v0.4, todos

diff --git a/configure.ac b/configure.ac
index 2efd2518af60af7808980d779b4fbfa8774c19d3..dfb322213a2bcd386de7dffaebfcf5822c4ace91 100644 (file)
--- a/configure.ac
+++ b/configure.ac
@@ -12,7 +12,7 @@ AC_CANONICAL_HOST
 AC_CANONICAL_TARGET
 
 # Automake
-AM_INIT_AUTOMAKE(ceph, 0.3)
+AM_INIT_AUTOMAKE(ceph, 0.4)
 AM_PROG_CC_C_O
 
 # Platform

diff --git a/src/TODO b/src/TODO
index bb092a73a258a7c0029daee3d159b2c2036970d4..05cfbde09cb1dc4b287bec1d435924b8311f9883 100644 (file)
--- a/src/TODO
+++ b/src/TODO
@@ -1,10 +1,7 @@
-v0.4
-/- btrfs latency.  update howto.
-/- snap garbage collection
-/- journal
-
 v0.5
 - ENOSPC
+- efficient snap recovery
+- throttle osd recovery?
 - finish client failure recovery (reconnect after long eviction; and slow delayed reconnect)
 - make kclient use ->sendpage?
 - rip out io interruption?
@@ -83,6 +80,8 @@ mds
 
 - whats with the 'clear if dirtyscattered' bit in decode_import_inode()?
 
+- what if a recovery is queued, or in progress, and the inode is then cowed?  can that happen?  
+
 - proper handling of cache expire messages during rejoin phase?
   -> i think cache expires are fine; the rejoin_ack handler just has to behave if rejoining items go missing
 - try_remove_unlinked_dn thing