app/vmbackupmanager: add metrics for better observability (#488)

* app/vmbackupmanager: add metrics for better observability, include more information to `/api/v1/backups` API call response

* app/vmbackupmanager: drop old metrics before creating new ones

* app/vmbackupmanager: use `_total` postfix for counter metrics

* app/vmbackupmanager: remove `_total` postfix for gauge-like metrics

* app/vmbackupmanager: add `_last_run_failed` metrics for backups and retention

* app/vmbackupmanager: address review feedback

* app/vmbackupmanager: fix metric name

* app/vmbackupmanager: address review feedback, remove background updates of metrics, add restoring state of `_last_run_failed` metric from remote storage

* app/vmbackupmanager: improve performance for backup size calculation

* app/vmbackupmanager: refactor backup and retention runs to deduplicate each run logic

* {app/vmbackupmanager,lib/formatutil}: move HumanizeBytes into lib package

* app/vmbackupmanager: fix creating new metrics instead of reusing existing ones

* lit/formatutil: add comment to make linter happy

* app/vmbackupmanager: address review feedback

app/vmalert/templates/template.go

@@ -27,11 +27,11 @@ import (
 	"strconv"
 	"strings"
 	"sync"
+	textTpl "text/template"
 	"time"
 
-	textTpl "text/template"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/formatutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
@@ -350,15 +350,7 @@ func templateFuncs() textTpl.FuncMap {
 			if math.Abs(v) <= 1 || math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v), nil
 			}
-			prefix := ""
+			return formatutil.HumanizeBytes(v), nil
-			for _, p := range []string{"ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi"} {
-				if math.Abs(v) < 1024 {
-					break
-				}
-				prefix = p
-				v /= 1024
-			}
-			return fmt.Sprintf("%.4g%s", v, prefix), nil
 		},
 
 		// humanizeDuration converts given seconds to a human-readable duration

app/vmalert/templates/template_test.go

@@ -1,6 +1,7 @@
 package templates
 
 import (
+	"math"
 	"strings"
 	"testing"
 	textTpl "text/template"
@@ -50,6 +51,31 @@ func TestTemplateFuncs(t *testing.T) {
 	if !ok {
 		t.Fatalf("unexpected mismatch")
 	}
+
+	formatting := func(funcName string, p interface{}, resultExpected string) {
+		t.Helper()
+		v := funcs[funcName]
+		fLocal := v.(func(s interface{}) (string, error))
+		result, err := fLocal(p)
+		if err != nil {
+			t.Fatalf("unexpected error for %s(%f): %s", funcName, p, err)
+		}
+		if result != resultExpected {
+			t.Fatalf("unexpected result for %s(%f); got\n%s\nwant\n%s", funcName, p, result, resultExpected)
+		}
+	}
+	formatting("humanize1024", float64(0), "0")
+	formatting("humanize1024", math.Inf(0), "+Inf")
+	formatting("humanize1024", math.NaN(), "NaN")
+	formatting("humanize1024", float64(127087), "124.1ki")
+	formatting("humanize1024", float64(130137088), "124.1Mi")
+	formatting("humanize1024", float64(133260378112), "124.1Gi")
+	formatting("humanize1024", float64(136458627186688), "124.1Ti")
+	formatting("humanize1024", float64(139733634239168512), "124.1Pi")
+	formatting("humanize1024", float64(143087241460908556288), "124.1Ei")
+	formatting("humanize1024", float64(146521335255970361638912), "124.1Zi")
+	formatting("humanize1024", float64(150037847302113650318245888), "124.1Yi")
+	formatting("humanize1024", float64(153638755637364377925883789312), "1.271e+05Yi")
 }
 
 func mkTemplate(current, replacement interface{}) textTemplate {

app/vmbackupmanager/README.md

@@ -158,7 +158,7 @@ The result on the GCS bucket. We see only 3 daily backups:
 * GET `/api/v1/backups` - returns list of backups in remote storage.
   Example output:
   ```json
-  ["daily/2022-10-06","daily/2022-10-10","hourly/2022-10-04:13","hourly/2022-10-06:12","hourly/2022-10-06:13","hourly/2022-10-10:14","hourly/2022-10-10:16","monthly/2022-10","weekly/2022-40","weekly/2022-41"]
+  [{"name":"daily/2022-11-30","size_bytes":26664689,"size":"25.429Mi"},{"name":"daily/2022-12-01","size_bytes":40160965,"size":"38.300Mi"},{"name":"hourly/2022-11-30:12","size_bytes":5846529,"size":"5.576Mi"},{"name":"hourly/2022-11-30:13","size_bytes":17651847,"size":"16.834Mi"},{"name":"hourly/2022-11-30:13:22","size_bytes":8797831,"size":"8.390Mi"},{"name":"hourly/2022-11-30:14","size_bytes":10680454,"size":"10.186Mi"}]
   ```
 
 * POST `/api/v1/restore` - saves backup name to restore when [performing restore](#restore-commands).
@@ -211,7 +211,7 @@ It can be changed by using flag:
 `vmbackupmanager backup list` lists backups in remote storage:
 ```console
 $ ./vmbackupmanager backup list
-["daily/2022-10-06","daily/2022-10-10","hourly/2022-10-04:13","hourly/2022-10-06:12","hourly/2022-10-06:13","hourly/2022-10-10:14","hourly/2022-10-10:16","monthly/2022-10","weekly/2022-40","weekly/2022-41"]
+[{"name":"daily/2022-11-30","size_bytes":26664689,"size":"25.429Mi"},{"name":"daily/2022-12-01","size_bytes":40160965,"size":"38.300Mi"},{"name":"hourly/2022-11-30:12","size_bytes":5846529,"size":"5.576Mi"},{"name":"hourly/2022-11-30:13","size_bytes":17651847,"size":"16.834Mi"},{"name":"hourly/2022-11-30:13:22","size_bytes":8797831,"size":"8.390Mi"},{"name":"hourly/2022-11-30:14","size_bytes":10680454,"size":"10.186Mi"}]
 ```
 
 ### Restore commands

docs/vmbackupmanager.md

@@ -162,7 +162,7 @@ The result on the GCS bucket. We see only 3 daily backups:
 * GET `/api/v1/backups` - returns list of backups in remote storage.
   Example output:
   ```json
-  ["daily/2022-10-06","daily/2022-10-10","hourly/2022-10-04:13","hourly/2022-10-06:12","hourly/2022-10-06:13","hourly/2022-10-10:14","hourly/2022-10-10:16","monthly/2022-10","weekly/2022-40","weekly/2022-41"]
+  [{"name":"daily/2022-11-30","size_bytes":26664689,"size":"25.429Mi"},{"name":"daily/2022-12-01","size_bytes":40160965,"size":"38.300Mi"},{"name":"hourly/2022-11-30:12","size_bytes":5846529,"size":"5.576Mi"},{"name":"hourly/2022-11-30:13","size_bytes":17651847,"size":"16.834Mi"},{"name":"hourly/2022-11-30:13:22","size_bytes":8797831,"size":"8.390Mi"},{"name":"hourly/2022-11-30:14","size_bytes":10680454,"size":"10.186Mi"}]
   ```
 
 * POST `/api/v1/restore` - saves backup name to restore when [performing restore](#restore-commands).
@@ -215,7 +215,7 @@ It can be changed by using flag:
 `vmbackupmanager backup list` lists backups in remote storage:
 ```console
 $ ./vmbackupmanager backup list
-["daily/2022-10-06","daily/2022-10-10","hourly/2022-10-04:13","hourly/2022-10-06:12","hourly/2022-10-06:13","hourly/2022-10-10:14","hourly/2022-10-10:16","monthly/2022-10","weekly/2022-40","weekly/2022-41"]
+[{"name":"daily/2022-11-30","size_bytes":26664689,"size":"25.429Mi"},{"name":"daily/2022-12-01","size_bytes":40160965,"size":"38.300Mi"},{"name":"hourly/2022-11-30:12","size_bytes":5846529,"size":"5.576Mi"},{"name":"hourly/2022-11-30:13","size_bytes":17651847,"size":"16.834Mi"},{"name":"hourly/2022-11-30:13:22","size_bytes":8797831,"size":"8.390Mi"},{"name":"hourly/2022-11-30:14","size_bytes":10680454,"size":"10.186Mi"}]
 ```
 
 ### Restore commands
@@ -274,7 +274,15 @@ If restore mark doesn't exist at `storageDataPath`(restore wasn't requested) `vm
 
 ### How to restore in Kubernetes
 
-1. Enter container running `vmbackupmanager`
+1. Ensure there is an init container with `vmbackupmanager restore` in `vmstorage` or `vmsingle` pod.
+   For [VictoriaMetrics operator](https://docs.victoriametrics.com/operator/VictoriaMetrics-Operator.html) deployments it is required to add:
+   ```yaml
+   vmbackup:
+     restore:
+       onStart: "true"
+   ```
+   See operator `VMStorage` schema [here](https://docs.victoriametrics.com/operator/api.html#vmstorage) and `VMSingle` [here](https://docs.victoriametrics.com/operator/api.html#vmsinglespec).
+2. Enter container running `vmbackupmanager`
 2. Use `vmbackupmanager backup list` to get list of available backups:
   ```console
   $ /vmbackupmanager-prod backup list
@@ -291,6 +299,33 @@ If restore mark doesn't exist at `storageDataPath`(restore wasn't requested) `vm
     ```
 4. Restart pod
 
+#### Restore cluster into another cluster
+
+These steps are assuming that [VictoriaMetrics operator](https://docs.victoriametrics.com/operator/VictoriaMetrics-Operator.html) is used to manage `VMCluster`.
+Clusters here are referred to as `source` and `destination`.
+
+1. Create a new cluster with access to *source* cluster `vmbackupmanager` storage and same number of storage nodes.
+   Add the following section in order to enable restore on start (operator `VMStorage` schema can be found [here](https://docs.victoriametrics.com/operator/api.html#vmstorage):
+   ```yaml
+   vmbackup:
+     restore:
+       onStart: "true"
+   ```
+   Note: it is safe to leave this section in the cluster configuration, since it will be ignored if restore mark doesn't exist.
+   > Important! Use different `-dst` for *destination* cluster to avoid overwriting backup data of the *source* cluster.
+2. Enter container running `vmbackupmanager` in *source* cluster
+2. Use `vmbackupmanager backup list` to get list of available backups:
+  ```console
+  $ /vmbackupmanager-prod backup list
+  ["daily/2022-10-06","daily/2022-10-10","hourly/2022-10-04:13","hourly/2022-10-06:12","hourly/2022-10-06:13","hourly/2022-10-10:14","hourly/2022-10-10:16","monthly/2022-10","weekly/2022-40","weekly/2022-41"]
+  ```
+3. Use `vmbackupmanager restore create` to create restore mark at each pod of the *destination* cluster.
+   Each pod in *destination* cluster should be restored from backup of respective pod in *source* cluster.
+   For example: `vmstorage-source-0` in *source* cluster should be restored from `vmstorage-destination-0` in *destination* cluster.
+  ```console
+  $ /vmbackupmanager-prod restore create s3://source_cluster/vmstorage-source-0/daily/2022-10-06
+  ```
+
 ## Configuration
 
 ### Flags

lib/backup/actions/backup.go

@@ -11,6 +11,12 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/fslocal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/fsnil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	bytesUploadedTotal       = uint64(0)
+	bytesUploadedTotalMetric = metrics.NewCounter(`vm_backups_uploaded_bytes_total`)
 )
 
 // Backup performs backup according to the provided settings.
@@ -163,6 +169,8 @@ func runBackup(src *fslocal.FS, dst common.RemoteFS, origin common.OriginFS, con
 			n := atomic.LoadUint64(&bytesUploaded)
 			logger.Infof("uploaded %d out of %d bytes from src %s to dst %s in %s", n, uploadSize, src, dst, elapsed)
 		})
+		atomic.AddUint64(&bytesUploadedTotal, bytesUploaded)
+		bytesUploadedTotalMetric.Set(bytesUploadedTotal)
 		if err != nil {
 			return err
 		}

lib/formatutil/human.go

@@ -0,0 +1,19 @@
+package formatutil
+
+import (
+	"fmt"
+	"math"
+)
+
+// HumanizeBytes returns human-readable representation of size in bytes with 1024 base.
+func HumanizeBytes(size float64) string {
+	prefix := ""
+	for _, p := range []string{"ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi"} {
+		if math.Abs(size) < 1024 {
+			break
+		}
+		prefix = p
+		size /= 1024
+	}
+	return fmt.Sprintf("%.4g%s", size, prefix)
+}