From 4f38cadf6e2963a652ed28327d1c2ccfa2ebb2b7 Mon Sep 17 00:00:00 2001
From: Alex <alex@adnab.me>
Date: Fri, 8 Jul 2022 13:30:26 +0200
Subject: Background task manager (#332)

- [x] New background worker trait
- [x] Adapt all current workers to use new API
- [x] Command to list currently running workers, and whether they are active, idle, or dead
- [x] Error reporting
- Optimizations
  - [x] Merkle updater: several items per iteration
  - [ ] Use `tokio::task::spawn_blocking` where appropriate so that CPU-intensive tasks don't block other things going on
- scrub:
  - [x] have only one worker with a channel to start/pause/cancel
  - [x] automatic scrub
  - [x] ability to view and change tranquility from CLI
  - [x] persistence of a few info
- [ ] Testing

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/332
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
---
 src/garage/admin.rs | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

(limited to 'src/garage/admin.rs')

diff --git a/src/garage/admin.rs b/src/garage/admin.rs
index 48914655..71ee608c 100644
--- a/src/garage/admin.rs
+++ b/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";
 
@@ -36,6 +36,7 @@ pub enum AdminRpc {
 	LaunchRepair(RepairOpt),
 	Migrate(MigrateOpt),
 	Stats(StatsOpt),
+	Worker(WorkerOpt),
 
 	// Replies
 	Ok(String),
@@ -47,6 +48,10 @@ pub enum AdminRpc {
 	},
 	KeyList(Vec<(String, String)>),
 	KeyInfo(Key, HashMap<Uuid, Bucket>),
+	WorkerList(
+		HashMap<usize, garage_util::background::WorkerInfo>,
+		WorkerListOpt,
+	),
 }
 
 impl Rpc for AdminRpc {
@@ -693,15 +698,7 @@ impl AdminRpcHandler {
 				)))
 			}
 		} else {
-			let repair = OnlineRepair {
-				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
-				});
+			launch_online_repair(self.garage.clone(), opt).await;
 			Ok(AdminRpc::Ok(format!(
 				"Repair launched on {:?}",
 				self.garage.system.id
@@ -830,6 +827,17 @@ impl AdminRpcHandler {
 
 		Ok(())
 	}
+
+	// ----
+
+	async fn handle_worker_cmd(&self, opt: WorkerOpt) -> Result<AdminRpc, Error> {
+		match opt.cmd {
+			WorkerCmd::List { opt } => {
+				let workers = self.garage.background.get_worker_info();
+				Ok(AdminRpc::WorkerList(workers, opt))
+			}
+		}
+	}
 }
 
 #[async_trait]
@@ -845,6 +853,7 @@ impl EndpointHandler<AdminRpc> for AdminRpcHandler {
 			AdminRpc::Migrate(opt) => self.handle_migrate(opt.clone()).await,
 			AdminRpc::LaunchRepair(opt) => self.handle_launch_repair(opt.clone()).await,
 			AdminRpc::Stats(opt) => self.handle_stats(opt.clone()).await,
+			AdminRpc::Worker(opt) => self.handle_worker_cmd(opt.clone()).await,
 			m => Err(GarageError::unexpected_rpc_message(m).into()),
 		}
 	}
-- 
cgit v1.2.3