Send every log line to a syslog server as well (closes #28)
check / check (push) Successful in 3m25s

With SWWAF_LOG_REMOTE_URL set (syslog+udp, syslog+tcp or syslog+tls),
every line on stdout is also sent as the message of an RFC 5424 record,
octet-counted over TCP and TLS, from a bounded buffer that drops its
oldest line when full, so a slow or unreachable server holds up nothing.
Failed connections are retried with backoff; lines sent, dropped and
waiting are metrics. At a stop the lines still waiting get at most two
seconds. Standard library only: log/syslog writes only the older format.

Deviation: SWWAF_LOG_REMOTE_APP_NAME defaults to the host's name until
SWWAF_INSTANCE_NAME exists.

Model: opus-5-5
This commit is contained in:
2026-10-06 15:14:02 +00:00
parent 6ec52e5b87
commit b8cef7e88d
8 changed files with 1388 additions and 17 deletions
+296
View File
@@ -0,0 +1,296 @@
// Package remotelog sends the lines smallwebwaf writes on stdout to the
// remote log endpoint, SWWAF_LOG_REMOTE_URL, as the "Request log" section
// of SPEC.md describes: each line as the message of an RFC 5424 syslog
// record, over UDP, TCP or TLS. Lines wait in a bounded buffer, so a slow
// or unreachable endpoint never holds up a request or stdout.
package remotelog
import (
"bytes"
"context"
"crypto/tls"
"crypto/x509"
"fmt"
"log/slog"
"net"
"net/url"
"os"
"strconv"
"sync/atomic"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// The forms of SWWAF_LOG_REMOTE_URL, by its scheme.
const (
SchemeUDP = "syslog+udp"
SchemeTCP = "syslog+tcp"
SchemeTLS = "syslog+tls"
)
// A record's priority is the number of its facility times the number of
// severities there are, plus the number of its severity. Every record's
// severity is informational.
const (
severities = 8
informational = 6
)
const (
// dialTimeout bounds connecting to the endpoint, the TLS handshake
// included.
dialTimeout = 10 * time.Second
// After a failed attempt to connect, the next is made a second later,
// and retryDelayFactor times as long after each further failure in a
// row, up to a minute.
firstRetryDelay = time.Second
retryDelayFactor = 2
maxRetryDelay = time.Minute
)
// Params are what New needs.
type Params struct {
// URL is the endpoint (SWWAF_LOG_REMOTE_URL): SchemeUDP, SchemeTCP or
// SchemeTLS, a host and a port.
URL *url.URL
// RootCAs are the certificates a SchemeTLS endpoint's certificate
// must chain to (SWWAF_LOG_REMOTE_TLS_CA_FILE), nil for the host's.
RootCAs *x509.CertPool
// Buffer is the most lines held while they wait to be sent
// (SWWAF_LOG_REMOTE_BUFFER).
Buffer int
// Facility is the number of the records' syslog facility
// (SWWAF_LOG_REMOTE_FACILITY), and AppName their APP-NAME
// (SWWAF_LOG_REMOTE_APP_NAME).
Facility int
AppName string
}
// Sender sends lines to the endpoint. Write puts them in its buffer, and
// Run sends them from there.
type Sender struct {
url *url.URL
tlsConfig *tls.Config
// beforeTime and afterTime are the parts of every record's header
// before and after its time, as RFC 5424 lays the header out.
beforeTime string
afterTime string
// records is the buffer: each line's record, framed to be sent.
records chan []byte
sent atomic.Int64
dropped atomic.Int64
}
// New returns a Sender for the endpoint params.URL.
func New(params Params) *Sender {
hostname, err := os.Hostname()
if err != nil || hostname == "" {
hostname = "-" // RFC 5424's value for a field that has none
}
priority := params.Facility*severities + informational
return &Sender{
url: params.URL,
tlsConfig: &tls.Config{
RootCAs: params.RootCAs,
MinVersion: tls.VersionTLS12,
},
// The 1 is the version of the format. The process id, the message
// id and the structured data have no value.
beforeTime: "<" + strconv.Itoa(priority) + ">1 ",
afterTime: " " + hostname + " " + params.AppName + " - - - ",
records: make(chan []byte, params.Buffer),
}
}
// Write puts each line in p in the buffer, as the message of a record of
// its own, and never waits: when the buffer is full, the oldest record in
// it is dropped to make room. It is safe for concurrent use.
func (s *Sender) Write(p []byte) (int, error) {
at := requestlog.FormatTime(time.Now())
for line := range bytes.Lines(p) {
line = bytes.TrimSuffix(line, []byte("\n"))
if len(line) > 0 {
s.put(s.record(at, line))
}
}
return len(p), nil
}
// Sent is how many records have been sent.
func (s *Sender) Sent() int64 {
return s.sent.Load()
}
// Dropped is how many records were dropped: the oldest in a full buffer,
// and those whose sending failed.
func (s *Sender) Dropped() int64 {
return s.dropped.Load()
}
// Depth is how many records are in the buffer.
func (s *Sender) Depth() int {
return len(s.records)
}
// Run connects to the endpoint and sends each record as it comes into the
// buffer, until ctx is done. Then it sends the records still in the buffer,
// on the connection open at that time or, if there is none, on a new one,
// until none is left or one fails, and returns. How long it may take over
// that is for the caller to bound.
//
// A connection on which a record fails is closed, the record dropped, and
// a new one made at once. A failed attempt to connect is logged to
// processLog and followed by the next after firstRetryDelay,
// retryDelayFactor times as long after each further failure in a row up
// to maxRetryDelay. Meanwhile the records wait in the buffer.
func (s *Sender) Run(ctx context.Context, processLog *slog.Logger) {
conn := s.send(ctx, processLog)
if conn == nil && len(s.records) > 0 {
conn, _ = s.dial(context.WithoutCancel(ctx))
}
if conn == nil {
return
}
defer func() {
_ = conn.Close()
}()
for {
select {
case record := <-s.records:
if s.write(conn, record) != nil {
return
}
default:
return
}
}
}
// record returns line as an RFC 5424 record made at the time at, framed
// for the endpoint: on its own over UDP, since each datagram holds one,
// and over TCP and TLS after its length in bytes and a space, the
// octet-counted framing of RFC 6587 and RFC 5425.
func (s *Sender) record(at string, line []byte) []byte {
record := make([]byte, 0, len(s.beforeTime)+len(at)+len(s.afterTime)+len(line))
record = append(record, s.beforeTime...)
record = append(record, at...)
record = append(record, s.afterTime...)
record = append(record, line...)
if s.url.Scheme == SchemeUDP {
return record
}
return append([]byte(strconv.Itoa(len(record))+" "), record...)
}
// put adds record to the buffer, first dropping the oldest record in it
// while it is full.
func (s *Sender) put(record []byte) {
for {
select {
case s.records <- record:
return
default:
}
select {
case <-s.records:
s.dropped.Add(1)
default:
}
}
}
// send connects to the endpoint and sends each record as it comes into
// the buffer, until ctx is done, and returns the connection then open, or
// nil.
func (s *Sender) send(ctx context.Context, processLog *slog.Logger) net.Conn {
delay := firstRetryDelay
for {
conn, err := s.dial(ctx)
switch {
case ctx.Err() != nil:
return conn
case err != nil:
processLog.Warn("connecting to SWWAF_LOG_REMOTE_URL failed",
"error", err.Error(), "connecting_again_in", delay.String())
select {
case <-time.After(delay):
case <-ctx.Done():
return nil
}
delay = min(retryDelayFactor*delay, maxRetryDelay)
continue
}
delay = firstRetryDelay
err = s.sendOn(ctx, conn)
if err == nil {
return conn
}
_ = conn.Close()
}
}
// sendOn sends each record on conn as it comes into the buffer, until one
// fails, whose error it returns, or ctx is done.
func (s *Sender) sendOn(ctx context.Context, conn net.Conn) error {
for {
select {
case record := <-s.records:
err := s.write(conn, record)
if err != nil {
return err
}
case <-ctx.Done():
return nil
}
}
}
// write sends record on conn, and counts it as sent or, if that fails,
// as dropped.
func (s *Sender) write(conn net.Conn, record []byte) error {
_, err := conn.Write(record)
if err != nil {
s.dropped.Add(1)
return fmt.Errorf("send a record: %w", err)
}
s.sent.Add(1)
return nil
}
// dial connects to the endpoint.
func (s *Sender) dial(ctx context.Context) (net.Conn, error) {
dialer := &net.Dialer{Timeout: dialTimeout}
switch s.url.Scheme {
case SchemeUDP:
return dialer.DialContext(ctx, "udp", s.url.Host)
case SchemeTLS:
tlsDialer := &tls.Dialer{NetDialer: dialer, Config: s.tlsConfig}
return tlsDialer.DialContext(ctx, "tcp", s.url.Host)
default:
return dialer.DialContext(ctx, "tcp", s.url.Host)
}
}
+458
View File
@@ -0,0 +1,458 @@
package remotelog_test
import (
"bufio"
"bytes"
"context"
"crypto/ecdsa"
"crypto/elliptic"
"crypto/rand"
"crypto/tls"
"crypto/x509"
"crypto/x509/pkix"
"encoding/json"
"fmt"
"io"
"log/slog"
"math/big"
"net"
"net/url"
"os"
"slices"
"strconv"
"strings"
"sync"
"testing"
"testing/synctest"
"time"
"sneak.berlin/go/smallwebwaf/internal/remotelog"
)
// The tests run in a synctest bubble, where the time package runs on a
// clock of the test's own, which starts at 2000-01-01T00:00:00Z: a wait
// lasts exactly as long as it should, however slowly the test process
// runs, and synctest.Wait returns once the sender has done all it can
// before time passes. The endpoint is a listener on the loopback address.
// A test reads from it only once the records are on their way, and checks
// the sender's counts first, since a goroutine of the bubble that waits on
// the network keeps that clock from moving on.
const (
// started is the time a record made as a test starts gives.
started = "2000-01-01T00:00:00.000Z"
appName = "fsn1app1/gitea"
// local0 is the number of the default facility, and local0Info the
// priority of its records.
local0 = 16
local0Info = "<134>"
// loopback is where the endpoints listen.
loopback = "127.0.0.1:0"
)
func TestRecordsOverUDPGoOnePerDatagram(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
endpoint, err := (&net.ListenConfig{}).ListenPacket(t.Context(), "udp", loopback)
if err != nil {
t.Fatalf("listen: %v", err)
}
t.Cleanup(func() { _ = endpoint.Close() })
sender, _, _ := run(t, params(remotelog.SchemeUDP, endpoint.LocalAddr()))
_, _ = sender.Write([]byte(`{"type":"request"}` + "\n" + `{"type":"process"}` + "\n"))
synctest.Wait()
wantCounts(t, sender, 2, 0, 0)
for _, line := range []string{`{"type":"request"}`, `{"type":"process"}`} {
datagram := make([]byte, 1024)
n, _, err := endpoint.ReadFrom(datagram)
if err != nil {
t.Fatalf("read: %v", err)
}
want := record(t, local0Info, appName, line)
if string(datagram[:n]) != want {
t.Errorf("datagram %q, want %q", datagram[:n], want)
}
}
})
}
func TestRecordsOverTCPAreOctetCountedWithTheirFacility(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
endpoint := listen(t, loopback)
endpointParams := params(remotelog.SchemeTCP, endpoint.Addr())
endpointParams.Facility = 19 // local3
endpointParams.AppName = "gitea"
sender, _, _ := run(t, endpointParams)
_, _ = sender.Write([]byte("first\nsecond\n"))
synctest.Wait()
wantCounts(t, sender, 2, 0, 0)
frames := bufio.NewReader(accept(t, endpoint))
wantFrame(t, frames, record(t, "<158>", "gitea", "first"))
wantFrame(t, frames, record(t, "<158>", "gitea", "second"))
})
}
func TestStalledEndpointHoldsUpNoWriteAndOldestRecordsAreDropped(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
certificate, roots := testCertificate(t)
endpoint := listen(t, loopback)
endpointParams := params(remotelog.SchemeTLS, endpoint.Addr())
endpointParams.RootCAs = roots
endpointParams.Buffer = 3
sender, _, _ := run(t, endpointParams)
// The sender connects, and its TLS handshake waits for an answer
// the endpoint does not give yet.
conn := accept(t, endpoint)
var stdout bytes.Buffer
out := io.MultiWriter(&stdout, sender)
for i := range 5 {
_, _ = fmt.Fprintf(out, "line %d\n", i+1)
}
if stdout.String() != "line 1\nline 2\nline 3\nline 4\nline 5\n" {
t.Errorf("stdout has %q", stdout.String())
}
wantCounts(t, sender, 0, 2, 3)
// Once the endpoint answers, the three newest records are sent.
server := tls.Server(conn, &tls.Config{
Certificates: []tls.Certificate{certificate},
MinVersion: tls.VersionTLS12,
})
err := server.HandshakeContext(t.Context())
if err != nil {
t.Fatalf("handshake: %v", err)
}
synctest.Wait()
wantCounts(t, sender, 3, 2, 0)
frames := bufio.NewReader(server)
for _, line := range []string{"line 3", "line 4", "line 5"} {
wantFrame(t, frames, record(t, local0Info, appName, line))
}
})
}
func TestReconnectsWithBackoffAfterTheEndpointGoesAway(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
endpoint := listen(t, loopback)
addr := endpoint.Addr()
sender, logged, _ := run(t, params(remotelog.SchemeTCP, addr))
_, _ = sender.Write([]byte("one\n"))
synctest.Wait()
wantCounts(t, sender, 1, 0, 0)
conn := accept(t, endpoint)
wantFrame(t, bufio.NewReader(conn), record(t, local0Info, appName, "one"))
// The endpoint goes away. The sender notices when a record fails,
// and tries to connect again at once, then a second later, then two
// seconds after that.
_ = conn.Close()
_ = endpoint.Close()
writeUntilDropped(t, sender, 1)
sent := sender.Sent()
_, _ = sender.Write([]byte("two\n"))
time.Sleep(time.Second)
synctest.Wait()
endpoint = listen(t, addr.String())
time.Sleep(2*time.Second - time.Nanosecond)
synctest.Wait()
wantCounts(t, sender, sent, 1, 1)
// The endpoint is back, and the record waiting is sent.
time.Sleep(time.Nanosecond)
synctest.Wait()
wantCounts(t, sender, sent+1, 1, 0)
conn = accept(t, endpoint)
wantFrame(t, bufio.NewReader(conn), record(t, local0Info, appName, "two"))
wantRetries(t, logged, "1s", "2s")
// Having connected, the sender waits a second again after the
// next failure.
_ = conn.Close()
_ = endpoint.Close()
writeUntilDropped(t, sender, 2)
wantRetries(t, logged, "1s", "2s", "1s")
})
}
func TestRecordsWaitingAtTheStopAreSent(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
// Nothing listens at addr when the sender starts: it fails to
// connect, and waits a second to try again.
endpoint := listen(t, loopback)
addr := endpoint.Addr()
_ = endpoint.Close()
sender, logged, stop := run(t, params(remotelog.SchemeTCP, addr))
synctest.Wait()
wantRetries(t, logged, "1s")
_, _ = sender.Write([]byte("one\ntwo\n"))
endpoint = listen(t, addr.String())
// Stopped before that second is over, it connects to send them.
stop()
wantCounts(t, sender, 2, 0, 0)
frames := bufio.NewReader(accept(t, endpoint))
wantFrame(t, frames, record(t, local0Info, appName, "one"))
wantFrame(t, frames, record(t, local0Info, appName, "two"))
})
}
// output collects what the sender logs.
type output struct {
mu sync.Mutex
buf bytes.Buffer
}
// Write adds lines the sender logs.
func (o *output) Write(p []byte) (int, error) {
o.mu.Lock()
defer o.mu.Unlock()
return o.buf.Write(p)
}
// text returns everything logged so far.
func (o *output) text() string {
o.mu.Lock()
defer o.mu.Unlock()
return o.buf.String()
}
// params returns the settings of a Sender for the endpoint at addr, in
// the form scheme names: room for ten lines, the default facility, and
// appName.
func params(scheme string, addr net.Addr) remotelog.Params {
return remotelog.Params{
URL: &url.URL{Scheme: scheme, Host: addr.String()},
Buffer: 10,
Facility: local0,
AppName: appName,
}
}
// run runs a Sender with settings until the test ends or the function
// it returns is called, which waits for Run to return. It returns the
// Sender, and what it logs.
func run(t *testing.T, settings remotelog.Params) (*remotelog.Sender, *output, func()) {
t.Helper()
sender := remotelog.New(settings)
logged := &output{}
ctx, cancel := context.WithCancel(t.Context())
ran := make(chan struct{})
go func() {
sender.Run(ctx, slog.New(slog.NewJSONHandler(logged, nil)))
close(ran)
}()
stop := func() {
cancel()
<-ran
}
t.Cleanup(stop)
return sender, logged, stop
}
// listen returns a TCP listener at addr, closed when the test ends.
func listen(t *testing.T, addr string) net.Listener {
t.Helper()
listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", addr)
if err != nil {
t.Fatalf("listen: %v", err)
}
t.Cleanup(func() { _ = listener.Close() })
return listener
}
// accept returns the next connection to listener, closed when the test
// ends.
func accept(t *testing.T, listener net.Listener) net.Conn {
t.Helper()
conn, err := listener.Accept()
if err != nil {
t.Fatalf("accept: %v", err)
}
t.Cleanup(func() { _ = conn.Close() })
return conn
}
// record returns the record of line made as the test started, with the
// priority and the app name given.
func record(t *testing.T, priority, app, line string) string {
t.Helper()
hostname, err := os.Hostname()
if err != nil || hostname == "" {
hostname = "-"
}
return priority + "1 " + started + " " + hostname + " " + app + " - - - " + line
}
// wantFrame reads the next octet-counted frame from frames, and checks
// that it holds want.
func wantFrame(t *testing.T, frames *bufio.Reader, want string) {
t.Helper()
count, err := frames.ReadString(' ')
if err != nil {
t.Fatalf("read a frame's length: %v", err)
}
length, err := strconv.Atoi(strings.TrimSuffix(count, " "))
if err != nil {
t.Fatalf("frame starts %q, not with its length", count)
}
got := make([]byte, length)
_, err = io.ReadFull(frames, got)
if err != nil {
t.Fatalf("read a frame: %v", err)
}
if string(got) != want {
t.Errorf("frame %q, want %q", got, want)
}
}
// wantCounts checks the records sender has sent, dropped and holds in
// its buffer.
func wantCounts(
t *testing.T, sender *remotelog.Sender, sent, dropped int64, depth int,
) {
t.Helper()
if sender.Sent() != sent || sender.Dropped() != dropped || sender.Depth() != depth {
t.Fatalf("sent %d, dropped %d, %d in the buffer; want %d, %d and %d",
sender.Sent(), sender.Dropped(), sender.Depth(), sent, dropped, depth)
}
}
// writeUntilDropped writes a line at a time until the count of records
// sender has dropped reaches dropped. The records it sends on a
// connection the endpoint has closed are lost before one fails; how many
// depends on when the endpoint's host answers that the connection is
// gone.
func writeUntilDropped(t *testing.T, sender *remotelog.Sender, dropped int64) {
t.Helper()
for sender.Dropped() < dropped {
_, _ = sender.Write([]byte("lost\n"))
synctest.Wait()
}
}
// wantRetries checks that the sender logged a failed attempt to connect
// for each of delays, the time until the next attempt, in order, and
// logged nothing else.
func wantRetries(t *testing.T, logged *output, delays ...string) {
t.Helper()
var got []string
for line := range strings.Lines(logged.text()) {
var fields map[string]any
err := json.Unmarshal([]byte(line), &fields)
if err != nil || fields["msg"] != "connecting to SWWAF_LOG_REMOTE_URL failed" {
t.Fatalf("logged %q", line)
}
delay, _ := fields["connecting_again_in"].(string)
got = append(got, delay)
}
if !slices.Equal(got, delays) {
t.Errorf("logged failures to connect again in %v, want %v", got, delays)
}
}
// testCertificate returns a certificate for 127.0.0.1 that is its own
// CA, and a pool that holds it.
func testCertificate(t *testing.T) (tls.Certificate, *x509.CertPool) {
t.Helper()
key, err := ecdsa.GenerateKey(elliptic.P256(), rand.Reader)
if err != nil {
t.Fatalf("generate a key: %v", err)
}
template := &x509.Certificate{
SerialNumber: big.NewInt(1),
Subject: pkix.Name{CommonName: "smallwebwaf test CA"},
NotBefore: time.Now().Add(-time.Hour),
NotAfter: time.Now().Add(time.Hour),
IsCA: true,
BasicConstraintsValid: true,
KeyUsage: x509.KeyUsageCertSign | x509.KeyUsageDigitalSignature,
ExtKeyUsage: []x509.ExtKeyUsage{x509.ExtKeyUsageServerAuth},
IPAddresses: []net.IP{net.IPv4(127, 0, 0, 1)},
}
der, err := x509.CreateCertificate(rand.Reader, template, template,
&key.PublicKey, key)
if err != nil {
t.Fatalf("create a certificate: %v", err)
}
certificate, err := x509.ParseCertificate(der)
if err != nil {
t.Fatalf("parse the certificate: %v", err)
}
roots := x509.NewCertPool()
roots.AddCert(certificate)
return tls.Certificate{Certificate: [][]byte{der}, PrivateKey: key}, roots
}