Only one scrub worker (wip)

3 files changed, 38 insertions, 11 deletions

diff --git a/src/garage/admin.rs b/src/garage/admin.rs
index de49331e..71ee608c 100644
--- a/src/garage/admin.rs
+++ b/src/garage/admin.rs
@@ -698,7 +698,7 @@ impl AdminRpcHandler {
 				)))
 			}
 		} else {
-			launch_online_repair(self.garage.clone(), opt);
+			launch_online_repair(self.garage.clone(), opt).await;
 			Ok(AdminRpc::Ok(format!(
 				"Repair launched on {:?}",
 				self.garage.system.id
diff --git a/src/garage/cli/structs.rs b/src/garage/cli/structs.rs
index c1ee32ab..bc44b5ef 100644
--- a/src/garage/cli/structs.rs
+++ b/src/garage/cli/structs.rs
@@ -427,8 +427,29 @@ pub enum RepairWhat {
 	/// Verify integrity of all blocks on disc (extremely slow, i/o intensive)
 	#[structopt(name = "scrub")]
 	Scrub {
-		/// Tranquility factor (see tranquilizer documentation)
-		#[structopt(name = "tranquility", default_value = "2")]
+		#[structopt(subcommand)]
+		cmd: ScrubCmd,
+	},
+}
+
+#[derive(Serialize, Deserialize, StructOpt, Debug, Eq, PartialEq, Clone)]
+pub enum ScrubCmd {
+	/// Start scrub
+	#[structopt(name = "start")]
+	Start,
+	/// Pause scrub (it will resume automatically after 24 hours)
+	#[structopt(name = "pause")]
+	Pause,
+	/// Resume paused scrub
+	#[structopt(name = "resume")]
+	Resume,
+	/// Cancel scrub in progress
+	#[structopt(name = "cancel")]
+	Cancel,
+	/// Set tranquility level for in-progress and future scrubs
+	#[structopt(name = "set-tranquility")]
+	SetTranquility {
+		#[structopt()]
 		tranquility: u32,
 	},
 }
diff --git a/src/garage/repair/online.rs b/src/garage/repair/online.rs
index b0437c5e..8207a8b4 100644
--- a/src/garage/repair/online.rs
+++ b/src/garage/repair/online.rs
@@ -1,8 +1,10 @@
 use std::sync::Arc;
+use std::time::Duration;
 
 use async_trait::async_trait;
 use tokio::sync::watch;
 
+use garage_block::repair::ScrubWorkerCommand;
 use garage_model::garage::Garage;
 use garage_model::s3::block_ref_table::*;
 use garage_model::s3::object_table::*;
@@ -13,7 +15,7 @@ use garage_util::error::Error;
 
 use crate::*;
 
-pub fn launch_online_repair(garage: Arc<Garage>, opt: RepairOpt) {
+pub async fn launch_online_repair(garage: Arc<Garage>, opt: RepairOpt) {
 	match opt.what {
 		RepairWhat::Tables => {
 			info!("Launching a full sync of tables");
@@ -43,14 +45,18 @@ pub fn launch_online_repair(garage: Arc<Garage>, opt: RepairOpt) {
 					garage.block_manager.clone(),
 				));
 		}
-		RepairWhat::Scrub { tranquility } => {
+		RepairWhat::Scrub { cmd } => {
 			info!("Verifying integrity of stored blocks");
-			garage
-				.background
-				.spawn_worker(garage_block::repair::ScrubWorker::new(
-					garage.block_manager.clone(),
-					tranquility,
-				));
+			let cmd = match cmd {
+				ScrubCmd::Start => ScrubWorkerCommand::Start,
+				ScrubCmd::Pause => ScrubWorkerCommand::Pause(Duration::from_secs(3600 * 24)),
+				ScrubCmd::Resume => ScrubWorkerCommand::Resume,
+				ScrubCmd::Cancel => ScrubWorkerCommand::Cancel,
+				ScrubCmd::SetTranquility { tranquility } => {
+					ScrubWorkerCommand::SetTranquility(tranquility)
+				}
+			};
+			garage.block_manager.send_scrub_command(cmd).await;
 		}
 	}
 }