
)
|
||
|
||
// Report returns the latest reachability report.
|
||
// Returns nil if a report isn’t available, which happens during initialization.
|
||
func (c *Client) Report() *Report {
|
||
metricReport.Add(1)
|
||
nm := c.nm.NetMapNoPeers()
|
||
if nm == nil {
|
||
return nil // The report wasn’t available.
|
||
}
|
||
|
||
// TODO(sfllaw): Return the latest snapshot produced by background probing.
|
||
r, err := c.ProbeAllHARouters(context.TODO(), 5, DefaultTimeout)
|
||
if err != nil {
|
||
c.logf("reachability report error: %v", err)
|
||
}
|
||
return r
|
||
}
|
||
|
||
// Report contains the result of a single routecheck.
|
||
type Report struct {
|
||
// Done is the time when the report was finished.
|
||
Done time.Time
|
||
|
||
// Reachable is the set of nodes that were reachable from the current host
|
||
// when this report was compiled. Missing nodes may or may not be reachable.
|
||
Reachable map[tailcfg.NodeID]Node
|
||
}
|
||
|
||
// Node represents a node in the reachability report.
|
||
type Node struct {
|
||
ID tailcfg.NodeID
|
||
|
||
// Name is the FQDN of the node.
|
||
// It is also the MagicDNS name for the node.
|
||
// It has a trailing dot.
|
||
// e.g. "host.tail-scale.ts.net."
|
||
Name string
|
||
|
||
// Addr is the IP address that was probed.
|
||
Addr netip.Addr
|
||
|
||
// Routes are the subnets that the node will route.
|
||
Routes []netip.Prefix
|
||
}
|