mirror of
https://github.com/coredns/coredns.git
synced 2026-01-16 22:01:20 -05:00
* 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>
148 lines
3.5 KiB
Go
148 lines
3.5 KiB
Go
package proxy
|
|
|
|
import (
|
|
"crypto/tls"
|
|
"sort"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/miekg/dns"
|
|
)
|
|
|
|
// a persistConn hold the dns.Conn and the last used time.
|
|
type persistConn struct {
|
|
c *dns.Conn
|
|
used time.Time
|
|
}
|
|
|
|
// Transport hold the persistent cache.
|
|
type Transport struct {
|
|
avgDialTime int64 // kind of average time of dial time
|
|
conns [typeTotalCount][]*persistConn // Buckets for udp, tcp and tcp-tls.
|
|
expire time.Duration // After this duration a connection is expired.
|
|
maxIdleConns int // Max idle connections per transport type; 0 means unlimited.
|
|
addr string
|
|
tlsConfig *tls.Config
|
|
proxyName string
|
|
|
|
mu sync.Mutex
|
|
stop chan struct{}
|
|
}
|
|
|
|
func newTransport(proxyName, addr string) *Transport {
|
|
t := &Transport{
|
|
avgDialTime: int64(maxDialTimeout / 2),
|
|
conns: [typeTotalCount][]*persistConn{},
|
|
expire: defaultExpire,
|
|
addr: addr,
|
|
stop: make(chan struct{}),
|
|
proxyName: proxyName,
|
|
}
|
|
return t
|
|
}
|
|
|
|
// connManager manages the persistent connection cache for UDP and TCP.
|
|
func (t *Transport) connManager() {
|
|
ticker := time.NewTicker(defaultExpire)
|
|
defer ticker.Stop()
|
|
for {
|
|
select {
|
|
case <-ticker.C:
|
|
t.cleanup(false)
|
|
case <-t.stop:
|
|
t.cleanup(true)
|
|
return
|
|
}
|
|
}
|
|
}
|
|
|
|
// closeConns closes connections.
|
|
func closeConns(conns []*persistConn) {
|
|
for _, pc := range conns {
|
|
pc.c.Close()
|
|
}
|
|
}
|
|
|
|
// cleanup removes connections from cache.
|
|
func (t *Transport) cleanup(all bool) {
|
|
var toClose []*persistConn
|
|
|
|
t.mu.Lock()
|
|
staleTime := time.Now().Add(-t.expire)
|
|
for transtype, stack := range t.conns {
|
|
if len(stack) == 0 {
|
|
continue
|
|
}
|
|
if all {
|
|
t.conns[transtype] = nil
|
|
toClose = append(toClose, stack...)
|
|
continue
|
|
}
|
|
if stack[0].used.After(staleTime) {
|
|
continue
|
|
}
|
|
|
|
// connections in stack are sorted by "used"
|
|
good := sort.Search(len(stack), func(i int) bool {
|
|
return stack[i].used.After(staleTime)
|
|
})
|
|
t.conns[transtype] = stack[good:]
|
|
toClose = append(toClose, stack[:good]...)
|
|
}
|
|
t.mu.Unlock()
|
|
|
|
// Close connections after releasing lock
|
|
closeConns(toClose)
|
|
}
|
|
|
|
// Yield returns the connection to transport for reuse.
|
|
func (t *Transport) Yield(pc *persistConn) {
|
|
// Check if transport is stopped before acquiring lock
|
|
select {
|
|
case <-t.stop:
|
|
// If stopped, don't return to pool, just close
|
|
pc.c.Close()
|
|
return
|
|
default:
|
|
}
|
|
|
|
pc.used = time.Now() // update used time
|
|
|
|
t.mu.Lock()
|
|
defer t.mu.Unlock()
|
|
|
|
transtype := t.transportTypeFromConn(pc)
|
|
|
|
if t.maxIdleConns > 0 && len(t.conns[transtype]) >= t.maxIdleConns {
|
|
pc.c.Close()
|
|
return
|
|
}
|
|
|
|
t.conns[transtype] = append(t.conns[transtype], pc)
|
|
}
|
|
|
|
// Start starts the transport's connection manager.
|
|
func (t *Transport) Start() { go t.connManager() }
|
|
|
|
// Stop stops the transport's connection manager.
|
|
func (t *Transport) Stop() { close(t.stop) }
|
|
|
|
// SetExpire sets the connection expire time in transport.
|
|
func (t *Transport) SetExpire(expire time.Duration) { t.expire = expire }
|
|
|
|
// SetMaxIdleConns sets the maximum idle connections per transport type.
|
|
// A value of 0 means unlimited (default).
|
|
func (t *Transport) SetMaxIdleConns(n int) { t.maxIdleConns = n }
|
|
|
|
// SetTLSConfig sets the TLS config in transport.
|
|
func (t *Transport) SetTLSConfig(cfg *tls.Config) { t.tlsConfig = cfg }
|
|
|
|
// GetTLSConfig returns the TLS config in transport.
|
|
func (t *Transport) GetTLSConfig() *tls.Config { return t.tlsConfig }
|
|
|
|
const (
|
|
defaultExpire = 10 * time.Second
|
|
minDialTimeout = 1 * time.Second
|
|
maxDialTimeout = 30 * time.Second
|
|
)
|