rpk: add rpk debug remote bundle

Fixes DEVEX-44

This commit introduces the rpk debug remote bundle
command, which allows the user to request a debug
bundle using the Admin API.

MODULE.bazel

@@ -185,6 +185,7 @@ use_repo(
     "com_github_docker_go_connections",
     "com_github_docker_go_units",
     "com_github_fatih_color",
+    "com_github_google_uuid",
     "com_github_hamba_avro",
     "com_github_hamba_avro_v2",
     "com_github_hashicorp_go_multierror",

src/go/rpk/go.mod

@@ -23,6 +23,7 @@ require (
 	github.com/docker/go-connections v0.5.0
 	github.com/docker/go-units v0.5.0
 	github.com/fatih/color v1.18.0
+	github.com/google/uuid v1.6.0
 	github.com/hamba/avro/v2 v2.27.0
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51
@@ -94,7 +95,6 @@ require (
 	github.com/google/gnostic-models v0.6.9-0.20230804172637-c7be7c783f49 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/google/gofuzz v1.2.0 // indirect
-	github.com/google/uuid v1.6.0 // indirect
 	github.com/grpc-ecosystem/grpc-gateway/v2 v2.19.1 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect

src/go/rpk/pkg/cli/debug/BUILD

@@ -10,6 +10,7 @@ go_library(
     visibility = ["//visibility:public"],
     deps = [
         "//src/go/rpk/pkg/cli/debug/bundle",
+        "//src/go/rpk/pkg/cli/debug/remotebundle",
         "//src/go/rpk/pkg/config",
         "@com_github_spf13_afero//:afero",
         "@com_github_spf13_cobra//:cobra",

src/go/rpk/pkg/cli/debug/bundle/bundle.go

@@ -155,7 +155,7 @@ func NewCommand(fs afero.Fs, p *config.Params) *cobra.Command {
 
 	f := cmd.Flags()
 	f.StringVarP(&outFile, outputFlag, "o", "", "The file path where the debug file will be written (default ./<timestamp>-bundle.zip)")
-	f.DurationVar(&timeout, "timeout", 31*time.Second, "How long to wait for child commands to execute (e.g. 30s, 1.5m)")
+	f.DurationVar(&timeout, "timeout", 31*time.Second, "How long to wait for child commands to execute. For example: 30s, 1.5m")
 	f.StringVar(&uploadURL, "upload-url", "", "If provided, where to upload the bundle in addition to creating a copy on disk")
 	// Debug bundle options.
 	opts.InstallFlags(f)

src/go/rpk/pkg/cli/debug/common/BUILD

@@ -1,4 +1,4 @@
-load("@rules_go//go:def.bzl", "go_library")
+load("@rules_go//go:def.bzl", "go_library", "go_test")
 
 go_library(
     name = "common",
@@ -7,3 +7,10 @@ go_library(
     visibility = ["//visibility:public"],
     deps = ["@com_github_spf13_pflag//:pflag"],
 )
+
+go_test(
+    name = "common_test",
+    srcs = ["common_test.go"],
+    embed = [":common"],
+    deps = ["@com_github_stretchr_testify//require"],
+)

src/go/rpk/pkg/cli/debug/common/common.go

@@ -25,16 +25,16 @@ type DebugBundleSharedOptions struct {
 // InstallFlags installs the debug bundle flags that fills the debug bundle
 // options.
 func (o *DebugBundleSharedOptions) InstallFlags(f *pflag.FlagSet) {
-	f.StringVar(&o.ControllerLogsSizeLimit, "controller-logs-size-limit", "132MB", "The size limit of the controller logs that can be stored in the bundle (e.g. 3MB, 1GiB)")
-	f.DurationVar(&o.CPUProfilerWait, "cpu-profiler-wait", 30*time.Second, "For how long to collect samples for the CPU profiler (e.g. 30s, 1.5m). Must be higher than 15s")
-	f.StringVar(&o.LogsSizeLimit, "logs-size-limit", "100MiB", "Read the logs until the given size is reached (e.g. 3MB, 1GiB)")
-	f.StringVar(&o.LogsSince, "logs-since", "yesterday", "Include logs dated from specified date onward; (journalctl date format: YYYY-MM-DD, 'yesterday', or 'today'). Refer to journalctl documentation for more options")
-	f.StringVar(&o.LogsUntil, "logs-until", "", "Include logs older than the specified date; (journalctl date format: YYYY-MM-DD, 'yesterday', or 'today'). Refer to journalctl documentation for more options")
-	f.DurationVar(&o.MetricsInterval, "metrics-interval", 10*time.Second, "Interval between metrics snapshots (e.g. 30s, 1.5m)")
+	f.StringVar(&o.ControllerLogsSizeLimit, "controller-logs-size-limit", "132MB", "The size limit of the controller logs that can be stored in the bundle. For example: 3MB, 1GiB")
+	f.DurationVar(&o.CPUProfilerWait, "cpu-profiler-wait", 30*time.Second, "How long to collect samples for the CPU profiler. For example: 30s, 1.5m. Must be higher than 15s")
+	f.StringVar(&o.LogsSizeLimit, "logs-size-limit", "100MiB", "Read the logs until the given size is reached. For example: 3MB, 1GiB")
+	f.StringVar(&o.LogsSince, "logs-since", "yesterday", "Include logs dated from specified date onward; (journalctl date format: YYYY-MM-DD, 'yesterday', or 'today'). See the journalctl documentation for more options")
+	f.StringVar(&o.LogsUntil, "logs-until", "", "Include logs older than the specified date; (journalctl date format: YYYY-MM-DD, 'yesterday', or 'today'). See the journalctl documentation for more options")
+	f.DurationVar(&o.MetricsInterval, "metrics-interval", 10*time.Second, "Interval between metrics snapshots. For example: 30s, 1.5m")
 	f.IntVar(&o.MetricsSampleCount, "metrics-samples", 2, "Number of metrics samples to take (at the interval of --metrics-interval). Must be >= 2")
-	f.StringArrayVarP(&o.PartitionFlag, "partition", "p", nil, "Comma-separated partition IDs; when provided, rpk saves extra admin API requests for those partitions. Check help for extended usage")
-	f.StringVarP(&o.Namespace, "namespace", "n", "redpanda", "The namespace to use to collect the resources from (k8s only)")
-	f.StringArrayVarP(&o.LabelSelector, "label-selector", "l", []string{"app.kubernetes.io/name=redpanda"}, "Comma-separated label selectors to filter your resources. e.g: <label>=<value>,<label>=<value> (k8s only)")
+	f.StringArrayVarP(&o.PartitionFlag, "partition", "p", nil, "Comma-separated partition IDs. When provided, rpk saves extra Admin API requests for those partitions. See the help for extended usage")
+	f.StringVarP(&o.Namespace, "namespace", "n", "redpanda", "The namespace to use to collect the resources from (K8s only)")
+	f.StringArrayVarP(&o.LabelSelector, "label-selector", "l", []string{"app.kubernetes.io/name=redpanda"}, "Comma-separated label selectors to filter your resources. For example: <label>=<value>,<label>=<value> (K8s only)")
 }
 
 // SanitizeName replace any of the following characters with "-": "<", ">", ":",

src/go/rpk/pkg/cli/debug/common/common_test.go

@@ -0,0 +1,58 @@
+package common
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestSanitizeName(t *testing.T) {
+	tests := []struct {
+		name  string
+		input string
+		exp   string
+	}{
+		{
+			name:  "No forbidden characters",
+			input: "validName",
+			exp:   "validName",
+		},
+		{
+			name:  "Single forbidden character",
+			input: "invalid:8083",
+			exp:   "invalid-8083",
+		},
+		{
+			name:  "Multiple forbidden characters",
+			input: "name/with|forbidden?chars",
+			exp:   "name-with-forbidden-chars",
+		},
+		{
+			name:  "Only forbidden characters",
+			input: `<>:\"/\\|?*`,
+			exp:   "-----------",
+		},
+		{
+			name:  "Empty string",
+			input: "",
+			exp:   "",
+		},
+		{
+			name:  "No change with already sanitized name",
+			input: "cleanName123",
+			exp:   "cleanName123",
+		},
+		{
+			name:  "Name with numbers and special characters",
+			input: "name123|test*<>",
+			exp:   "name123-test---",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			actual := SanitizeName(tt.input)
+			require.Equal(t, tt.exp, actual)
+		})
+	}
+}

src/go/rpk/pkg/cli/debug/debug.go

@@ -11,6 +11,7 @@ package debug
 
 import (
 	"github.com/redpanda-data/redpanda/src/go/rpk/pkg/cli/debug/bundle"
+	"github.com/redpanda-data/redpanda/src/go/rpk/pkg/cli/debug/remotebundle"
 	"github.com/redpanda-data/redpanda/src/go/rpk/pkg/config"
 	"github.com/spf13/afero"
 	"github.com/spf13/cobra"
@@ -25,6 +26,7 @@ func NewCommand(fs afero.Fs, p *config.Params) *cobra.Command {
 	cmd.AddCommand(
 		bundle.NewCommand(fs, p),
 		NewInfoCommand(),
+		remotebundle.NewCommand(fs, p),
 	)
 
 	return cmd

src/go/rpk/pkg/cli/debug/remotebundle/BUILD

@@ -0,0 +1,27 @@
+load("@rules_go//go:def.bzl", "go_library")
+
+go_library(
+    name = "remotebundle",
+    srcs = [
+        "cancel.go",
+        "download.go",
+        "remote.go",
+        "start.go",
+        "status.go",
+    ],
+    importpath = "github.com/redpanda-data/redpanda/src/go/rpk/pkg/cli/debug/remotebundle",
+    visibility = ["//visibility:public"],
+    deps = [
+        "//src/go/rpk/pkg/adminapi",
+        "//src/go/rpk/pkg/cli/debug/common",
+        "//src/go/rpk/pkg/config",
+        "//src/go/rpk/pkg/out",
+        "@com_github_docker_go_units//:go-units",
+        "@com_github_google_uuid//:uuid",
+        "@com_github_redpanda_data_common_go_rpadmin//:rpadmin",
+        "@com_github_spf13_afero//:afero",
+        "@com_github_spf13_cobra//:cobra",
+        "@io_k8s_apimachinery//pkg/labels",
+        "@org_golang_x_sync//errgroup",
+    ],
+)

src/go/rpk/pkg/cli/debug/remotebundle/cancel.go

@@ -0,0 +1,121 @@
+// Copyright 2024 Redpanda Data, Inc.
+//
+// Use of this software is governed by the Business Source License
+// included in the file licenses/BSL.md
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0
+
+package remotebundle
+
+import (
+	"fmt"
+	"os"
+	"sync"
+
+	"github.com/redpanda-data/redpanda/src/go/rpk/pkg/config"
+	"github.com/redpanda-data/redpanda/src/go/rpk/pkg/out"
+	"github.com/spf13/afero"
+	"github.com/spf13/cobra"
+)
+
+type cancelResponse struct {
+	Broker   string
+	Canceled bool
+	Error    string
+}
+
+func newCancelCommand(fs afero.Fs, p *config.Params) *cobra.Command {
+	var noConfirm bool
+	var jobID string
+	cmd := &cobra.Command{
+		Use:   "cancel",
+		Short: "Cancel a remote bundle execution",
+		Long: `Cancel a remote bundle execution.
+
+This command cancels the debug collection process in a remote cluster that
+you configured in flags, environment variables, or your rpk profile.
+
+Use the flag '--job-id' to only cancel the debug bundle with
+the given job ID.
+
+Use the flag '--no-confirm' to avoid the confirmation prompt.
+`,
+		Args: cobra.NoArgs,
+		Run: func(cmd *cobra.Command, _ []string) {
+			p, err := p.LoadVirtualProfile(fs)
+			out.MaybeDie(err, "rpk unable to load config: %v", err)
+			config.CheckExitCloudAdmin(p)
+
+			status, anyErr, _, cache := executeBundleStatus(cmd.Context(), fs, p)
+			if jobID != "" {
+				status = filterStatusByJobID(status, jobID)
+			}
+			if !noConfirm {
+				printTextBundleStatus(status, anyErr)
+				confirmed, err := out.Confirm("Confirm debug bundle cancel from these brokers?")
+				out.MaybeDie(err, "unable to confirm cancel: %v;  if you want to select a single broker, use -X admin.hosts=<brokers,to,cancel>", err)
+				if !confirmed {
+					out.Exit("operation canceled; if you want to select a single broker, use -X admin.hosts=<brokers,to,cancel>")
+				}
+			}
+			var (
+				wg           sync.WaitGroup
+				rwMu         sync.RWMutex // read from cache.
+				mu           sync.Mutex   // write to status.
+				response     []cancelResponse
+				anyCancelErr bool
+			)
+			updateStatus := func(resp cancelResponse, err error) {
+				mu.Lock()
+				defer mu.Unlock()
+				anyCancelErr = anyCancelErr || err != nil
+				response = append(response, resp)
+			}
+			for _, s := range status {
+				wg.Add(1)
+				go func(addr, jobID string) {
+					defer wg.Done()
+					rwMu.RLock()
+					cl := cache[addr]
+					rwMu.RUnlock()
+					resp := cancelResponse{Broker: addr}
+					err := cl.CancelDebugBundleProcess(cmd.Context(), jobID)
+					if err != nil {
+						resp.Error = fmt.Sprintf("unable to cancel debug bundle: %s", tryMessageFromErr(err))
+						updateStatus(resp, err)
+						return
+					}
+					resp.Canceled = true
+					updateStatus(resp, nil)
+				}(s.Broker, s.JobID)
+			}
+			wg.Wait()
+			headers := []string{"broker", "canceled"}
+			if anyCancelErr {
+				headers = append(headers, "error")
+				defer os.Exit(1)
+			}
+
+			tw := out.NewTable(headers...)
+			defer tw.Flush()
+			for _, row := range response {
+				tw.PrintStructFields(row)
+			}
+		},
+	}
+	cmd.Flags().StringVar(&jobID, "job-id", "", "ID of the job to cancel the debug bundle")
+	cmd.Flags().BoolVar(&noConfirm, "no-confirm", false, "Disable confirmation prompt")
+	return cmd
+}
+
+func filterStatusByJobID(status []statusResponse, jobID string) []statusResponse {
+	var filtered []statusResponse
+	for _, s := range status {
+		if s.JobID == jobID {
+			filtered = append(filtered, s)
+		}
+	}
+	return filtered
+}