Files
coredns/plugin/pkg/proxy/proxy.go

124 lines
2.9 KiB
Go
Raw Normal View History

package proxy
import (
"crypto/tls"
"runtime"
"sync/atomic"
"time"
"github.com/coredns/coredns/plugin/pkg/log"
"github.com/coredns/coredns/plugin/pkg/up"
)
// Proxy defines an upstream host.
type Proxy struct {
fails uint32
addr string
proxyName string
transport *Transport
readTimeout time.Duration
// health checking
probe *up.Probe
health HealthChecker
}
// NewProxy returns a new proxy.
func NewProxy(proxyName, addr, trans string) *Proxy {
p := &Proxy{
addr: addr,
fails: 0,
probe: up.New(),
readTimeout: 2 * time.Second,
transport: newTransport(proxyName, addr),
health: NewHealthChecker(proxyName, trans, true, "."),
proxyName: proxyName,
}
runtime.SetFinalizer(p, (*Proxy).finalizer)
return p
}
func (p *Proxy) Addr() string { return p.addr }
// SetTLSConfig sets the TLS config in the lower p.transport and in the healthchecking client.
func (p *Proxy) SetTLSConfig(cfg *tls.Config) {
p.transport.SetTLSConfig(cfg)
p.health.SetTLSConfig(cfg)
}
// SetExpire sets the expire duration in the lower p.transport.
func (p *Proxy) SetExpire(expire time.Duration) { p.transport.SetExpire(expire) }
plugin/forward: add max_age option to enforce an absolute connection lifetime (#7903) * plugin/pkg/proxy: add max_age for per-connection lifetime cap Introduce a max_age setting on Transport that closes connections based on creation time, independent of idle-timeout (expire). Background: PR #7790 changed the connection pool from LIFO to FIFO for source-port diversity. Under FIFO, every connection is cycled through the pool and its used timestamp is refreshed continuously. When request rate is high enough that pool_size / request_rate < expire, no connection ever becomes idle and expire never fires. This prevents CoreDNS from opening new connections to upstreams that scale out (e.g. new Kubernetes pods behind a ClusterIP service with conntrack pinning). max_age addresses this by enforcing an absolute upper bound on connection lifetime regardless of activity: - persistConn gains a created field set at dial time. - Transport gains maxAge (default 0 = unlimited, preserving existing behaviour). - Dial(): rejects cached connections whose creation age exceeds max_age. - cleanup(): when maxAge > 0, uses a linear scan over both idle-timeout and max-age predicates; when maxAge == 0, preserves the original binary-search path on used time (sorted by FIFO insertion order). - Both hot paths pre-compute the deadline outside any inner loop to avoid repeated time.Now() calls. Tests added: - TestMaxAgeExpireByCreation: connection with old created but fresh used must be rejected even though idle-timeout would pass. - TestMaxAgeFIFORotation: three FIFO-rotated connections (old created, fresh used) must all be rejected, confirming that continuous rotation cannot prevent max-age expiry. Signed-off-by: cangming <cangming@cangming.app> * plugin/forward: add max_age option Expose Transport.SetMaxAge through the forward plugin so operators can set an absolute upper bound on connection lifetime via the Corefile. Usage: forward . 1.2.3.4 { max_age 30s } Default is 0 (unlimited), which preserves existing behaviour. A positive value causes connections older than max_age to be closed and re-dialled on the next request, ensuring CoreDNS reconnects to newly scaled-out upstream pods even under sustained load where the idle timeout (expire) would never fire. If max_age is set, it must not be less than expire; the parser rejects this combination at startup with a clear error message. Signed-off-by: cangming <cangming@cangming.app> --------- Signed-off-by: cangming <cangming@cangming.app>
2026-03-10 02:50:03 +08:00
// SetMaxAge sets the maximum connection lifetime in the lower p.transport.
// A value of 0 (default) disables max-age.
func (p *Proxy) SetMaxAge(maxAge time.Duration) { p.transport.SetMaxAge(maxAge) }
perf(proxy): use mutex-based connection pool (#7790) * perf(proxy): use mutex-based connection pool The proxy package (used for example by the forward plugin) utilized an actor model where a single connManager goroutine managed connection pooling via unbuffered channels (dial, yield, ret). This design serialized all connection acquisition and release operations through a single goroutine, creating a bottleneck under high concurrency. This was observable as a performance degradation when using a single upstream backend compared to multiple backends (which sharded the bottleneck). Changes: - Removed dial, yield, and ret channels from the Transport struct. - Removed the connManager goroutine's request processing loop. - Implemented Dial() and Yield() using a sync.Mutex to protect the connection slice, allowing for fast concurrent access without context switching. - Downgraded connManager to a simple background cleanup loop that only handles connection expiration on a ticker. - Updated plugin/pkg/proxy/connect.go to use direct method calls instead of channel sends. - Updated tests to reflect the removal of internal channels. Benchmarks show that this change eliminates the single-backend bottleneck. Now a single upstream backend performs on par with multiple backends, and overall throughput is improved. The implementation aligns with standard Go patterns for connection pooling (e.g., net/http.Transport). Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> * fix: address PR review for persistent.go - Named mutex field instead of embedding, to not expose Lock() and Unlock() - Move stop check outside of lock in Yield() - Close() without a separate goroutine - Change stop channel to struct Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> * fix: address code review feedback for conn pool - Switch from LIFO to FIFO connection selection for source port diversity, reducing DNS cache poisoning risk (RFC 5452). - Remove "clear entire cache" optimization as it was LIFO-specific. FIFO naturally iterates and skips expired connections. - Remove all goroutines for closing connections; collect connections while holding lock, close synchronously after releasing lock. Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> * fix: remove unused error consts No longer utilised after refactoring the channel based approach. Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> * feat(forward): add max_idle_conns option Add configurable connection pool limit for the forward plugin via the max_idle_conns Corefile option. Changes: - Add SetMaxIdleConns to proxy - Add maxIdleConns field to Forward struct - Add max_idle_conns parsing in forward plugin setup - Apply setting to each proxy during configuration - Update forward plugin README with new option By default the value is 0 (unbounded). When set, excess connections returned to the pool are closed immediately rather than cached. Also add a yield related test. Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> * chore(proxy): simple Dial by closing conns inline Remove toClose slice collection to reduce complexity. Instead close expired connections directly while iterating. Reduces complexity with negligible lock-time impact. Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> * chore: fewer explicit Unlock calls Cleaner and less chance of forgetting to unlock on new possible code paths. Signed-off-by: Ville Vesilehto <ville@vesilehto.fi> --------- Signed-off-by: Ville Vesilehto <ville@vesilehto.fi>
2026-01-14 03:49:46 +02:00
// SetMaxIdleConns sets the maximum idle connections per transport type.
// A value of 0 means unlimited (default).
func (p *Proxy) SetMaxIdleConns(n int) { p.transport.SetMaxIdleConns(n) }
func (p *Proxy) GetHealthchecker() HealthChecker {
return p.health
}
func (p *Proxy) GetTransport() *Transport {
return p.transport
}
func (p *Proxy) Fails() uint32 {
return atomic.LoadUint32(&p.fails)
}
// Healthcheck kicks of a round of health checks for this proxy.
func (p *Proxy) Healthcheck() {
if p.health == nil {
log.Warning("No healthchecker")
return
}
p.probe.Do(func() error {
return p.health.Check(p)
})
}
// Down returns true if this proxy is down, i.e. has *more* fails than maxfails.
func (p *Proxy) Down(maxfails uint32) bool {
if maxfails == 0 {
return false
}
fails := atomic.LoadUint32(&p.fails)
return fails > maxfails
}
// Stop close stops the health checking goroutine.
func (p *Proxy) Stop() { p.probe.Stop() }
func (p *Proxy) finalizer() { p.transport.Stop() }
// Start starts the proxy's healthchecking.
func (p *Proxy) Start(duration time.Duration) {
p.probe.Start(duration)
p.transport.Start()
}
func (p *Proxy) SetReadTimeout(duration time.Duration) {
p.readTimeout = duration
}
// incrementFails increments the number of fails safely.
func (p *Proxy) incrementFails() {
curVal := atomic.LoadUint32(&p.fails)
if curVal > curVal+1 {
// overflow occurred, do not update the counter again
return
}
atomic.AddUint32(&p.fails, 1)
}
const (
maxTimeout = 2 * time.Second
)