consul/agent/xds/endpoints_test.go

381 lines
11 KiB
Go
Raw Normal View History

package xds
import (
"log"
"os"
"path"
"sort"
"testing"
"github.com/mitchellh/copystructure"
"github.com/stretchr/testify/require"
envoy "github.com/envoyproxy/go-control-plane/envoy/api/v2"
"github.com/envoyproxy/go-control-plane/envoy/api/v2/core"
envoyendpoint "github.com/envoyproxy/go-control-plane/envoy/api/v2/endpoint"
"github.com/hashicorp/consul/agent/proxycfg"
"github.com/hashicorp/consul/agent/structs"
testinf "github.com/mitchellh/go-testing-interface"
)
func Test_makeLoadAssignment(t *testing.T) {
testCheckServiceNodes := structs.CheckServiceNodes{
structs.CheckServiceNode{
Node: &structs.Node{
ID: "node1-id",
Node: "node1",
Address: "10.10.10.10",
Datacenter: "dc1",
},
Service: &structs.NodeService{
Service: "web",
Port: 1234,
},
Checks: structs.HealthChecks{
&structs.HealthCheck{
Node: "node1",
CheckID: "serfHealth",
Status: "passing",
},
&structs.HealthCheck{
Node: "node1",
ServiceID: "web",
CheckID: "web:check",
Status: "passing",
},
},
},
structs.CheckServiceNode{
Node: &structs.Node{
ID: "node2-id",
Node: "node2",
Address: "10.10.10.20",
Datacenter: "dc1",
},
Service: &structs.NodeService{
Service: "web",
Port: 1234,
},
Checks: structs.HealthChecks{
&structs.HealthCheck{
Node: "node2",
CheckID: "serfHealth",
Status: "passing",
},
&structs.HealthCheck{
Node: "node2",
ServiceID: "web",
CheckID: "web:check",
Status: "passing",
},
},
},
}
testWeightedCheckServiceNodesRaw, err := copystructure.Copy(testCheckServiceNodes)
require.NoError(t, err)
testWeightedCheckServiceNodes := testWeightedCheckServiceNodesRaw.(structs.CheckServiceNodes)
testWeightedCheckServiceNodes[0].Service.Weights = &structs.Weights{
Passing: 10,
Warning: 1,
}
testWeightedCheckServiceNodes[1].Service.Weights = &structs.Weights{
Passing: 5,
Warning: 0,
}
testWarningCheckServiceNodesRaw, err := copystructure.Copy(testWeightedCheckServiceNodes)
require.NoError(t, err)
testWarningCheckServiceNodes := testWarningCheckServiceNodesRaw.(structs.CheckServiceNodes)
testWarningCheckServiceNodes[0].Checks[0].Status = "warning"
testWarningCheckServiceNodes[1].Checks[0].Status = "warning"
// TODO(rb): test onlypassing
tests := []struct {
name string
clusterName string
endpoints []loadAssignmentEndpointGroup
want *envoy.ClusterLoadAssignment
}{
{
name: "no instances",
clusterName: "service:test",
endpoints: []loadAssignmentEndpointGroup{
{Endpoints: nil},
},
want: &envoy.ClusterLoadAssignment{
ClusterName: "service:test",
Endpoints: []envoyendpoint.LocalityLbEndpoints{{
LbEndpoints: []envoyendpoint.LbEndpoint{},
}},
},
},
{
name: "instances, no weights",
clusterName: "service:test",
endpoints: []loadAssignmentEndpointGroup{
{Endpoints: testCheckServiceNodes},
},
want: &envoy.ClusterLoadAssignment{
ClusterName: "service:test",
Endpoints: []envoyendpoint.LocalityLbEndpoints{{
LbEndpoints: []envoyendpoint.LbEndpoint{
envoyendpoint.LbEndpoint{
HostIdentifier: &envoyendpoint.LbEndpoint_Endpoint{
Endpoint: &envoyendpoint.Endpoint{
Address: makeAddressPtr("10.10.10.10", 1234),
}},
HealthStatus: core.HealthStatus_HEALTHY,
LoadBalancingWeight: makeUint32Value(1),
},
envoyendpoint.LbEndpoint{
HostIdentifier: &envoyendpoint.LbEndpoint_Endpoint{
Endpoint: &envoyendpoint.Endpoint{
Address: makeAddressPtr("10.10.10.20", 1234),
}},
HealthStatus: core.HealthStatus_HEALTHY,
LoadBalancingWeight: makeUint32Value(1),
},
},
}},
},
},
{
name: "instances, healthy weights",
clusterName: "service:test",
endpoints: []loadAssignmentEndpointGroup{
{Endpoints: testWeightedCheckServiceNodes},
},
want: &envoy.ClusterLoadAssignment{
ClusterName: "service:test",
Endpoints: []envoyendpoint.LocalityLbEndpoints{{
LbEndpoints: []envoyendpoint.LbEndpoint{
envoyendpoint.LbEndpoint{
HostIdentifier: &envoyendpoint.LbEndpoint_Endpoint{
Endpoint: &envoyendpoint.Endpoint{
Address: makeAddressPtr("10.10.10.10", 1234),
}},
HealthStatus: core.HealthStatus_HEALTHY,
LoadBalancingWeight: makeUint32Value(10),
},
envoyendpoint.LbEndpoint{
HostIdentifier: &envoyendpoint.LbEndpoint_Endpoint{
Endpoint: &envoyendpoint.Endpoint{
Address: makeAddressPtr("10.10.10.20", 1234),
}},
HealthStatus: core.HealthStatus_HEALTHY,
LoadBalancingWeight: makeUint32Value(5),
},
},
}},
},
},
{
name: "instances, warning weights",
clusterName: "service:test",
endpoints: []loadAssignmentEndpointGroup{
{Endpoints: testWarningCheckServiceNodes},
},
want: &envoy.ClusterLoadAssignment{
ClusterName: "service:test",
Endpoints: []envoyendpoint.LocalityLbEndpoints{{
LbEndpoints: []envoyendpoint.LbEndpoint{
envoyendpoint.LbEndpoint{
HostIdentifier: &envoyendpoint.LbEndpoint_Endpoint{
Endpoint: &envoyendpoint.Endpoint{
Address: makeAddressPtr("10.10.10.10", 1234),
}},
HealthStatus: core.HealthStatus_HEALTHY,
LoadBalancingWeight: makeUint32Value(1),
},
envoyendpoint.LbEndpoint{
HostIdentifier: &envoyendpoint.LbEndpoint_Endpoint{
Endpoint: &envoyendpoint.Endpoint{
Address: makeAddressPtr("10.10.10.20", 1234),
}},
HealthStatus: core.HealthStatus_UNHEALTHY,
LoadBalancingWeight: makeUint32Value(1),
},
},
}},
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := makeLoadAssignment(
tt.clusterName,
tt.endpoints,
"dc1",
)
require.Equal(t, tt.want, got)
})
}
}
func Test_endpointsFromSnapshot(t *testing.T) {
tests := []struct {
name string
create func(t testinf.T) *proxycfg.ConfigSnapshot
// Setup is called before the test starts. It is passed the snapshot from
// create func and is allowed to modify it in any way to setup the
// test input.
setup func(snap *proxycfg.ConfigSnapshot)
overrideGoldenName string
}{
{
name: "defaults",
create: proxycfg.TestConfigSnapshot,
setup: nil, // Default snapshot
},
{
name: "mesh-gateway",
create: proxycfg.TestConfigSnapshotMeshGateway,
setup: nil,
},
{
name: "connect-proxy-with-chain",
create: proxycfg.TestConfigSnapshotDiscoveryChain,
setup: nil,
},
connect: reconcile how upstream configuration works with discovery chains (#6225) * connect: reconcile how upstream configuration works with discovery chains The following upstream config fields for connect sidecars sanely integrate into discovery chain resolution: - Destination Namespace/Datacenter: Compilation occurs locally but using different default values for namespaces and datacenters. The xDS clusters that are created are named as they normally would be. - Mesh Gateway Mode (single upstream): If set this value overrides any value computed for any resolver for the entire discovery chain. The xDS clusters that are created may be named differently (see below). - Mesh Gateway Mode (whole sidecar): If set this value overrides any value computed for any resolver for the entire discovery chain. If this is specifically overridden for a single upstream this value is ignored in that case. The xDS clusters that are created may be named differently (see below). - Protocol (in opaque config): If set this value overrides the value computed when evaluating the entire discovery chain. If the normal chain would be TCP or if this override is set to TCP then the result is that we explicitly disable L7 Routing and Splitting. The xDS clusters that are created may be named differently (see below). - Connect Timeout (in opaque config): If set this value overrides the value for any resolver in the entire discovery chain. The xDS clusters that are created may be named differently (see below). If any of the above overrides affect the actual result of compiling the discovery chain (i.e. "tcp" becomes "grpc" instead of being a no-op override to "tcp") then the relevant parameters are hashed and provided to the xDS layer as a prefix for use in naming the Clusters. This is to ensure that if one Upstream discovery chain has no overrides and tangentially needs a cluster named "api.default.XXX", and another Upstream does have overrides for "api.default.XXX" that they won't cross-pollinate against the operator's wishes. Fixes #6159
2019-08-02 03:03:34 +00:00
{
name: "connect-proxy-with-chain-and-overrides",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithOverrides,
setup: nil,
},
{
name: "connect-proxy-with-chain-and-failover",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithFailover,
setup: nil,
},
connect: fix failover through a mesh gateway to a remote datacenter (#6259) Failover is pushed entirely down to the data plane by creating envoy clusters and putting each successive destination in a different load assignment priority band. For example this shows that normally requests go to 1.2.3.4:8080 but when that fails they go to 6.7.8.9:8080: - name: foo load_assignment: cluster_name: foo policy: overprovisioning_factor: 100000 endpoints: - priority: 0 lb_endpoints: - endpoint: address: socket_address: address: 1.2.3.4 port_value: 8080 - priority: 1 lb_endpoints: - endpoint: address: socket_address: address: 6.7.8.9 port_value: 8080 Mesh gateways route requests based solely on the SNI header tacked onto the TLS layer. Envoy currently only lets you configure the outbound SNI header at the cluster layer. If you try to failover through a mesh gateway you ideally would configure the SNI value per endpoint, but that's not possible in envoy today. This PR introduces a simpler way around the problem for now: 1. We identify any target of failover that will use mesh gateway mode local or remote and then further isolate any resolver node in the compiled discovery chain that has a failover destination set to one of those targets. 2. For each of these resolvers we will perform a small measurement of comparative healths of the endpoints that come back from the health API for the set of primary target and serial failover targets. We walk the list of targets in order and if any endpoint is healthy we return that target, otherwise we move on to the next target. 3. The CDS and EDS endpoints both perform the measurements in (2) for the affected resolver nodes. 4. For CDS this measurement selects which TLS SNI field to use for the cluster (note the cluster is always going to be named for the primary target) 5. For EDS this measurement selects which set of endpoints will populate the cluster. Priority tiered failover is ignored. One of the big downsides to this approach to failover is that the failover detection and correction is going to be controlled by consul rather than deferring that entirely to the data plane as with the prior version. This also means that we are bound to only failover using official health signals and cannot make use of data plane signals like outlier detection to affect failover. In this specific scenario the lack of data plane signals is ok because the effectiveness is already muted by the fact that the ultimate destination endpoints will have their data plane signals scrambled when they pass through the mesh gateway wrapper anyway so we're not losing much. Another related fix is that we now use the endpoint health from the underlying service, not the health of the gateway (regardless of failover mode).
2019-08-05 18:30:35 +00:00
{
name: "connect-proxy-with-tcp-chain-failover-through-remote-gateway",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithFailoverThroughRemoteGateway,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-failover-through-remote-gateway-triggered",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithFailoverThroughRemoteGatewayTriggered,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-double-failover-through-remote-gateway",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithDoubleFailoverThroughRemoteGateway,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-double-failover-through-remote-gateway-triggered",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithDoubleFailoverThroughRemoteGatewayTriggered,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-failover-through-local-gateway",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithFailoverThroughLocalGateway,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-failover-through-local-gateway-triggered",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithFailoverThroughLocalGatewayTriggered,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-double-failover-through-local-gateway",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithDoubleFailoverThroughLocalGateway,
setup: nil,
},
{
name: "connect-proxy-with-tcp-chain-double-failover-through-local-gateway-triggered",
create: proxycfg.TestConfigSnapshotDiscoveryChainWithDoubleFailoverThroughLocalGatewayTriggered,
setup: nil,
},
{
name: "splitter-with-resolver-redirect",
create: proxycfg.TestConfigSnapshotDiscoveryChain_SplitterWithResolverRedirectMultiDC,
setup: nil,
},
{
name: "mesh-gateway-service-subsets",
create: proxycfg.TestConfigSnapshotMeshGateway,
setup: func(snap *proxycfg.ConfigSnapshot) {
snap.MeshGateway.ServiceResolvers = map[string]*structs.ServiceResolverConfigEntry{
"bar": &structs.ServiceResolverConfigEntry{
Kind: structs.ServiceResolver,
Name: "bar",
Subsets: map[string]structs.ServiceResolverSubset{
"v1": structs.ServiceResolverSubset{
Filter: "Service.Meta.version == 1",
},
"v2": structs.ServiceResolverSubset{
Filter: "Service.Meta.version == 2",
OnlyPassing: true,
},
},
},
"foo": &structs.ServiceResolverConfigEntry{
Kind: structs.ServiceResolver,
Name: "foo",
Subsets: map[string]structs.ServiceResolverSubset{
"v1": structs.ServiceResolverSubset{
Filter: "Service.Meta.version == 1",
},
"v2": structs.ServiceResolverSubset{
Filter: "Service.Meta.version == 2",
OnlyPassing: true,
},
},
},
}
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
require := require.New(t)
// Sanity check default with no overrides first
snap := tt.create(t)
// We need to replace the TLS certs with deterministic ones to make golden
// files workable. Note we don't update these otherwise they'd change
// golden files for every test case and so not be any use!
if snap.ConnectProxy.Leaf != nil {
snap.ConnectProxy.Leaf.CertPEM = golden(t, "test-leaf-cert", "")
snap.ConnectProxy.Leaf.PrivateKeyPEM = golden(t, "test-leaf-key", "")
}
if snap.Roots != nil {
snap.Roots.Roots[0].RootCert = golden(t, "test-root-cert", "")
}
if tt.setup != nil {
tt.setup(snap)
}
// Need server just for logger dependency
s := Server{Logger: log.New(os.Stderr, "", log.LstdFlags)}
endpoints, err := s.endpointsFromSnapshot(snap, "my-token")
sort.Slice(endpoints, func(i, j int) bool {
return endpoints[i].(*envoy.ClusterLoadAssignment).ClusterName < endpoints[j].(*envoy.ClusterLoadAssignment).ClusterName
})
require.NoError(err)
r, err := createResponse(EndpointType, "00000001", "00000001", endpoints)
require.NoError(err)
gotJSON := responseToJSON(t, r)
gName := tt.name
if tt.overrideGoldenName != "" {
gName = tt.overrideGoldenName
}
require.JSONEq(golden(t, path.Join("endpoints", gName), gotJSON), gotJSON)
})
}
}