open-consul/lib/routine/routine.go

177 lines
3.8 KiB
Go
Raw Normal View History

// Copyright (c) HashiCorp, Inc.
// SPDX-License-Identifier: MPL-2.0
package routine
import (
"context"
"os"
"sync"
"github.com/hashicorp/go-hclog"
)
type Routine func(ctx context.Context) error
// cancelCh is the ctx.Done()
// When cancel() is called, if the routine is running a blocking call (e.g. some ACL replication RPCs),
// stoppedCh won't be closed till the blocking call returns, while cancelCh will be closed immediately.
// cancelCh is used to properly detect routine running status between cancel() and close(stoppedCh)
type routineTracker struct {
cancel context.CancelFunc
cancelCh <-chan struct{} // closed when ctx is done
stoppedCh chan struct{} // closed when no longer running
}
func (r *routineTracker) running() bool {
select {
case <-r.stoppedCh:
return false
case <-r.cancelCh:
return false
default:
return true
}
}
func (r *routineTracker) wait() {
<-r.stoppedCh
}
type Manager struct {
lock sync.RWMutex
logger hclog.Logger
routines map[string]*routineTracker
}
func NewManager(logger hclog.Logger) *Manager {
if logger == nil {
logger = hclog.New(&hclog.LoggerOptions{
Output: os.Stderr,
})
}
return &Manager{
logger: logger,
routines: make(map[string]*routineTracker),
}
}
func (m *Manager) IsRunning(name string) bool {
m.lock.Lock()
defer m.lock.Unlock()
if routine, ok := m.routines[name]; ok {
return routine.running()
}
return false
}
func (m *Manager) Start(ctx context.Context, name string, routine Routine) error {
m.lock.Lock()
defer m.lock.Unlock()
if instance, ok := m.routines[name]; ok && instance.running() {
return nil
}
if ctx == nil {
ctx = context.Background()
}
rtCtx, cancel := context.WithCancel(ctx)
instance := &routineTracker{
cancel: cancel,
cancelCh: ctx.Done(),
stoppedCh: make(chan struct{}),
}
go m.execute(rtCtx, name, routine, instance.stoppedCh)
m.routines[name] = instance
m.logger.Info("started routine", "routine", name)
return nil
}
// execute will run the given routine in the foreground and close the given channel when its done executing
func (m *Manager) execute(ctx context.Context, name string, routine Routine, done chan struct{}) {
defer func() {
close(done)
}()
err := routine(ctx)
if err != nil && err != context.DeadlineExceeded && err != context.Canceled {
m.logger.Error("routine exited with error",
"routine", name,
"error", err,
)
} else {
m.logger.Info("stopped routine", "routine", name)
}
}
// Caveat: The returned stoppedCh indicates that the routine is completed
// It's possible that ctx is canceled, but stoppedCh not yet closed
// Use mgr.IsRunning(name) than this stoppedCh to tell whether the
// instance is still running (not cancelled or completed).
func (m *Manager) Stop(name string) <-chan struct{} {
instance := m.stopInstance(name)
if instance == nil {
// Fabricate a closed channel so it won't block forever.
ch := make(chan struct{})
close(ch)
return ch
}
return instance.stoppedCh
}
func (m *Manager) stopInstance(name string) *routineTracker {
m.lock.Lock()
defer m.lock.Unlock()
instance, ok := m.routines[name]
if !ok {
// no running instance
return nil
}
if !instance.running() {
return instance
}
m.logger.Info("stopping routine", "routine", name)
instance.cancel()
wan federation via mesh gateways (#6884) This is like a Möbius strip of code due to the fact that low-level components (serf/memberlist) are connected to high-level components (the catalog and mesh-gateways) in a twisty maze of references which make it hard to dive into. With that in mind here's a high level summary of what you'll find in the patch: There are several distinct chunks of code that are affected: * new flags and config options for the server * retry join WAN is slightly different * retry join code is shared to discover primary mesh gateways from secondary datacenters * because retry join logic runs in the *agent* and the results of that operation for primary mesh gateways are needed in the *server* there are some methods like `RefreshPrimaryGatewayFallbackAddresses` that must occur at multiple layers of abstraction just to pass the data down to the right layer. * new cache type `FederationStateListMeshGatewaysName` for use in `proxycfg/xds` layers * the function signature for RPC dialing picked up a new required field (the node name of the destination) * several new RPCs for manipulating a FederationState object: `FederationState:{Apply,Get,List,ListMeshGateways}` * 3 read-only internal APIs for debugging use to invoke those RPCs from curl * raft and fsm changes to persist these FederationStates * replication for FederationStates as they are canonically stored in the Primary and replicated to the Secondaries. * a special derivative of anti-entropy that runs in secondaries to snapshot their local mesh gateway `CheckServiceNodes` and sync them into their upstream FederationState in the primary (this works in conjunction with the replication to distribute addresses for all mesh gateways in all DCs to all other DCs) * a "gateway locator" convenience object to make use of this data to choose the addresses of gateways to use for any given RPC or gossip operation to a remote DC. This gets data from the "retry join" logic in the agent and also directly calls into the FSM. * RPC (`:8300`) on the server sniffs the first byte of a new connection to determine if it's actually doing native TLS. If so it checks the ALPN header for protocol determination (just like how the existing system uses the type-byte marker). * 2 new kinds of protocols are exclusively decoded via this native TLS mechanism: one for ferrying "packet" operations (udp-like) from the gossip layer and one for "stream" operations (tcp-like). The packet operations re-use sockets (using length-prefixing) to cut down on TLS re-negotiation overhead. * the server instances specially wrap the `memberlist.NetTransport` when running with gateway federation enabled (in a `wanfed.Transport`). The general gist is that if it tries to dial a node in the SAME datacenter (deduced by looking at the suffix of the node name) there is no change. If dialing a DIFFERENT datacenter it is wrapped up in a TLS+ALPN blob and sent through some mesh gateways to eventually end up in a server's :8300 port. * a new flag when launching a mesh gateway via `consul connect envoy` to indicate that the servers are to be exposed. This sets a special service meta when registering the gateway into the catalog. * `proxycfg/xds` notice this metadata blob to activate additional watches for the FederationState objects as well as the location of all of the consul servers in that datacenter. * `xds:` if the extra metadata is in place additional clusters are defined in a DC to bulk sink all traffic to another DC's gateways. For the current datacenter we listen on a wildcard name (`server.<dc>.consul`) that load balances all servers as well as one mini-cluster per node (`<node>.server.<dc>.consul`) * the `consul tls cert create` command got a new flag (`-node`) to help create an additional SAN in certs that can be used with this flavor of federation.
2020-03-09 20:59:02 +00:00
delete(m.routines, name)
return instance
}
// StopAll goroutines. Once StopAll is called, it is no longer safe to add no
// goroutines to the Manager.
func (m *Manager) StopAll() {
m.lock.Lock()
defer m.lock.Unlock()
for name, routine := range m.routines {
if !routine.running() {
continue
}
m.logger.Info("stopping routine", "routine", name)
routine.cancel()
}
}
// Wait for all goroutines to stop after StopAll is called.
func (m *Manager) Wait() {
m.lock.Lock()
defer m.lock.Unlock()
for _, routine := range m.routines {
routine.wait()
}
}