open-nomad/nomad/testing.go

227 lines
6 KiB
Go
Raw Normal View History

2018-01-12 01:00:30 +00:00
package nomad
import (
"fmt"
"math/rand"
"net"
"sync/atomic"
"time"
2019-01-15 19:46:12 +00:00
testing "github.com/mitchellh/go-testing-interface"
"github.com/pkg/errors"
2019-01-15 19:46:12 +00:00
2018-01-12 01:00:30 +00:00
"github.com/hashicorp/nomad/command/agent/consul"
"github.com/hashicorp/nomad/helper/freeport"
2019-01-23 14:27:14 +00:00
"github.com/hashicorp/nomad/helper/pluginutils/catalog"
"github.com/hashicorp/nomad/helper/pluginutils/singleton"
2018-01-12 01:00:30 +00:00
"github.com/hashicorp/nomad/helper/testlog"
csi: CLI for volume status, registration/deregistration and plugin status (#7193) * command/csi: csi, csi_plugin, csi_volume * helper/funcs: move ExtraKeys from parse_config to UnusedKeys * command/agent/config_parse: use helper.UnusedKeys * api/csi: annotate CSIVolumes with hcl fields * command/csi_plugin: add Synopsis * command/csi_volume_register: use hcl.Decode style parsing * command/csi_volume_list * command/csi_volume_status: list format, cleanup * command/csi_plugin_list * command/csi_plugin_status * command/csi_volume_deregister * command/csi_volume: add Synopsis * api/contexts/contexts: add csi search contexts to the constants * command/commands: register csi commands * api/csi: fix struct tag for linter * command/csi_plugin_list: unused struct vars * command/csi_plugin_status: unused struct vars * command/csi_volume_list: unused struct vars * api/csi: add allocs to CSIPlugin * command/csi_plugin_status: format the allocs * api/allocations: copy Allocation.Stub in from structs * nomad/client_rpc: add some error context with Errorf * api/csi: collapse read & write alloc maps to a stub list * command/csi_volume_status: cleanup allocation display * command/csi_volume_list: use Schedulable instead of Healthy * command/csi_volume_status: use Schedulable instead of Healthy * command/csi_volume_list: sprintf string * command/csi: delete csi.go, csi_plugin.go * command/plugin: refactor csi components to sub-command plugin status * command/plugin: remove csi * command/plugin_status: remove csi * command/volume: remove csi * command/volume_status: split out csi specific * helper/funcs: add RemoveEqualFold * command/agent/config_parse: use helper.RemoveEqualFold * api/csi: do ,unusedKeys right * command/volume: refactor csi components to `nomad volume` * command/volume_register: split out csi specific * command/commands: use the new top level commands * command/volume_deregister: hardwired type csi for now * command/volume_status: csiFormatVolumes rescued from volume_list * command/plugin_status: avoid a panic on no args * command/volume_status: avoid a panic on no args * command/plugin_status: predictVolumeType * command/volume_status: predictVolumeType * nomad/csi_endpoint_test: move CreateTestPlugin to testing * command/plugin_status_test: use CreateTestCSIPlugin * nomad/structs/structs: add CSIPlugins and CSIVolumes search consts * nomad/state/state_store: add CSIPlugins and CSIVolumesByIDPrefix * nomad/search_endpoint: add CSIPlugins and CSIVolumes * command/plugin_status: move the header to the csi specific * command/volume_status: move the header to the csi specific * nomad/state/state_store: CSIPluginByID prefix * command/status: rename the search context to just Plugins/Volumes * command/plugin,volume_status: test return ids now * command/status: rename the search context to just Plugins/Volumes * command/plugin_status: support -json and -t * command/volume_status: support -json and -t * command/plugin_status_csi: comments * command/*_status: clean up text * api/csi: fix stale comments * command/volume: make deregister sound less fearsome * command/plugin_status: set the id length * command/plugin_status_csi: more compact plugin health * command/volume: better error message, comment
2020-03-06 15:09:10 +00:00
"github.com/hashicorp/nomad/helper/uuid"
2018-01-12 01:00:30 +00:00
"github.com/hashicorp/nomad/nomad/mock"
csi: CLI for volume status, registration/deregistration and plugin status (#7193) * command/csi: csi, csi_plugin, csi_volume * helper/funcs: move ExtraKeys from parse_config to UnusedKeys * command/agent/config_parse: use helper.UnusedKeys * api/csi: annotate CSIVolumes with hcl fields * command/csi_plugin: add Synopsis * command/csi_volume_register: use hcl.Decode style parsing * command/csi_volume_list * command/csi_volume_status: list format, cleanup * command/csi_plugin_list * command/csi_plugin_status * command/csi_volume_deregister * command/csi_volume: add Synopsis * api/contexts/contexts: add csi search contexts to the constants * command/commands: register csi commands * api/csi: fix struct tag for linter * command/csi_plugin_list: unused struct vars * command/csi_plugin_status: unused struct vars * command/csi_volume_list: unused struct vars * api/csi: add allocs to CSIPlugin * command/csi_plugin_status: format the allocs * api/allocations: copy Allocation.Stub in from structs * nomad/client_rpc: add some error context with Errorf * api/csi: collapse read & write alloc maps to a stub list * command/csi_volume_status: cleanup allocation display * command/csi_volume_list: use Schedulable instead of Healthy * command/csi_volume_status: use Schedulable instead of Healthy * command/csi_volume_list: sprintf string * command/csi: delete csi.go, csi_plugin.go * command/plugin: refactor csi components to sub-command plugin status * command/plugin: remove csi * command/plugin_status: remove csi * command/volume: remove csi * command/volume_status: split out csi specific * helper/funcs: add RemoveEqualFold * command/agent/config_parse: use helper.RemoveEqualFold * api/csi: do ,unusedKeys right * command/volume: refactor csi components to `nomad volume` * command/volume_register: split out csi specific * command/commands: use the new top level commands * command/volume_deregister: hardwired type csi for now * command/volume_status: csiFormatVolumes rescued from volume_list * command/plugin_status: avoid a panic on no args * command/volume_status: avoid a panic on no args * command/plugin_status: predictVolumeType * command/volume_status: predictVolumeType * nomad/csi_endpoint_test: move CreateTestPlugin to testing * command/plugin_status_test: use CreateTestCSIPlugin * nomad/structs/structs: add CSIPlugins and CSIVolumes search consts * nomad/state/state_store: add CSIPlugins and CSIVolumesByIDPrefix * nomad/search_endpoint: add CSIPlugins and CSIVolumes * command/plugin_status: move the header to the csi specific * command/volume_status: move the header to the csi specific * nomad/state/state_store: CSIPluginByID prefix * command/status: rename the search context to just Plugins/Volumes * command/plugin,volume_status: test return ids now * command/status: rename the search context to just Plugins/Volumes * command/plugin_status: support -json and -t * command/volume_status: support -json and -t * command/plugin_status_csi: comments * command/*_status: clean up text * api/csi: fix stale comments * command/volume: make deregister sound less fearsome * command/plugin_status: set the id length * command/plugin_status_csi: more compact plugin health * command/volume: better error message, comment
2020-03-06 15:09:10 +00:00
"github.com/hashicorp/nomad/nomad/state"
2018-01-12 01:00:30 +00:00
"github.com/hashicorp/nomad/nomad/structs"
2019-09-04 01:42:41 +00:00
"github.com/hashicorp/nomad/version"
2018-01-12 01:00:30 +00:00
)
var (
nodeNumber uint32 = 0
)
func TestACLServer(t testing.T, cb func(*Config)) (*Server, *structs.ACLToken, func()) {
server, cleanup := TestServer(t, func(c *Config) {
2018-01-12 01:00:30 +00:00
c.ACLEnabled = true
if cb != nil {
cb(c)
}
})
token := mock.ACLManagementToken()
err := server.State().BootstrapACLTokens(1, 0, token)
if err != nil {
t.Fatalf("failed to bootstrap ACL token: %v", err)
}
return server, token, cleanup
2018-01-12 01:00:30 +00:00
}
func TestServer(t testing.T, cb func(*Config)) (*Server, func()) {
2018-01-12 01:00:30 +00:00
// Setup the default settings
config := DefaultConfig()
2018-09-15 23:23:13 +00:00
config.Logger = testlog.HCLogger(t)
2019-09-04 01:42:41 +00:00
config.Build = version.Version + "+unittest"
2018-01-12 01:00:30 +00:00
config.DevMode = true
Simplify Bootstrap logic in tests This change updates tests to honor `BootstrapExpect` exclusively when forming test clusters and removes test only knobs, e.g. `config.DevDisableBootstrap`. Background: Test cluster creation is fragile. Test servers don't follow the BootstapExpected route like production clusters. Instead they start as single node clusters and then get rejoin and may risk causing brain split or other test flakiness. The test framework expose few knobs to control those (e.g. `config.DevDisableBootstrap` and `config.Bootstrap`) that control whether a server should bootstrap the cluster. These flags are confusing and it's unclear when to use: their usage in multi-node cluster isn't properly documented. Furthermore, they have some bad side-effects as they don't control Raft library: If `config.DevDisableBootstrap` is true, the test server may not immediately attempt to bootstrap a cluster, but after an election timeout (~50ms), Raft may force a leadership election and win it (with only one vote) and cause a split brain. The knobs are also confusing as Bootstrap is an overloaded term. In BootstrapExpect, we refer to bootstrapping the cluster only after N servers are connected. But in tests and the knobs above, it refers to whether the server is a single node cluster and shouldn't wait for any other server. Changes: This commit makes two changes: First, it relies on `BootstrapExpected` instead of `Bootstrap` and/or `DevMode` flags. This change is relatively trivial. Introduce a `Bootstrapped` flag to track if the cluster is bootstrapped. This allows us to keep `BootstrapExpected` immutable. Previously, the flag was a config value but it gets set to 0 after cluster bootstrap completes.
2020-03-02 15:29:24 +00:00
config.BootstrapExpect = 1
2018-01-12 01:00:30 +00:00
nodeNum := atomic.AddUint32(&nodeNumber, 1)
config.NodeName = fmt.Sprintf("nomad-%03d", nodeNum)
// Tighten the Serf timing
config.SerfConfig.MemberlistConfig.BindAddr = "127.0.0.1"
config.SerfConfig.MemberlistConfig.SuspicionMult = 2
config.SerfConfig.MemberlistConfig.RetransmitMult = 2
config.SerfConfig.MemberlistConfig.ProbeTimeout = 50 * time.Millisecond
config.SerfConfig.MemberlistConfig.ProbeInterval = 100 * time.Millisecond
config.SerfConfig.MemberlistConfig.GossipInterval = 100 * time.Millisecond
// Tighten the Raft timing
config.RaftConfig.LeaderLeaseTimeout = 50 * time.Millisecond
config.RaftConfig.HeartbeatTimeout = 50 * time.Millisecond
config.RaftConfig.ElectionTimeout = 50 * time.Millisecond
config.RaftTimeout = 500 * time.Millisecond
// Disable Vault
f := false
config.VaultConfig.Enabled = &f
// Squelch output when -v isn't specified
config.LogOutput = testlog.NewWriter(t)
2018-02-15 23:48:32 +00:00
// Tighten the autopilot timing
config.AutopilotConfig.ServerStabilizationTime = 100 * time.Millisecond
config.ServerHealthInterval = 50 * time.Millisecond
config.AutopilotInterval = 100 * time.Millisecond
// Set the plugin loaders
config.PluginLoader = catalog.TestPluginLoader(t)
config.PluginSingletonLoader = singleton.NewSingletonLoader(config.Logger, config.PluginLoader)
// Disable consul autojoining: tests typically join servers directly
config.ConsulConfig.ServerAutoJoin = &f
2018-01-12 01:00:30 +00:00
// Invoke the callback if any
if cb != nil {
cb(config)
}
2018-09-15 23:23:13 +00:00
catalog := consul.NewMockCatalog(config.Logger)
2018-01-12 01:00:30 +00:00
acls := consul.NewMockACLsAPI(config.Logger)
2018-01-12 01:00:30 +00:00
for i := 10; i >= 0; i-- {
// Get random ports, need to cleanup later
ports := freeport.MustTake(2)
2018-01-12 01:00:30 +00:00
config.RPCAddr = &net.TCPAddr{
IP: []byte{127, 0, 0, 1},
Port: ports[0],
}
config.SerfConfig.MemberlistConfig.BindPort = ports[1]
// Create server
server, err := NewServer(config, catalog, acls)
2018-01-12 01:00:30 +00:00
if err == nil {
return server, func() {
ch := make(chan error)
go func() {
defer close(ch)
// Shutdown server
err := server.Shutdown()
if err != nil {
ch <- errors.Wrap(err, "failed to shutdown server")
}
freeport.Return(ports)
}()
select {
case e := <-ch:
if e != nil {
t.Fatal(e.Error())
}
case <-time.After(1 * time.Minute):
t.Fatal("timed out while shutting down server")
}
}
2018-01-12 01:00:30 +00:00
} else if i == 0 {
freeport.Return(ports)
2018-01-12 01:00:30 +00:00
t.Fatalf("err: %v", err)
} else {
if server != nil {
_ = server.Shutdown()
freeport.Return(ports)
2018-01-12 01:00:30 +00:00
}
wait := time.Duration(rand.Int31n(2000)) * time.Millisecond
time.Sleep(wait)
}
}
return nil, nil
2018-01-12 01:00:30 +00:00
}
func TestJoin(t testing.T, s1 *Server, other ...*Server) {
addr := fmt.Sprintf("127.0.0.1:%d",
s1.config.SerfConfig.MemberlistConfig.BindPort)
for _, s2 := range other {
if num, err := s2.Join([]string{addr}); err != nil {
t.Fatalf("err: %v", err)
} else if num != 1 {
t.Fatalf("bad: %d", num)
}
}
}
csi: CLI for volume status, registration/deregistration and plugin status (#7193) * command/csi: csi, csi_plugin, csi_volume * helper/funcs: move ExtraKeys from parse_config to UnusedKeys * command/agent/config_parse: use helper.UnusedKeys * api/csi: annotate CSIVolumes with hcl fields * command/csi_plugin: add Synopsis * command/csi_volume_register: use hcl.Decode style parsing * command/csi_volume_list * command/csi_volume_status: list format, cleanup * command/csi_plugin_list * command/csi_plugin_status * command/csi_volume_deregister * command/csi_volume: add Synopsis * api/contexts/contexts: add csi search contexts to the constants * command/commands: register csi commands * api/csi: fix struct tag for linter * command/csi_plugin_list: unused struct vars * command/csi_plugin_status: unused struct vars * command/csi_volume_list: unused struct vars * api/csi: add allocs to CSIPlugin * command/csi_plugin_status: format the allocs * api/allocations: copy Allocation.Stub in from structs * nomad/client_rpc: add some error context with Errorf * api/csi: collapse read & write alloc maps to a stub list * command/csi_volume_status: cleanup allocation display * command/csi_volume_list: use Schedulable instead of Healthy * command/csi_volume_status: use Schedulable instead of Healthy * command/csi_volume_list: sprintf string * command/csi: delete csi.go, csi_plugin.go * command/plugin: refactor csi components to sub-command plugin status * command/plugin: remove csi * command/plugin_status: remove csi * command/volume: remove csi * command/volume_status: split out csi specific * helper/funcs: add RemoveEqualFold * command/agent/config_parse: use helper.RemoveEqualFold * api/csi: do ,unusedKeys right * command/volume: refactor csi components to `nomad volume` * command/volume_register: split out csi specific * command/commands: use the new top level commands * command/volume_deregister: hardwired type csi for now * command/volume_status: csiFormatVolumes rescued from volume_list * command/plugin_status: avoid a panic on no args * command/volume_status: avoid a panic on no args * command/plugin_status: predictVolumeType * command/volume_status: predictVolumeType * nomad/csi_endpoint_test: move CreateTestPlugin to testing * command/plugin_status_test: use CreateTestCSIPlugin * nomad/structs/structs: add CSIPlugins and CSIVolumes search consts * nomad/state/state_store: add CSIPlugins and CSIVolumesByIDPrefix * nomad/search_endpoint: add CSIPlugins and CSIVolumes * command/plugin_status: move the header to the csi specific * command/volume_status: move the header to the csi specific * nomad/state/state_store: CSIPluginByID prefix * command/status: rename the search context to just Plugins/Volumes * command/plugin,volume_status: test return ids now * command/status: rename the search context to just Plugins/Volumes * command/plugin_status: support -json and -t * command/volume_status: support -json and -t * command/plugin_status_csi: comments * command/*_status: clean up text * api/csi: fix stale comments * command/volume: make deregister sound less fearsome * command/plugin_status: set the id length * command/plugin_status_csi: more compact plugin health * command/volume: better error message, comment
2020-03-06 15:09:10 +00:00
// CreateTestPlugin is a helper that generates the node + fingerprint results necessary to
// create a CSIPlugin by directly inserting into the state store. It's exported for use in
// other test packages
func CreateTestCSIPlugin(s *state.StateStore, id string) func() {
// Create some nodes
ns := make([]*structs.Node, 3)
for i := range ns {
n := mock.Node()
ns[i] = n
}
// Install healthy plugin fingerprinting results
ns[0].CSIControllerPlugins = map[string]*structs.CSIInfo{
id: {
PluginID: id,
AllocID: uuid.Generate(),
Healthy: true,
HealthDescription: "healthy",
RequiresControllerPlugin: true,
RequiresTopologies: false,
ControllerInfo: &structs.CSIControllerInfo{
SupportsReadOnlyAttach: true,
SupportsAttachDetach: true,
SupportsListVolumes: true,
SupportsListVolumesAttachedNodes: false,
},
},
}
// Install healthy plugin fingerprinting results
allocID := uuid.Generate()
for _, n := range ns[1:] {
n.CSINodePlugins = map[string]*structs.CSIInfo{
id: {
PluginID: id,
AllocID: allocID,
Healthy: true,
HealthDescription: "healthy",
RequiresControllerPlugin: true,
RequiresTopologies: false,
NodeInfo: &structs.CSINodeInfo{
ID: n.ID,
MaxVolumes: 64,
RequiresNodeStageVolume: true,
},
},
}
}
// Insert them into the state store
index := uint64(999)
for _, n := range ns {
index++
s.UpsertNode(index, n)
}
// Return cleanup function that deletes the nodes
return func() {
ids := make([]string, len(ns))
for i, n := range ns {
ids[i] = n.ID
}
index++
s.DeleteNode(index, ids)
}
}