Backup tag

README.md

@@ -30,7 +30,7 @@ Download the latest release from the [Releases page](https://github.com/maorfr/c
 
 ### From source
 
-```
+```shell
 mkdir -p $GOPATH/src/github.com/maorfr && cd $_
 git clone https://github.com/maorfr/cain.git && cd cain
 make
@@ -41,14 +41,15 @@ make
 ### Backup Cassandra cluster to cloud storage
 
 Cain performs a backup in the following way:
+
 1. Backup the `keyspace` schema (using `cqlsh`).
-1. Get backup data using `nodetool snapshot` - it creates a snapshot of the `keyspace` in all Cassandra pods in the given `namespace` (according to `selector`).
-2. Copy the files in `parallel` to cloud storage using [Skbn](https://github.com/maorfr/skbn) - it copies the files to the specified `dst`, under `namespace/<cassandrClusterName>/keyspace/<keyspaceSchemaHash>/tag/`.
-3. Clear all snapshots.
+2. Get backup data using `nodetool snapshot` - it creates a snapshot of the `keyspace` in all Cassandra pods in the given `namespace` (according to `selector`).
+3. Copy the files in `parallel` to cloud storage using [Skbn](https://github.com/maorfr/skbn) - it copies the files to the specified `dst`, under `namespace/<cassandrClusterName>/keyspace/<keyspaceSchemaHash>/tag/`.
+4. Clear all snapshots.
 
 #### Usage
 
-```
+```shell
 $ cain backup --help
 backup cassandra cluster to cloud storage
 
@@ -60,27 +61,43 @@ Flags:
       --cassandra-data-dir string   cassandra data directory. Overrides $CAIN_CASSANDRA_DATA_DIR (default "/var/lib/cassandra/data")
   -c, --container string            container name to act on. Overrides $CAIN_CONTAINER (default "cassandra")
       --dst string                  destination to backup to. Example: s3://bucket/cassandra. Overrides $CAIN_DST
+  -h, --help                        help for backup
   -k, --keyspace string             keyspace to act on. Overrides $CAIN_KEYSPACE
   -n, --namespace string            namespace to find cassandra cluster. Overrides $CAIN_NAMESPACE (default "default")
   -p, --parallel int                number of files to copy in parallel. set this flag to 0 for full parallelism. Overrides $CAIN_PARALLEL (default 1)
+  -w, --password string             password for the cassandra connection. Overrides $CAIN_PASSWORD (default "cassandra")
   -l, --selector string             selector to filter on. Overrides $CAIN_SELECTOR (default "app=cassandra")
+  -t, --tag string                  tag to backup, if empty then will use current timestamp. Use with caution - if tag exists then its contents will be overwritten. Overrides $CAIN_TAG
+  -u, --username string             username for the cassandra connection. Overrides $CAIN_USERNAME (default "cassandra")
+
 ```
 
 #### Examples
 
 Backup to AWS S3
 
-```
+```shell
 cain backup \
     -n default \
     -l release=cassandra \
     -k keyspace \
     --dst s3://db-backup/cassandra
 ```
 
-Backup to Azure Blob Storage
+Backup to AWS S3 using specific tag named `before-upgrade`
 
+```shell
+cain backup \
+    -n default \
+    -l release=cassandra \
+    -k keyspace \
+    --dst s3://db-backup/cassandra \
+    -t before-upgrade
 ```
+
+Backup to Azure Blob Storage
+
+```shell
 cain backup \
     -n default \
     -l release=cassandra \
@@ -90,7 +107,7 @@ cain backup \
 
 Backup to Google Cloud Storage
 
-```
+```shell
 cain backup \
     -n default \
     -l release=cassandra \
@@ -101,14 +118,15 @@ cain backup \
 ### Restore Cassandra backup from cloud storage
 
 Cain performs a restore in the following way:
+
 1. Restore schema if `schema` is specified.
 2. Truncate all tables in `keyspace`.
 3. Copy files from the specified `src` (under `keyspace/<keyspaceSchemaHash>/tag/`) - restore is only possible for the same keyspace schema.
 4. Load new data using `nodetool refresh`.
 
 #### Usage
 
-```
+```shell
 $ cain restore --help
 restore cassandra cluster from cloud storage
 
@@ -124,16 +142,17 @@ Flags:
   -p, --parallel int                number of files to copy in parallel. set this flag to 0 for full parallelism. Overrides $CAIN_PARALLEL (default 1)
   -s, --schema string               schema version to restore (optional). Overrides $CAIN_SCHEMA
   -l, --selector string             selector to filter on. Overrides $CAIN_SELECTOR (default "app=cassandra")
-      --src string                  source to restore from. Example: s3://bucket/cassandra/namespace/cluster-name. Overrides $CAIN_SRC
+      --src string                  source to restore from. Example: s3://bucket/cassandra/namespace/cluster-name. Notice that the src should not end with the forward slash. Overrides $CAIN_SRC
   -t, --tag string                  tag to restore. Overrides $CAIN_TAG
-      --user-group string           user and group who should own restored files. Overrides $CAIN_USER_GROUP (default "cassandra:cassandra")
+      --user-group string           user and group who should own restored files. Overrides $CAIN_USER_GROUP (default "cassandra:cassandra").
+        If you use rootless containers then ensure to set exactly the same user and group (by name or number) as in target container.
 ```
 
 #### Examples
 
 Restore from S3
 
-```
+```shell
 cain restore \
     --src s3://db-backup/cassandra/default/ring01
     -n default \
@@ -142,9 +161,20 @@ cain restore \
     -t 20180903091624
 ```
 
-Restore from Azure Blob Storage
+Restore from S3 from specific tag used before
 
+```shell
+cain restore \
+    --src s3://db-backup/cassandra/default/ring01
+    -n default \
+    -k keyspace \
+    -l release=cassandra \
+    -t before-upgrade
 ```
+
+Restore from Azure Blob Storage
+
+```shell
 cain restore \
     --src s3://my-account/db-backup-container/cassandra/default/ring01
     -n default \
@@ -155,7 +185,7 @@ cain restore \
 
 Restore from Google Cloud Storage
 
-```
+```shell
 cain restore \
     --src gcs://db-backup/cassandra/default/ring01
     -n default \
@@ -170,7 +200,7 @@ Cain describes the `keyspace` schema using `cqlsh`. It can return the schema its
 
 #### Usage
 
-```
+```shell
 $ cain schema --help
 get schema of cassandra cluster
 
@@ -187,13 +217,14 @@ Flags:
 
 #### Examples
 
-```
+```shell
 cain schema \
     -n default \
     -l release=cassandra \
     -k keyspace
 ```
-```
+
+```shell
 cain schema \
     -n default \
     -l release=cassandra \
@@ -206,17 +237,17 @@ cain schema \
 Cain commands support the usage of environment variables instead of flags. For example:
 The `backup` command can be executed as mentioned in the example:
 
-```
+```shell
 cain backup \
     -n default \
     -l release=cassandra \
     -k keyspace \
     --dst s3://db-backup/cassandra
 ```
 
-You can also set the appropriate envrionment variables (CAIN_FLAG, _ instead of -):
+You can also set the appropriate environment variables (`CAIN_FLAG`, `_` instead of `-`):
 
-```
+```shell
 export CAIN_NAMESPACE=default
 export CAIN_SELECTOR=release=cassandra
 export CAIN_KEYSPACE=keyspace
@@ -245,15 +276,14 @@ Since Cain uses [Skbn](https://github.com/maorfr/skbn), adding support for addit
 
 ## Credentials
 
-
 ### Kubernetes
 
 Cain tries to get credentials in the following order:
+
 1. if `KUBECONFIG` environment variable is set - cain will use the current context from that config file
 2. if `~/.kube/config` exists - cain will use the current context from that config file with an [out-of-cluster client configuration](https://github.com/kubernetes/client-go/tree/master/examples/out-of-cluster-client-configuration)
 3. if `~/.kube/config` does not exist - cain will assume it is working from inside a pod and will use an [in-cluster client configuration](https://github.com/kubernetes/client-go/tree/master/examples/in-cluster-client-configuration)
 
-
 ### AWS
 
 Cain uses the default AWS [credentials chain](https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html).
@@ -264,8 +294,8 @@ Cain uses `AZURE_STORAGE_ACCOUNT` and `AZURE_STORAGE_ACCESS_KEY` environment var
 
 ### Google Cloud Storage
 
-Cain uses Google [Application Default Credentials](https://cloud.google.com/docs/authentication/production). 
-Basically, it will first look for the `GOOGLE_APPLICATION_CREDENTIALS` environment variable. If it is not defined, it will look for the default service account, or throw an error if none is configured. 
+Cain uses Google [Application Default Credentials](https://cloud.google.com/docs/authentication/production).
+Basically, it will first look for the `GOOGLE_APPLICATION_CREDENTIALS` environment variable. If it is not defined, it will look for the default service account, or throw an error if none is configured.
 
 ## Examples
 

cmd/cain.go

@@ -49,6 +49,7 @@ type backupCmd struct {
 	cassandraDataDir string
 	username         string
 	password         string
+	tag              string
 
 	out io.Writer
 }
@@ -85,6 +86,7 @@ func NewBackupCmd(out io.Writer) *cobra.Command {
 				CassandraDataDir: b.cassandraDataDir,
 				Username:         b.username,
 				Password:         b.password,
+				Tag:              b.tag,
 			}
 			if _, err := cain.Backup(options); err != nil {
 				log.Fatal(err)
@@ -103,6 +105,7 @@ func NewBackupCmd(out io.Writer) *cobra.Command {
 	f.StringVar(&b.cassandraDataDir, "cassandra-data-dir", utils.GetStringEnvVar("CAIN_CASSANDRA_DATA_DIR", "/var/lib/cassandra/data"), "cassandra data directory. Overrides $CAIN_CASSANDRA_DATA_DIR")
 	f.StringVarP(&b.username, "username", "u", utils.GetStringEnvVar("CAIN_USERNAME", "cassandra"), "username for the cassandra connection. Overrides $CAIN_USERNAME")
 	f.StringVarP(&b.password, "password", "w", utils.GetStringEnvVar("CAIN_PASSWORD", "cassandra"), "password for the cassandra connection. Overrides $CAIN_PASSWORD")
+	f.StringVarP(&b.tag, "tag", "t", utils.GetStringEnvVar("CAIN_TAG", ""), "tag to backup, if empty then will use current timestamp. Use with cauthon - if tag exists then its contents will be overwritten. Overrides $CAIN_TAG")
 
 	return cmd
 }

pkg/cain/cain.go

@@ -21,6 +21,7 @@ type BackupOptions struct {
 	CassandraDataDir string
 	Username         string
 	Password         string
+	Tag              string
 }
 
 // Backup performs backup
@@ -56,7 +57,7 @@ func Backup(o BackupOptions) (string, error) {
 	}
 
 	log.Println("Taking snapshots")
-	tag := TakeSnapshots(k8sClient, pods, o.Namespace, o.Container, o.Keyspace, o.Username, o.Password)
+	tag := TakeSnapshots(k8sClient, pods, o.Namespace, o.Container, o.Keyspace, o.Username, o.Password, o.Tag)
 
 	log.Println("Calculating paths. This may take a while...")
 	fromToPathsAllPods, err := utils.GetFromAndToPathsFromK8s(k8sClient, pods, o.Namespace, o.Container, o.Keyspace, tag, dstBasePath, o.CassandraDataDir)

pkg/cain/nodetool.go

@@ -11,24 +11,31 @@ import (
 )
 
 // TakeSnapshots takes a snapshot using nodetool in all pods in parallel
-func TakeSnapshots(iClient interface{}, pods []string, namespace, container, keyspace string, username string, password string) string {
+func TakeSnapshots(iClient interface{}, pods []string, namespace, container, keyspace string, username string, password string, tag string) string {
 	k8sClient := iClient.(*skbn.K8sClient)
-	tag := utils.GetTimeStamp()
+
+	// get current time as tag
+	realtag := utils.GetTimeStamp()
+	// set custom tag if provided
+	if len(tag) != 0 {
+		realtag = tag
+	}
+
 	bwgSize := len(pods)
 	bwg := utils.NewBoundedWaitGroup(bwgSize)
 	for _, pod := range pods {
 		bwg.Add(1)
 
 		go func(k8sClient *skbn.K8sClient, namespace, pod, container, keyspace, username, password, tag string) {
-			if err := takeSnapshot(k8sClient, namespace, pod, container, keyspace, username, password, tag); err != nil {
+			if err := takeSnapshot(k8sClient, namespace, pod, container, keyspace, username, password, realtag); err != nil {
 				log.Fatal(err)
 			}
 			bwg.Done()
-		}(k8sClient, namespace, pod, container, keyspace, username, password, tag)
+		}(k8sClient, namespace, pod, container, keyspace, username, password, realtag)
 	}
 	bwg.Wait()
 
-	return tag
+	return realtag
 }
 
 // ClearSnapshots clears a snapshot using nodetool in all pods in parallel