net/netmon, wgengine/userspace: purge ChangeDelta.Major and address TODOs (#17823)
updates tailscale/corp#33891 Addresses several older the TODO's in netmon. This removes the Major flag precomputes the ChangeDelta state, rather than making consumers of ChangeDeltas sort that out themselves. We're also seeing a lot of ChangeDelta's being flagged as "Major" when they are not interesting, triggering rebinds in wgengine that are not needed. This cleans that up and adds a host of additional tests. The dependencies are cleaned, notably removing dependency on netmon itself for calculating what is interesting, and what is not. This includes letting individual platforms set a bespoke global "IsInterestingInterface" function. This is only used on Darwin. RebindRequired now roughly follows how "Major" was historically calculated but includes some additional checks for various uninteresting events such as changes in interface addresses that shouldn't trigger a rebind. This significantly reduces thrashing (by roughly half on Darwin clients which switching between nics). The individual values that we roll into RebindRequired are also exposed so that components consuming netmap.ChangeDelta can ask more targeted questions. Signed-off-by: Jonathan Nobels <jonathan@tailscale.com>
This commit is contained in:
+22
-17
@@ -6,38 +6,43 @@ package netmon
|
||||
import (
|
||||
"context"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"tailscale.com/types/logger"
|
||||
"tailscale.com/util/eventbus"
|
||||
)
|
||||
|
||||
const cooldownSeconds = 300
|
||||
|
||||
// LinkChangeLogLimiter returns a new [logger.Logf] that logs each unique
|
||||
// format string to the underlying logger only once per major LinkChange event.
|
||||
// format string to the underlying logger only once per major LinkChange event
|
||||
// with a cooldownSeconds second cooldown.
|
||||
//
|
||||
// The logger stops tracking seen format strings when the provided context is
|
||||
// done.
|
||||
func LinkChangeLogLimiter(ctx context.Context, logf logger.Logf, nm *Monitor) logger.Logf {
|
||||
var formatSeen sync.Map // map[string]bool
|
||||
sub := eventbus.SubscribeFunc(nm.b, func(cd ChangeDelta) {
|
||||
// If we're in a major change or a time jump, clear the seen map.
|
||||
if cd.Major || cd.TimeJumped {
|
||||
formatSeen.Clear()
|
||||
var formatLastSeen sync.Map // map[string]int64
|
||||
|
||||
sub := eventbus.SubscribeFunc(nm.b, func(cd *ChangeDelta) {
|
||||
// Any link changes that are flagged as likely require a rebind are
|
||||
// interesting enough that we should log them.
|
||||
if cd.RebindLikelyRequired {
|
||||
formatLastSeen.Clear()
|
||||
}
|
||||
})
|
||||
context.AfterFunc(ctx, sub.Close)
|
||||
return func(format string, args ...any) {
|
||||
// We only store 'true' in the map, so if it's present then it
|
||||
// means we've already logged this format string.
|
||||
_, loaded := formatSeen.LoadOrStore(format, true)
|
||||
if loaded {
|
||||
// TODO(andrew-d): we may still want to log this
|
||||
// message every N minutes (1x/hour?) even if it's been
|
||||
// seen, so that debugging doesn't require searching
|
||||
// back in the logs for an unbounded amount of time.
|
||||
//
|
||||
// See: https://github.com/tailscale/tailscale/issues/13145
|
||||
return
|
||||
// get the current timestamp
|
||||
now := time.Now().Unix()
|
||||
lastSeen, ok := formatLastSeen.Load(format)
|
||||
if ok {
|
||||
// if we've seen this format string within the last cooldownSeconds, skip logging
|
||||
if now-lastSeen.(int64) < cooldownSeconds {
|
||||
return
|
||||
}
|
||||
}
|
||||
// update the last seen timestamp for this format string
|
||||
formatLastSeen.Store(format, now)
|
||||
|
||||
logf(format, args...)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user