Online repair new workers, except blocks and scrub

src/garage/admin.rs

@@ -24,7 +24,7 @@ use garage_model::migrate::Migrate;
 use garage_model::permission::*;
 
 use crate::cli::*;
-use crate::repair::online::OnlineRepair;
+use crate::repair::online::launch_online_repair;
 
 pub const ADMIN_RPC_PATH: &str = "garage/admin_rpc.rs/Rpc";
 
@@ -693,15 +693,7 @@ impl AdminRpcHandler {
 				)))
 			}
 		} else {
-			let repair = OnlineRepair {
+			launch_online_repair(self.garage.clone(), opt)?;
-				garage: self.garage.clone(),
-			};
-			self.garage
-				.system
-				.background
-				.spawn_worker("Repair worker".into(), move |must_exit| async move {
-					repair.repair_worker(opt, must_exit).await
-				});
 			Ok(AdminRpc::Ok(format!(
 				"Repair launched on {:?}",
 				self.garage.system.id

src/garage/repair/online.rs

@@ -1,5 +1,6 @@
 use std::sync::Arc;
 
+use async_trait::async_trait;
 use tokio::sync::watch;
 
 use garage_model::garage::Garage;
@@ -7,83 +8,103 @@ use garage_model::s3::block_ref_table::*;
 use garage_model::s3::object_table::*;
 use garage_model::s3::version_table::*;
 use garage_table::*;
+use garage_util::background::*;
 use garage_util::error::Error;
 
 use crate::*;
 
-pub struct OnlineRepair {
+pub fn launch_online_repair(garage: Arc<Garage>, opt: RepairOpt) -> Result<(), Error> {
-	pub garage: Arc<Garage>,
+	match opt.what {
+		RepairWhat::Tables => {
+			info!("Launching a full sync of tables");
+			garage.bucket_table.syncer.add_full_sync();
+			garage.object_table.syncer.add_full_sync();
+			garage.version_table.syncer.add_full_sync();
+			garage.block_ref_table.syncer.add_full_sync();
+			garage.key_table.syncer.add_full_sync();
+		}
+		RepairWhat::Versions => {
+			info!("Repairing the versions table");
+			garage
+				.background
+				.spawn_worker(RepairVersionsWorker::new(garage.clone()));
+		}
+		RepairWhat::BlockRefs => {
+			info!("Repairing the block refs table");
+			garage
+				.background
+				.spawn_worker(RepairBlockrefsWorker::new(garage.clone()));
+		}
+		RepairWhat::Blocks => {
+			unimplemented!()
+			/*
+			info!("Repairing the stored blocks");
+			self.garage
+				.block_manager
+				.repair_data_store(&must_exit)
+				.await?;
+				*/
+		}
+		RepairWhat::Scrub { tranquility } => {
+			unimplemented!()
+			/*
+			info!("Verifying integrity of stored blocks");
+			self.garage
+				.block_manager
+				.scrub_data_store(&must_exit, tranquility)
+				.await?;
+				*/
+		}
+	}
+	Ok(())
 }
 
-impl OnlineRepair {
+// ----
-	pub async fn repair_worker(&self, opt: RepairOpt, must_exit: watch::Receiver<bool>) {
+
-		if let Err(e) = self.repair_worker_aux(opt, must_exit).await {
+struct RepairVersionsWorker {
-			warn!("Repair worker failed with error: {}", e);
+	garage: Arc<Garage>,
+	pos: Vec<u8>,
+	iter: usize,
+}
+
+impl RepairVersionsWorker {
+	fn new(garage: Arc<Garage>) -> Self {
+		Self {
+			garage,
+			pos: vec![],
+			iter: 0,
 		}
 	}
+}
 
-	async fn repair_worker_aux(
+#[async_trait]
-		&self,
+impl Worker for RepairVersionsWorker {
-		opt: RepairOpt,
+	fn name(&self) -> String {
-		must_exit: watch::Receiver<bool>,
+		"Version repair worker".into()
-	) -> Result<(), Error> {
-		match opt.what {
-			RepairWhat::Tables => {
-				info!("Launching a full sync of tables");
-				self.garage.bucket_table.syncer.add_full_sync();
-				self.garage.object_table.syncer.add_full_sync();
-				self.garage.version_table.syncer.add_full_sync();
-				self.garage.block_ref_table.syncer.add_full_sync();
-				self.garage.key_table.syncer.add_full_sync();
-			}
-			RepairWhat::Versions => {
-				info!("Repairing the versions table");
-				self.repair_versions(&must_exit).await?;
-			}
-			RepairWhat::BlockRefs => {
-				info!("Repairing the block refs table");
-				self.repair_block_ref(&must_exit).await?;
-			}
-			RepairWhat::Blocks => {
-				info!("Repairing the stored blocks");
-				self.garage
-					.block_manager
-					.repair_data_store(&must_exit)
-					.await?;
-			}
-			RepairWhat::Scrub { tranquility } => {
-				info!("Verifying integrity of stored blocks");
-				self.garage
-					.block_manager
-					.scrub_data_store(&must_exit, tranquility)
-					.await?;
-			}
-		}
-		Ok(())
 	}
 
-	async fn repair_versions(&self, must_exit: &watch::Receiver<bool>) -> Result<(), Error> {
+	async fn work(
-		let mut pos = vec![];
+		&mut self,
-		let mut i = 0;
+		_must_exit: &mut watch::Receiver<bool>,
-
+	) -> Result<WorkerStatus, Error> {
-		while !*must_exit.borrow() {
+		let item_bytes = match self.garage.version_table.data.store.get_gt(&self.pos)? {
-			let item_bytes = match self.garage.version_table.data.store.get_gt(pos)? {
+			Some((k, v)) => {
-				Some((k, v)) => {
+				self.pos = k;
-					pos = k;
+				v
-					v
-				}
-				None => break,
-			};
-
-			i += 1;
-			if i % 1000 == 0 {
-				info!("repair_versions: {}", i);
 			}
-
+			None => {
-			let version = rmp_serde::decode::from_read_ref::<_, Version>(&item_bytes)?;
+				info!("repair_versions: finished, done {}", self.iter);
-			if version.deleted.get() {
+				return Ok(WorkerStatus::Done);
-				continue;
 			}
+		};
+
+		self.iter += 1;
+		if self.iter % 1000 == 0 {
+			info!("repair_versions: {}", self.iter);
+		}
+
+		let version = rmp_serde::decode::from_read_ref::<_, Version>(&item_bytes)?;
+		if !version.deleted.get() {
 			let object = self
 				.garage
 				.object_table
@@ -109,32 +130,61 @@ impl OnlineRepair {
 					.await?;
 			}
 		}
-		info!("repair_versions: finished, done {}", i);
+
-		Ok(())
+		Ok(WorkerStatus::Busy)
 	}
 
-	async fn repair_block_ref(&self, must_exit: &watch::Receiver<bool>) -> Result<(), Error> {
+	async fn wait_for_work(&mut self, _must_exit: &watch::Receiver<bool>) -> WorkerStatus {
-		let mut pos = vec![];
+		unreachable!()
-		let mut i = 0;
+	}
+}
 
-		while !*must_exit.borrow() {
+// ----
-			let item_bytes = match self.garage.block_ref_table.data.store.get_gt(pos)? {
-				Some((k, v)) => {
-					pos = k;
-					v
-				}
-				None => break,
-			};
 
-			i += 1;
+struct RepairBlockrefsWorker {
-			if i % 1000 == 0 {
+	garage: Arc<Garage>,
-				info!("repair_block_ref: {}", i);
+	pos: Vec<u8>,
+	iter: usize,
+}
+
+impl RepairBlockrefsWorker {
+	fn new(garage: Arc<Garage>) -> Self {
+		Self {
+			garage,
+			pos: vec![],
+			iter: 0,
+		}
+	}
+}
+
+#[async_trait]
+impl Worker for RepairBlockrefsWorker {
+	fn name(&self) -> String {
+		"Block refs repair worker".into()
+	}
+
+	async fn work(
+		&mut self,
+		_must_exit: &mut watch::Receiver<bool>,
+	) -> Result<WorkerStatus, Error> {
+		let item_bytes = match self.garage.block_ref_table.data.store.get_gt(&self.pos)? {
+			Some((k, v)) => {
+				self.pos = k;
+				v
 			}
-
+			None => {
-			let block_ref = rmp_serde::decode::from_read_ref::<_, BlockRef>(&item_bytes)?;
+				info!("repair_block_ref: finished, done {}", self.iter);
-			if block_ref.deleted.get() {
+				return Ok(WorkerStatus::Done);
-				continue;
 			}
+		};
+
+		self.iter += 1;
+		if self.iter % 1000 == 0 {
+			info!("repair_block_ref: {}", self.iter);
+		}
+
+		let block_ref = rmp_serde::decode::from_read_ref::<_, BlockRef>(&item_bytes)?;
+		if !block_ref.deleted.get() {
 			let version = self
 				.garage
 				.version_table
@@ -157,7 +207,11 @@ impl OnlineRepair {
 					.await?;
 			}
 		}
-		info!("repair_block_ref: finished, done {}", i);
+
-		Ok(())
+		Ok(WorkerStatus::Busy)
+	}
+
+	async fn wait_for_work(&mut self, _must_exit: &watch::Receiver<bool>) -> WorkerStatus {
+		unreachable!()
 	}
 }