From 231cb32955080557b05c7dde7d7adee664457e0e Mon Sep 17 00:00:00 2001
From: Alex Auvolat <alex@adnab.me>
Date: Wed, 22 Apr 2020 19:25:15 +0000
Subject: Do not delete block if just a single replication error. Write TODO
 stuff.

---
 TODO         | 34 ++++++++++++++++++++++++++--------
 src/block.rs | 20 ++++++++++----------
 2 files changed, 36 insertions(+), 18 deletions(-)

diff --git a/TODO b/TODO
index 1b5f466d..a8ac6a49 100644
--- a/TODO
+++ b/TODO
@@ -1,18 +1,36 @@
-Replication
------------
-
-Finish the thing that sends blocks to other nodes if needed before deleting them locally.
+Testing
+-------
 
 How are we going to test that our replication method works correctly?
 We will have to introduce lots of dummy data and then add/remove nodes many times.
 
-Repair:
-- re-propagate block ref table to rc
+
+Improvements
+------------
+
+Membership: keep IP addresses of failed nodes and try to reping them regularly
+
+RPC client/server: do not go through the serialization+HTTP+TLS+deserialization when doing a request to ourself.
+
+RPC requests: unify quorum + timeout in a "RequestStrategy" class,
+and add to the request strategy whether or not the request should continue in the background
+once `quorum` valid responses have been received
+
+
+Attaining S3 compatibility
+--------------------------
+
+- table for access keys
+- S3 request signature verification
+- api_server following the S3 semantics for get/put/delete
+- implement object listing
+- possibly other necessary endpoints ?
 
 
-To do list
-----------
+Lower priority
+--------------
 
 - less a priority: hinted handoff
+- repair: re-propagate block ref table to rc
 - FIXME in rpc_server when garage shuts down and futures can be interrupted
   (tokio::spawn should be replaced by a new function background::spawn_joinable)
diff --git a/src/block.rs b/src/block.rs
index 46abcf02..6c785f89 100644
--- a/src/block.rs
+++ b/src/block.rs
@@ -278,25 +278,25 @@ impl BlockManager {
 				let who_needs = join_all(who_needs_fut).await;
 
 				let mut need_nodes = vec![];
-				let mut errors = 0;
 				for (node, needed) in who.into_iter().zip(who_needs.iter()) {
 					match needed {
 						Ok(Message::NeedBlockReply(true)) => {
 							need_nodes.push(node);
 						}
-						Err(_) => {
-							errors += 1;
+						Err(e) => {
+							return Err(Error::Message(format!(
+								"Should delete block, but unable to confirm that all other nodes that need it have it: {}",
+								e
+							)));
+						}
+						_ => {
+							return Err(Error::Message(format!(
+								"Unexpected response to NeedBlockQuery RPC"
+							)));
 						}
-						_ => (),
 					}
 				}
 
-				if errors > (garage.system.config.data_replication_factor - 1) / 2 {
-					return Err(Error::Message(format!(
-						"Should delete block, but not enough nodes confirm that they have it."
-					)));
-				}
-
 				if need_nodes.len() > 0 {
 					let put_block_message = self.read_block(hash).await?;
 					let put_responses = self
-- 
cgit v1.2.3