From d876e06e35b15a1fdf9d7383d79cd010f5348521 Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Wed, 28 Aug 2024 14:13:12 -0400
Subject: [PATCH] err on the side of larger repository size

When a live update is removing a key, it might fail. So only count those
once they have succeeded. When a live update is adding a key, count it
immediately to avoid over-filling a repo.

This also makes the 1 minute delay between stale live changes checks
more defensible, because a stale live change can only cause us to err
more on the side of caution.
---
 Annex/RepoSize.hs    |  9 ++++++++-
 Database/RepoSize.hs | 10 +++++-----
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/Annex/RepoSize.hs b/Annex/RepoSize.hs
index 8da005e2a8..680a6e897b 100644
--- a/Annex/RepoSize.hs
+++ b/Annex/RepoSize.hs
@@ -57,7 +57,7 @@ getLiveRepoSizes quiet = do
 	go sizemap = do
 		h <- Db.getRepoSizeHandle
 		checkStaleSizeChanges h
-		liveoffsets <- liftIO $ Db.liveRepoOffsets h
+		liveoffsets <- liftIO $ Db.liveRepoOffsets h wantlivesizechange
 		let calc u (RepoSize size, SizeOffset startoffset) =
 			case M.lookup u liveoffsets of
 				Nothing -> RepoSize size
@@ -65,6 +65,13 @@ getLiveRepoSizes quiet = do
 					size + (offset - startoffset)
 		return $ M.mapWithKey calc sizemap
 
+	-- When a live update is in progress, only count it
+	-- when it makes a repository larger. Better to err on the side
+	-- of repositories being too large than assume that drops will
+	-- always succeed.
+	wantlivesizechange AddingKey = True
+	wantlivesizechange RemovingKey = False
+
 {- Fills an empty Annex.reposizes MVar with current information
  - from the git-annex branch, supplimented with journalled but
  - not yet committed information.
diff --git a/Database/RepoSize.hs b/Database/RepoSize.hs
index 1fbee8f660..73a1d06700 100644
--- a/Database/RepoSize.hs
+++ b/Database/RepoSize.hs
@@ -353,7 +353,7 @@ recordedRepoOffsets (RepoSizeHandle (Just h) _) =
 recordedRepoOffsets (RepoSizeHandle Nothing _) = pure mempty
 
 {- Gets the offsets to sizes of Repos, including all live changes that
- - are happening now.
+ - are happening now whose SizeChange matches the provided function.
  -
  - This does not necessarily include all changes that have been made,
  - only ones that had startingLiveSizeChange called for them will be
@@ -372,8 +372,8 @@ recordedRepoOffsets (RepoSizeHandle Nothing _) = pure mempty
  - This is only expensive when there are a lot of live changes happening at
  - the same time.
  -}
-liveRepoOffsets :: RepoSizeHandle -> IO (M.Map UUID SizeOffset)
-liveRepoOffsets (RepoSizeHandle (Just h) _) = H.queryDb h $ do
+liveRepoOffsets :: RepoSizeHandle -> (SizeChange -> Bool) -> IO (M.Map UUID SizeOffset)
+liveRepoOffsets (RepoSizeHandle (Just h) _) wantedsizechange = H.queryDb h $ do
 	sizechanges <- getSizeChanges
 	livechanges <- getLiveSizeChangesMap
 	let us = S.toList $ S.fromList $
@@ -390,7 +390,7 @@ liveRepoOffsets (RepoSizeHandle (Just h) _) = H.queryDb h $ do
 			filterM (nonredundantlivechange livechangesbykey u)
 				(fromMaybe [] $ M.lookup u livechanges)
 		let sizechange = foldl' 
-			(\t (k, sc) -> updateRollingTotal t sc k)
+			(\t (k, sc) -> if wantedsizechange sc then updateRollingTotal t sc k else t)
 			(fromMaybe 0 (M.lookup u sizechanges))
 			livechanges'
 		return (u, SizeOffset sizechange)
@@ -411,4 +411,4 @@ liveRepoOffsets (RepoSizeHandle (Just h) _) = H.queryDb h $ do
 		filter (\(sc', cid') -> cid /= cid' && sc' == AddingKey)
 			(fromMaybe [] $ M.lookup k livechangesbykey)
 	competinglivechanges _ _ AddingKey _ = []
-liveRepoOffsets (RepoSizeHandle Nothing _) = pure mempty
+liveRepoOffsets (RepoSizeHandle Nothing _) _ = pure mempty