crypto/tls: don't cache marshal'd bytes

Only cache the wire representation for clientHelloMsg and serverHelloMsg
during unmarshal, which are the only places we actually need to hold
onto them. For everything else, remove the raw field.

This appears to have zero performance impact:

name                                               old time/op   new time/op   delta
CertCache/0-10                                       177µs ± 2%    189µs ±11%   ~     (p=0.700 n=3+3)
CertCache/1-10                                       184µs ± 3%    182µs ± 6%   ~     (p=1.000 n=3+3)
CertCache/2-10                                       187µs ±12%    187µs ± 2%   ~     (p=1.000 n=3+3)
CertCache/3-10                                       204µs ±21%    187µs ± 1%   ~     (p=0.700 n=3+3)
HandshakeServer/RSA-10                               410µs ± 2%    410µs ± 3%   ~     (p=1.000 n=3+3)
HandshakeServer/ECDHE-P256-RSA/TLSv13-10             473µs ± 3%    460µs ± 2%   ~     (p=0.200 n=3+3)
HandshakeServer/ECDHE-P256-RSA/TLSv12-10             498µs ± 3%    489µs ± 2%   ~     (p=0.700 n=3+3)
HandshakeServer/ECDHE-P256-ECDSA-P256/TLSv13-10      140µs ± 5%    138µs ± 5%   ~     (p=1.000 n=3+3)
HandshakeServer/ECDHE-P256-ECDSA-P256/TLSv12-10      132µs ± 1%    133µs ± 2%   ~     (p=0.400 n=3+3)
HandshakeServer/ECDHE-X25519-ECDSA-P256/TLSv13-10    168µs ± 1%    171µs ± 4%   ~     (p=1.000 n=3+3)
HandshakeServer/ECDHE-X25519-ECDSA-P256/TLSv12-10    166µs ± 3%    163µs ± 0%   ~     (p=0.700 n=3+3)
HandshakeServer/ECDHE-P521-ECDSA-P521/TLSv13-10     1.87ms ± 2%   1.81ms ± 0%   ~     (p=0.100 n=3+3)
HandshakeServer/ECDHE-P521-ECDSA-P521/TLSv12-10     1.86ms ± 0%   1.86ms ± 1%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/1MB/TLSv12-10                  6.79ms ± 3%   6.73ms ± 0%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/1MB/TLSv13-10                  6.73ms ± 1%   6.75ms ± 0%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/2MB/TLSv12-10                  12.8ms ± 2%   12.7ms ± 0%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/2MB/TLSv13-10                  13.1ms ± 3%   12.8ms ± 1%   ~     (p=0.400 n=3+3)
Throughput/MaxPacket/4MB/TLSv12-10                  24.9ms ± 2%   24.7ms ± 1%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/4MB/TLSv13-10                  26.0ms ± 4%   24.9ms ± 1%   ~     (p=0.100 n=3+3)
Throughput/MaxPacket/8MB/TLSv12-10                  50.0ms ± 3%   48.9ms ± 0%   ~     (p=0.200 n=3+3)
Throughput/MaxPacket/8MB/TLSv13-10                  49.8ms ± 2%   49.3ms ± 1%   ~     (p=0.400 n=3+3)
Throughput/MaxPacket/16MB/TLSv12-10                 97.3ms ± 1%   97.4ms ± 0%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/16MB/TLSv13-10                 97.9ms ± 0%   97.9ms ± 1%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/32MB/TLSv12-10                  195ms ± 0%    194ms ± 1%   ~     (p=0.400 n=3+3)
Throughput/MaxPacket/32MB/TLSv13-10                  196ms ± 0%    196ms ± 1%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/64MB/TLSv12-10                  405ms ± 3%    385ms ± 0%   ~     (p=0.100 n=3+3)
Throughput/MaxPacket/64MB/TLSv13-10                  391ms ± 1%    388ms ± 1%   ~     (p=0.200 n=3+3)
Throughput/DynamicPacket/1MB/TLSv12-10              6.75ms ± 0%   6.75ms ± 1%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/1MB/TLSv13-10              6.84ms ± 1%   6.77ms ± 0%   ~     (p=0.100 n=3+3)
Throughput/DynamicPacket/2MB/TLSv12-10              12.8ms ± 1%   12.8ms ± 1%   ~     (p=0.400 n=3+3)
Throughput/DynamicPacket/2MB/TLSv13-10              12.8ms ± 1%   13.0ms ± 1%   ~     (p=0.200 n=3+3)
Throughput/DynamicPacket/4MB/TLSv12-10              24.8ms ± 1%   24.8ms ± 0%   ~     (p=1.000 n=3+3)
Throughput/DynamicPacket/4MB/TLSv13-10              25.1ms ± 2%   25.1ms ± 1%   ~     (p=1.000 n=3+3)
Throughput/DynamicPacket/8MB/TLSv12-10              49.2ms ± 2%   48.9ms ± 0%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/8MB/TLSv13-10              49.3ms ± 1%   49.4ms ± 1%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/16MB/TLSv12-10             97.1ms ± 0%   98.0ms ± 1%   ~     (p=0.200 n=3+3)
Throughput/DynamicPacket/16MB/TLSv13-10             98.8ms ± 1%   98.4ms ± 1%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/32MB/TLSv12-10              192ms ± 0%    198ms ± 5%   ~     (p=0.100 n=3+3)
Throughput/DynamicPacket/32MB/TLSv13-10              194ms ± 0%    196ms ± 1%   ~     (p=0.400 n=3+3)
Throughput/DynamicPacket/64MB/TLSv12-10              385ms ± 1%    384ms ± 0%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/64MB/TLSv13-10              387ms ± 0%    388ms ± 0%   ~     (p=0.400 n=3+3)
Latency/MaxPacket/200kbps/TLSv12-10                  694ms ± 0%    694ms ± 0%   ~     (p=0.700 n=3+3)
Latency/MaxPacket/200kbps/TLSv13-10                  699ms ± 0%    699ms ± 0%   ~     (p=0.700 n=3+3)
Latency/MaxPacket/500kbps/TLSv12-10                  278ms ± 0%    278ms ± 0%   ~     (p=0.400 n=3+3)
Latency/MaxPacket/500kbps/TLSv13-10                  280ms ± 0%    280ms ± 0%   ~     (p=1.000 n=3+3)
Latency/MaxPacket/1000kbps/TLSv12-10                 140ms ± 1%    140ms ± 0%   ~     (p=0.700 n=3+3)
Latency/MaxPacket/1000kbps/TLSv13-10                 141ms ± 0%    141ms ± 0%   ~     (p=1.000 n=3+3)
Latency/MaxPacket/2000kbps/TLSv12-10                70.5ms ± 0%   70.4ms ± 0%   ~     (p=0.700 n=3+3)
Latency/MaxPacket/2000kbps/TLSv13-10                70.7ms ± 0%   70.7ms ± 0%   ~     (p=0.700 n=3+3)
Latency/MaxPacket/5000kbps/TLSv12-10                28.8ms ± 0%   28.8ms ± 0%   ~     (p=0.700 n=3+3)
Latency/MaxPacket/5000kbps/TLSv13-10                28.9ms ± 0%   28.9ms ± 0%   ~     (p=0.700 n=3+3)
Latency/DynamicPacket/200kbps/TLSv12-10              134ms ± 0%    134ms ± 0%   ~     (p=0.700 n=3+3)
Latency/DynamicPacket/200kbps/TLSv13-10              138ms ± 0%    138ms ± 0%   ~     (p=1.000 n=3+3)
Latency/DynamicPacket/500kbps/TLSv12-10             54.1ms ± 0%   54.1ms ± 0%   ~     (p=1.000 n=3+3)
Latency/DynamicPacket/500kbps/TLSv13-10             55.7ms ± 0%   55.7ms ± 0%   ~     (p=0.100 n=3+3)
Latency/DynamicPacket/1000kbps/TLSv12-10            27.6ms ± 0%   27.6ms ± 0%   ~     (p=0.200 n=3+3)
Latency/DynamicPacket/1000kbps/TLSv13-10            28.4ms ± 0%   28.4ms ± 0%   ~     (p=0.200 n=3+3)
Latency/DynamicPacket/2000kbps/TLSv12-10            14.4ms ± 0%   14.4ms ± 0%   ~     (p=1.000 n=3+3)
Latency/DynamicPacket/2000kbps/TLSv13-10            14.6ms ± 0%   14.6ms ± 0%   ~     (p=1.000 n=3+3)
Latency/DynamicPacket/5000kbps/TLSv12-10            6.44ms ± 0%   6.45ms ± 0%   ~     (p=0.100 n=3+3)
Latency/DynamicPacket/5000kbps/TLSv13-10            6.49ms ± 0%   6.49ms ± 0%   ~     (p=0.700 n=3+3)

name                                               old speed     new speed     delta
Throughput/MaxPacket/1MB/TLSv12-10                 155MB/s ± 3%  156MB/s ± 0%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/1MB/TLSv13-10                 156MB/s ± 1%  155MB/s ± 0%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/2MB/TLSv12-10                 163MB/s ± 2%  165MB/s ± 0%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/2MB/TLSv13-10                 160MB/s ± 3%  164MB/s ± 1%   ~     (p=0.400 n=3+3)
Throughput/MaxPacket/4MB/TLSv12-10                 168MB/s ± 2%  170MB/s ± 1%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/4MB/TLSv13-10                 162MB/s ± 4%  168MB/s ± 1%   ~     (p=0.100 n=3+3)
Throughput/MaxPacket/8MB/TLSv12-10                 168MB/s ± 3%  172MB/s ± 0%   ~     (p=0.200 n=3+3)
Throughput/MaxPacket/8MB/TLSv13-10                 168MB/s ± 2%  170MB/s ± 1%   ~     (p=0.400 n=3+3)
Throughput/MaxPacket/16MB/TLSv12-10                172MB/s ± 1%  172MB/s ± 0%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/16MB/TLSv13-10                171MB/s ± 0%  171MB/s ± 1%   ~     (p=1.000 n=3+3)
Throughput/MaxPacket/32MB/TLSv12-10                172MB/s ± 0%  173MB/s ± 1%   ~     (p=0.400 n=3+3)
Throughput/MaxPacket/32MB/TLSv13-10                171MB/s ± 0%  172MB/s ± 1%   ~     (p=0.700 n=3+3)
Throughput/MaxPacket/64MB/TLSv12-10                166MB/s ± 3%  174MB/s ± 0%   ~     (p=0.100 n=3+3)
Throughput/MaxPacket/64MB/TLSv13-10                171MB/s ± 1%  173MB/s ± 1%   ~     (p=0.200 n=3+3)
Throughput/DynamicPacket/1MB/TLSv12-10             155MB/s ± 0%  155MB/s ± 1%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/1MB/TLSv13-10             153MB/s ± 1%  155MB/s ± 0%   ~     (p=0.100 n=3+3)
Throughput/DynamicPacket/2MB/TLSv12-10             164MB/s ± 1%  164MB/s ± 1%   ~     (p=0.400 n=3+3)
Throughput/DynamicPacket/2MB/TLSv13-10             163MB/s ± 1%  162MB/s ± 1%   ~     (p=0.200 n=3+3)
Throughput/DynamicPacket/4MB/TLSv12-10             169MB/s ± 1%  169MB/s ± 0%   ~     (p=1.000 n=3+3)
Throughput/DynamicPacket/4MB/TLSv13-10             167MB/s ± 1%  167MB/s ± 1%   ~     (p=1.000 n=3+3)
Throughput/DynamicPacket/8MB/TLSv12-10             170MB/s ± 2%  171MB/s ± 0%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/8MB/TLSv13-10             170MB/s ± 1%  170MB/s ± 1%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/16MB/TLSv12-10            173MB/s ± 0%  171MB/s ± 1%   ~     (p=0.200 n=3+3)
Throughput/DynamicPacket/16MB/TLSv13-10            170MB/s ± 1%  170MB/s ± 1%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/32MB/TLSv12-10            175MB/s ± 0%  170MB/s ± 5%   ~     (p=0.100 n=3+3)
Throughput/DynamicPacket/32MB/TLSv13-10            173MB/s ± 0%  171MB/s ± 1%   ~     (p=0.300 n=3+3)
Throughput/DynamicPacket/64MB/TLSv12-10            174MB/s ± 1%  175MB/s ± 0%   ~     (p=0.700 n=3+3)
Throughput/DynamicPacket/64MB/TLSv13-10            174MB/s ± 0%  173MB/s ± 0%   ~     (p=0.400 n=3+3)

Change-Id: Ifa79cce002011850ed8b2835edd34f60e014eea8
Cq-Include-Trybots: luci.golang.try:gotip-linux-amd64-longtest,gotip-linux-arm64-longtest
Reviewed-on: https://go-review.googlesource.com/c/go/+/580215
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Damien Neil <dneil@google.com>
Reviewed-by: Filippo Valsorda <filippo@golang.org>
Auto-Submit: Roland Shoemaker <roland@golang.org>
This commit is contained in:
Roland Shoemaker 2024-04-18 10:51:25 -07:00 committed by Gopher Robot
parent c16fc29ae8
commit 990f526003
4 changed files with 114 additions and 189 deletions

View file

@ -53,49 +53,61 @@ func TestMarshalUnmarshal(t *testing.T) {
for i, m := range tests {
ty := reflect.ValueOf(m).Type()
n := 100
if testing.Short() {
n = 5
}
for j := 0; j < n; j++ {
v, ok := quick.Value(ty, rand)
if !ok {
t.Errorf("#%d: failed to create value", i)
break
t.Run(ty.String(), func(t *testing.T) {
n := 100
if testing.Short() {
n = 5
}
for j := 0; j < n; j++ {
v, ok := quick.Value(ty, rand)
if !ok {
t.Errorf("#%d: failed to create value", i)
break
}
m1 := v.Interface().(handshakeMessage)
marshaled := mustMarshal(t, m1)
if !m.unmarshal(marshaled) {
t.Errorf("#%d failed to unmarshal %#v %x", i, m1, marshaled)
break
}
m.marshal() // to fill any marshal cache in the message
m1 := v.Interface().(handshakeMessage)
marshaled := mustMarshal(t, m1)
if !m.unmarshal(marshaled) {
t.Errorf("#%d failed to unmarshal %#v %x", i, m1, marshaled)
break
}
if m, ok := m.(*SessionState); ok {
m.activeCertHandles = nil
}
if m, ok := m.(*SessionState); ok {
m.activeCertHandles = nil
}
if !reflect.DeepEqual(m1, m) {
t.Errorf("#%d got:%#v want:%#v %x", i, m, m1, marshaled)
break
}
// clientHelloMsg and serverHelloMsg, when unmarshalled, store
// their original representation, for later use in the handshake
// transcript. In order to prevent DeepEqual from failing since
// we didn't create the original message via unmarshalling, nil
// the field.
switch t := m.(type) {
case *clientHelloMsg:
t.original = nil
case *serverHelloMsg:
t.original = nil
}
if i >= 3 {
// The first three message types (ClientHello,
// ServerHello and Finished) are allowed to
// have parsable prefixes because the extension
// data is optional and the length of the
// Finished varies across versions.
for j := 0; j < len(marshaled); j++ {
if m.unmarshal(marshaled[0:j]) {
t.Errorf("#%d unmarshaled a prefix of length %d of %#v", i, j, m1)
break
if !reflect.DeepEqual(m1, m) {
t.Errorf("#%d got:%#v want:%#v %x", i, m, m1, marshaled)
break
}
if i >= 3 {
// The first three message types (ClientHello,
// ServerHello and Finished) are allowed to
// have parsable prefixes because the extension
// data is optional and the length of the
// Finished varies across versions.
for j := 0; j < len(marshaled); j++ {
if m.unmarshal(marshaled[0:j]) {
t.Errorf("#%d unmarshaled a prefix of length %d of %#v", i, j, m1)
break
}
}
}
}
}
})
}
}