From 4172109c8dc91c41cb9ad868243c3c1e6e511ee3 Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Wed, 26 Jun 2024 15:02:10 -0400
Subject: [PATCH] support multi-gateway clusters

VIA extension still needed otherwise a copy to a cluster can loop
forever.
---
 Annex/Cluster.hs                | 18 +++++++++++++-----
 doc/todo/git-annex_proxies.mdwn |  6 ------
 2 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/Annex/Cluster.hs b/Annex/Cluster.hs
index 599dc1c417..6ddf9029c1 100644
--- a/Annex/Cluster.hs
+++ b/Annex/Cluster.hs
@@ -65,8 +65,9 @@ clusterProxySelector clusteruuid protocolversion = do
 	nodeuuids <- (fromMaybe S.empty . M.lookup clusteruuid . clusterUUIDs)
 		<$> getClusters
 	clusternames <- annexClusters <$> Annex.getGitConfig
-	remotes <- filter (isnode nodeuuids clusternames) <$> remoteList
-	nodes <- mapM (proxySshRemoteSide protocolversion) remotes
+	allremotes <- remoteList
+	let clusterremotes = filter (isnode allremotes nodeuuids clusternames) allremotes
+	nodes <- mapM (proxySshRemoteSide protocolversion) clusterremotes
 	return $ ProxySelector
 		{ proxyCHECKPRESENT = nodecontaining nodes
 		, proxyGET = nodecontaining nodes
@@ -94,15 +95,22 @@ clusterProxySelector clusteruuid protocolversion = do
 		}
   where
 	-- Nodes of the cluster have remote.name.annex-cluster-node
-	-- containing its name.
-	isnode nodeuuids clusternames r = 
+	-- containing its name. Or they are proxied by a remote
+	-- that has remote.name.annex-cluster-node containing the cluster's
+	-- UUID.
+	isnode rs nodeuuids clusternames r = 
 		case remoteAnnexClusterNode (Remote.gitconfig r) of
-			Nothing -> False
 			Just names
 				| any (isclustername clusternames) names ->
 					flip S.member nodeuuids $ 
 						ClusterNodeUUID $ Remote.uuid r
 				| otherwise -> False
+			Nothing -> case remoteAnnexProxiedBy (Remote.gitconfig r) of
+				Just proxyuuid -> not $ null $
+					filter (== clusteruuid) $
+					concatMap (remoteAnnexClusterGateway . Remote.gitconfig) $
+					filter (\p -> Remote.uuid p == proxyuuid) rs
+				Nothing -> False
 	
 	isclustername clusternames name = 
 		M.lookup name clusternames == Just clusteruuid
diff --git a/doc/todo/git-annex_proxies.mdwn b/doc/todo/git-annex_proxies.mdwn
index a3584840cf..ac106adceb 100644
--- a/doc/todo/git-annex_proxies.mdwn
+++ b/doc/todo/git-annex_proxies.mdwn
@@ -33,12 +33,6 @@ For June's work on [[design/passthrough_proxy]], remaining todos:
   protocol messages on to any remotes that have the same UUID as
   the cluster. Needs VIA extension to P2P protocol to avoid cycles.
 
-  Current status: Distributed cluster nodes are visible,
-  and can be accessed directly, but trying to GET from a cluster
-  fails when the content is located behind a remote gateway.
-  And PUT only sends to the immediate nodes
-  of the cluster, not on to other gateways.
-
 * Getting a key from a cluster currently always selects the lowest cost
   remote, and always the same remote if cost is the same. Should
   round-robin amoung remotes, and prefer to avoid using remotes that