consul/command/agent/agent.go
Ashvitha 091925bcb7
HCP Telemetry Feature (#17460)
* Move hcp client to subpackage hcpclient (#16800)

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* [HCP Observability] OTELExporter (#17128)

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* [HCP Observability] OTELSink (#17159)

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Initialize OTELSink with sync.Map for all the instrument stores.

* Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests.

* Switch to mutex instead of sync.Map to avoid type assertion

* Add gauge store

* Clarify comments

* return concrete sink type

* Fix lint errors

* Move gauge store to be within sink

* Use context.TODO,rebase and clenaup opts handling

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Fix imports

* Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx

* Add lots of documentation to the OTELSink

* Fix gauge store comment and check ok

* Add select and ctx.Done() check to gauge callback

* use require.Equal for attributes

* Fixed import naming

* Remove float64 calls and add a NewGaugeStore method

* Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store

* Generate 100 gauge operations

* Seperate the labels into goroutines in sink test

* Generate kv store for the test case keys to avoid using uuid

* Added a race test with 300 samples for OTELSink

* Do not pass in waitgroup and use error channel instead.

* Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel

* Fix nits

* [HCP Observability] Init OTELSink in Telemetry (#17162)

* Move hcp client to subpackage hcpclient (#16800)

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Initialize OTELSink with sync.Map for all the instrument stores.

* Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests.

* Switch to mutex instead of sync.Map to avoid type assertion

* Add gauge store

* Clarify comments

* return concrete sink type

* Fix lint errors

* Move gauge store to be within sink

* Use context.TODO,rebase and clenaup opts handling

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Fix imports

* Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx

* Add lots of documentation to the OTELSink

* Fix gauge store comment and check ok

* Add select and ctx.Done() check to gauge callback

* use require.Equal for attributes

* Fixed import naming

* Remove float64 calls and add a NewGaugeStore method

* Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store

* Generate 100 gauge operations

* Seperate the labels into goroutines in sink test

* Generate kv store for the test case keys to avoid using uuid

* Added a race test with 300 samples for OTELSink

* [HCP Observability] OTELExporter (#17128)

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Do not pass in waitgroup and use error channel instead.

* Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Initialize OTELSink with sync.Map for all the instrument stores.

* Added telemetry agent to client and init sink in deps

* Fixed client

* Initalize sink in deps

* init sink in telemetry library

* Init deps before telemetry

* Use concrete telemetry.OtelSink type

* add /v1/metrics

* Avoid returning err for telemetry init

* move sink init within the IsCloudEnabled()

* Use HCPSinkOpts in deps instead

* update golden test for configuration file

* Switch to using extra sinks in the telemetry library

* keep name MetricsConfig

* fix log in verifyCCMRegistration

* Set logger in context

* pass around MetricSink in deps

* Fix imports

* Rebased onto otel sink pr

* Fix URL in test

* [HCP Observability] OTELSink (#17159)

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Initialize OTELSink with sync.Map for all the instrument stores.

* Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests.

* Switch to mutex instead of sync.Map to avoid type assertion

* Add gauge store

* Clarify comments

* return concrete sink type

* Fix lint errors

* Move gauge store to be within sink

* Use context.TODO,rebase and clenaup opts handling

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Fix imports

* Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx

* Add lots of documentation to the OTELSink

* Fix gauge store comment and check ok

* Add select and ctx.Done() check to gauge callback

* use require.Equal for attributes

* Fixed import naming

* Remove float64 calls and add a NewGaugeStore method

* Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store

* Generate 100 gauge operations

* Seperate the labels into goroutines in sink test

* Generate kv store for the test case keys to avoid using uuid

* Added a race test with 300 samples for OTELSink

* Do not pass in waitgroup and use error channel instead.

* Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel

* Fix nits

* pass extraSinks as function param instead

* Add default interval as package export

* remove verifyCCM func

* Add clusterID

* Fix import and add t.Parallel() for missing tests

* Kick Vercel CI

* Remove scheme from endpoint path, and fix error logging

* return metrics.MetricSink for sink method

* Update SDK

* [HCP Observability] Metrics filtering and Labels in Go Metrics sink (#17184)

* Move hcp client to subpackage hcpclient (#16800)

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* [HCP Observability] New MetricsClient (#17100)

* Client configured with TLS using HCP config and retry/throttle

* Add tests and godoc for metrics client

* close body after request

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* remove clone

* Extract CloudConfig and mock for future PR

* Switch to hclog.FromContext

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Initialize OTELSink with sync.Map for all the instrument stores.

* Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests.

* Switch to mutex instead of sync.Map to avoid type assertion

* Add gauge store

* Clarify comments

* return concrete sink type

* Fix lint errors

* Move gauge store to be within sink

* Use context.TODO,rebase and clenaup opts handling

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Fix imports

* Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx

* Add lots of documentation to the OTELSink

* Fix gauge store comment and check ok

* Add select and ctx.Done() check to gauge callback

* use require.Equal for attributes

* Fixed import naming

* Remove float64 calls and add a NewGaugeStore method

* Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store

* Generate 100 gauge operations

* Seperate the labels into goroutines in sink test

* Generate kv store for the test case keys to avoid using uuid

* Added a race test with 300 samples for OTELSink

* [HCP Observability] OTELExporter (#17128)

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Do not pass in waitgroup and use error channel instead.

* Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Initialize OTELSink with sync.Map for all the instrument stores.

* Added telemetry agent to client and init sink in deps

* Fixed client

* Initalize sink in deps

* init sink in telemetry library

* Init deps before telemetry

* Use concrete telemetry.OtelSink type

* add /v1/metrics

* Avoid returning err for telemetry init

* move sink init within the IsCloudEnabled()

* Use HCPSinkOpts in deps instead

* update golden test for configuration file

* Switch to using extra sinks in the telemetry library

* keep name MetricsConfig

* fix log in verifyCCMRegistration

* Set logger in context

* pass around MetricSink in deps

* Fix imports

* Rebased onto otel sink pr

* Fix URL in test

* [HCP Observability] OTELSink (#17159)

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Create new OTELExporter which uses the MetricsClient
Add transform because the conversion is in an /internal package

* Fix lint error

* early return when there are no metrics

* Add NewOTELExporter() function

* Downgrade to metrics SDK version: v1.15.0-rc.1

* Fix imports

* fix small nits with comments and url.URL

* Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile

* Cleanup error handling and clarify empty metrics case

* Fix input/expected naming in otel_transform_test.go

* add comment for metric tracking

* Add a general isEmpty method

* Add clear error types

* update to latest version 1.15.0 of OTEL

* Client configured with TLS using HCP config and retry/throttle

* run go mod tidy

* Remove one abstraction to use the config from deps

* Address PR feedback

* Initialize OTELSink with sync.Map for all the instrument stores.

* Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests.

* Switch to mutex instead of sync.Map to avoid type assertion

* Add gauge store

* Clarify comments

* return concrete sink type

* Fix lint errors

* Move gauge store to be within sink

* Use context.TODO,rebase and clenaup opts handling

* Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1

* Fix imports

* Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx

* Add lots of documentation to the OTELSink

* Fix gauge store comment and check ok

* Add select and ctx.Done() check to gauge callback

* use require.Equal for attributes

* Fixed import naming

* Remove float64 calls and add a NewGaugeStore method

* Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store

* Generate 100 gauge operations

* Seperate the labels into goroutines in sink test

* Generate kv store for the test case keys to avoid using uuid

* Added a race test with 300 samples for OTELSink

* Do not pass in waitgroup and use error channel instead.

* Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel

* Fix nits

* pass extraSinks as function param instead

* Add default interval as package export

* remove verifyCCM func

* Add clusterID

* Fix import and add t.Parallel() for missing tests

* Kick Vercel CI

* Remove scheme from endpoint path, and fix error logging

* return metrics.MetricSink for sink method

* Update SDK

* Added telemetry agent to client and init sink in deps

* Add node_id and __replica__ default labels

* add function for default labels and set x-hcp-resource-id

* Fix labels tests

* Commit suggestion for getDefaultLabels

Co-authored-by: Joshua Timmons <joshua.timmons1@gmail.com>

* Fixed server.id, and t.Parallel()

* Make defaultLabels a method on the TelemetryConfig object

* Rename FilterList to lowercase filterList

* Cleanup filter implemetation by combining regex into a single one, and making the type lowercase

* Fix append

* use regex directly for filters

* Fix x-resource-id test to use mocked value

* Fix log.Error formats

* Forgot the len(opts.Label) optimization)

* Use cfg.NodeID instead

---------

Co-authored-by: Joshua Timmons <joshua.timmons1@gmail.com>

* remove replic tag (#17484)

* [HCP Observability] Add custom metrics for OTEL sink, improve logging, upgrade modules and cleanup metrics client (#17455)

* Add custom metrics for Exporter and transform operations

* Improve deps logging

Run go mod tidy

* Upgrade SDK and OTEL

* Remove the partial success implemetation and check for HTTP status code in metrics client

* Add x-channel

* cleanup logs in deps.go based on PR feedback

* Change to debug log and lowercase

* address test operation feedback

* use GetHumanVersion on version

* Fix error wrapping

* Fix metric names

* [HCP Observability] Turn off retries for now until dynamically configurable (#17496)

* Remove retries for now until dynamic configuration is possible

* Clarify comment

* Update changelog

* improve changelog

---------

Co-authored-by: Joshua Timmons <joshua.timmons1@gmail.com>
2023-05-29 16:11:08 -04:00

377 lines
11 KiB
Go

// Copyright (c) HashiCorp, Inc.
// SPDX-License-Identifier: MPL-2.0
package agent
import (
"context"
"flag"
"fmt"
"io"
"os"
"os/signal"
"path/filepath"
"strings"
"syscall"
"time"
"github.com/hashicorp/go-checkpoint"
"github.com/hashicorp/go-hclog"
mcli "github.com/mitchellh/cli"
"github.com/hashicorp/consul/agent"
"github.com/hashicorp/consul/agent/config"
hcpbootstrap "github.com/hashicorp/consul/agent/hcp/bootstrap"
hcpclient "github.com/hashicorp/consul/agent/hcp/client"
"github.com/hashicorp/consul/command/cli"
"github.com/hashicorp/consul/command/flags"
"github.com/hashicorp/consul/lib"
"github.com/hashicorp/consul/logging"
"github.com/hashicorp/consul/service_os"
consulversion "github.com/hashicorp/consul/version"
)
func New(ui cli.Ui) *cmd {
buildDate, err := time.Parse(time.RFC3339, consulversion.BuildDate)
if err != nil {
ui.Error(fmt.Sprintf("Fatal error with internal time set; check makefile for build date %v %v \n", buildDate, err))
return nil
}
c := &cmd{
ui: ui,
revision: consulversion.GitCommit,
version: consulversion.Version,
versionPrerelease: consulversion.VersionPrerelease,
versionHuman: consulversion.GetHumanVersion(),
buildDate: buildDate,
flags: flag.NewFlagSet("", flag.ContinueOnError),
}
config.AddFlags(c.flags, &c.configLoadOpts)
c.help = flags.Usage(help, c.flags)
return c
}
// AgentCommand is a Command implementation that runs a Consul agent.
// The command will not end unless a shutdown message is sent on the
// ShutdownCh. If two messages are sent on the ShutdownCh it will forcibly
// exit.
type cmd struct {
ui cli.Ui
flags *flag.FlagSet
http *flags.HTTPFlags
help string
revision string
version string
versionPrerelease string
versionHuman string
buildDate time.Time
configLoadOpts config.LoadOpts
logger hclog.InterceptLogger
}
func (c *cmd) Run(args []string) int {
code := c.run(args)
if c.logger != nil {
c.logger.Info("Exit code", "code", code)
}
return code
}
// checkpointResults is used to handler periodic results from our update checker
func (c *cmd) checkpointResults(results *checkpoint.CheckResponse, err error) {
if err != nil {
c.logger.Error("Failed to check for updates", "error", err)
return
}
if results.Outdated {
c.logger.Info("Newer Consul version available", "new_version", results.CurrentVersion, "current_version", c.version)
}
for _, alert := range results.Alerts {
switch alert.Level {
case "info":
c.logger.Info("Bulletin", "alert_level", alert.Level, "alert_message", alert.Message, "alert_URL", alert.URL)
default:
c.logger.Error("Bulletin", "alert_level", alert.Level, "alert_message", alert.Message, "alert_URL", alert.URL)
}
}
}
func (c *cmd) startupUpdateCheck(config *config.RuntimeConfig) {
version := config.Version
if config.VersionPrerelease != "" {
version += fmt.Sprintf("-%s", config.VersionPrerelease)
}
updateParams := &checkpoint.CheckParams{
Product: "consul",
Version: version,
}
if !config.DisableAnonymousSignature {
updateParams.SignatureFile = filepath.Join(config.DataDir, "checkpoint-signature")
}
// Schedule a periodic check with expected interval of 24 hours
checkpoint.CheckInterval(updateParams, 24*time.Hour, c.checkpointResults)
// Do an immediate check within the next 30 seconds
go func() {
time.Sleep(lib.RandomStagger(30 * time.Second))
c.checkpointResults(checkpoint.Check(updateParams))
}()
}
func (c *cmd) run(args []string) int {
ui := &mcli.PrefixedUi{
OutputPrefix: "==> ",
InfoPrefix: " ", // Note that startupLogger also uses this prefix
ErrorPrefix: "==> ",
Ui: c.ui,
}
if err := c.flags.Parse(args); err != nil {
if !strings.Contains(err.Error(), "help requested") {
ui.Error(fmt.Sprintf("error parsing flags: %v", err))
}
return 1
}
if len(c.flags.Args()) > 0 {
ui.Error(fmt.Sprintf("Unexpected extra arguments: %v", c.flags.Args()))
return 1
}
// FIXME: logs should always go to stderr, but previously they were sent to
// stdout, so continue to use Stdout for now, and fix this in a future release.
logGate := &logging.GatedWriter{Writer: c.ui.Stdout()}
loader := func(source config.Source) (config.LoadResult, error) {
c.configLoadOpts.DefaultConfig = source
return config.Load(c.configLoadOpts)
}
// wait for signal
signalCh := make(chan os.Signal, 10)
signal.Notify(signalCh, os.Interrupt, syscall.SIGTERM, syscall.SIGHUP, syscall.SIGPIPE)
ctx, cancel := context.WithCancel(context.Background())
// startup logger is a shim since we need to be about to log both before and
// after logging is setup properly but before agent has started fully. This
// takes care of that!
suLogger := newStartupLogger()
go handleStartupSignals(ctx, cancel, signalCh, suLogger)
// See if we need to bootstrap config from HCP before we go any further with
// agent startup. First do a preliminary load of agent configuration using the given loader.
// This is just to peek whether bootstrapping from HCP is enabled. The result is discarded
// on the call to agent.NewBaseDeps so that the wrapped loader takes effect.
res, err := loader(nil)
if err != nil {
ui.Error(err.Error())
return 1
}
if res.RuntimeConfig.IsCloudEnabled() {
client, err := hcpclient.NewClient(res.RuntimeConfig.Cloud)
if err != nil {
ui.Error("error building HCP HTTP client: " + err.Error())
return 1
}
// We override loader with the one returned as it was modified to include HCP-provided config.
loader, err = hcpbootstrap.LoadConfig(ctx, client, res.RuntimeConfig.DataDir, loader, ui)
if err != nil {
ui.Error(err.Error())
return 1
}
}
bd, err := agent.NewBaseDeps(loader, logGate, nil)
if err != nil {
ui.Error(err.Error())
return 1
}
c.logger = bd.Logger
agent, err := agent.New(bd)
if err != nil {
ui.Error(err.Error())
return 1
}
// Upgrade our startupLogger to use the real logger now we have it
suLogger.SetLogger(c.logger)
config := bd.RuntimeConfig
if config.Logging.LogJSON {
// Hide all non-error output when JSON logging is enabled.
ui.Ui = &cli.BasicUI{
BasicUi: mcli.BasicUi{ErrorWriter: c.ui.Stderr(), Writer: io.Discard},
}
}
ui.Output("Starting Consul agent...")
segment := config.SegmentName
if config.ServerMode {
segment = "<all>"
}
ui.Info(fmt.Sprintf(" Version: '%s'", c.versionHuman))
if strings.Contains(c.versionHuman, "dev") {
ui.Info(fmt.Sprintf(" Revision: '%s'", c.revision))
}
ui.Info(fmt.Sprintf(" Build Date: '%s'", c.buildDate))
ui.Info(fmt.Sprintf(" Node ID: '%s'", config.NodeID))
ui.Info(fmt.Sprintf(" Node name: '%s'", config.NodeName))
if ap := config.PartitionOrEmpty(); ap != "" {
ui.Info(fmt.Sprintf(" Partition: '%s'", ap))
}
ui.Info(fmt.Sprintf(" Datacenter: '%s' (Segment: '%s')", config.Datacenter, segment))
ui.Info(fmt.Sprintf(" Server: %v (Bootstrap: %v)", config.ServerMode, config.Bootstrap))
ui.Info(fmt.Sprintf(" Client Addr: %v (HTTP: %d, HTTPS: %d, gRPC: %d, gRPC-TLS: %d, DNS: %d)", config.ClientAddrs,
config.HTTPPort, config.HTTPSPort, config.GRPCPort, config.GRPCTLSPort, config.DNSPort))
ui.Info(fmt.Sprintf(" Cluster Addr: %v (LAN: %d, WAN: %d)", config.AdvertiseAddrLAN,
config.SerfPortLAN, config.SerfPortWAN))
ui.Info(fmt.Sprintf(" Gossip Encryption: %t", config.EncryptKey != ""))
ui.Info(fmt.Sprintf(" Auto-Encrypt-TLS: %t", config.AutoEncryptTLS || config.AutoEncryptAllowTLS))
ui.Info(fmt.Sprintf(" ACL Enabled: %t", config.ACLsEnabled))
ui.Info(fmt.Sprintf("ACL Default Policy: %s", config.ACLResolverSettings.ACLDefaultPolicy))
ui.Info(fmt.Sprintf(" HTTPS TLS: Verify Incoming: %t, Verify Outgoing: %t, Min Version: %s",
config.TLS.HTTPS.VerifyIncoming, config.TLS.HTTPS.VerifyOutgoing, config.TLS.HTTPS.TLSMinVersion))
ui.Info(fmt.Sprintf(" gRPC TLS: Verify Incoming: %t, Min Version: %s", config.TLS.GRPC.VerifyIncoming, config.TLS.GRPC.TLSMinVersion))
ui.Info(fmt.Sprintf(" Internal RPC TLS: Verify Incoming: %t, Verify Outgoing: %t (Verify Hostname: %t), Min Version: %s",
config.TLS.InternalRPC.VerifyIncoming, config.TLS.InternalRPC.VerifyOutgoing, config.TLS.InternalRPC.VerifyServerHostname, config.TLS.InternalRPC.TLSMinVersion))
// Enable log streaming
ui.Output("")
ui.Output("Log data will now stream in as it occurs:\n")
logGate.Flush()
err = agent.Start(ctx)
signal.Stop(signalCh)
cancel()
if err != nil {
c.logger.Error("Error starting agent", "error", err)
return 1
}
// shutdown agent before endpoints
defer agent.ShutdownEndpoints()
defer agent.ShutdownAgent()
if !config.DisableUpdateCheck && !config.DevMode {
c.startupUpdateCheck(config)
}
// Let the agent know we've finished registration
agent.StartSync()
c.logger.Info("Consul agent running!")
// wait for signal
signalCh = make(chan os.Signal, 10)
signal.Notify(signalCh, os.Interrupt, syscall.SIGTERM, syscall.SIGHUP, syscall.SIGPIPE)
for {
var sig os.Signal
select {
case s := <-signalCh:
sig = s
case <-service_os.Shutdown_Channel():
sig = os.Interrupt
case err := <-agent.RetryJoinCh():
c.logger.Error("Retry join failed", "error", err)
return 1
case <-agent.Failed():
// The deferred Shutdown method will log the appropriate error
return 1
case <-agent.ShutdownCh():
// agent is already down!
return 0
}
switch sig {
case syscall.SIGPIPE:
continue
case syscall.SIGHUP:
c.logger.Info("Caught", "signal", sig)
err := agent.ReloadConfig()
if err != nil {
c.logger.Error("Reload config failed", "error", err)
}
config = agent.GetConfig()
default:
c.logger.Info("Caught", "signal", sig)
graceful := (sig == os.Interrupt && !(config.SkipLeaveOnInt)) || (sig == syscall.SIGTERM && (config.LeaveOnTerm))
if !graceful {
c.logger.Info("Graceful shutdown disabled. Exiting")
return 1
}
c.logger.Info("Gracefully shutting down agent...")
gracefulCh := make(chan struct{})
go func() {
if err := agent.Leave(); err != nil {
c.logger.Error("Error on leave", "error", err)
return
}
close(gracefulCh)
}()
gracefulTimeout := 15 * time.Second
select {
case <-signalCh:
c.logger.Info("Caught second signal, Exiting", "signal", sig)
return 1
case <-time.After(gracefulTimeout):
c.logger.Info("Timeout on graceful leave. Exiting")
return 1
case <-gracefulCh:
c.logger.Info("Graceful exit completed")
return 0
}
}
}
}
func handleStartupSignals(ctx context.Context, cancel func(), signalCh chan os.Signal, logger *startupLogger) {
for {
var sig os.Signal
select {
case s := <-signalCh:
sig = s
case <-ctx.Done():
return
}
switch sig {
case syscall.SIGPIPE:
continue
case syscall.SIGHUP:
err := fmt.Errorf("cannot reload before agent started")
logger.Error("Caught", "signal", sig, "error", err)
default:
logger.Info("Caught", "signal", sig)
cancel()
return
}
}
}
func (c *cmd) Synopsis() string {
return synopsis
}
func (c *cmd) Help() string {
return c.help
}
const synopsis = "Runs a Consul agent"
const help = `
Usage: consul agent [options]
Starts the Consul agent and runs until an interrupt is received. The
agent represents a single node in a cluster.
`