Merge branch 'unstable' into mds

Conflicts:
	src/TODO

1 files changed, 120 insertions, 1 deletions

diff --git a/src/TODO b/src/TODO
index a57a00112b5..bdc3b297cd1 100644
--- a/src/TODO
+++ b/src/TODO
@@ -61,10 +61,126 @@ filestore
 
 bugs
 - mds: rdlock forwards to auth on inode file lock, leading to an infinite forward loop if dirfrag is a subtree on another node.
-
+- mds states
+  - closing -> opening transition
+- mds prepare_force_open_sessions, then import aborts.. session is still OPENING but no client_session is sent...
 - rm -r failure (on kernel tree)
 - dbench 1, restart mds (may take a few times), dbench will error out.
 
+- kclient lockdep warning
+[ 1615.328733] =======================================================
+[ 1615.331050] [ INFO: possible circular locking dependency detected ]
+[ 1615.331050] 2.6.34-rc2 #22
+[ 1615.331050] -------------------------------------------------------
+[ 1615.331050] fixdep/3263 is trying to acquire lock:
+[ 1615.331050]  (&osdc->request_mutex){+.+...}, at: [<ffffffffa007b66c>] ceph_osdc_start_request+0x4d/0x278 [ceph]
+[ 1615.331050] 
+[ 1615.331050] but task is already holding lock:
+[ 1615.331050]  (&mm->mmap_sem){++++++}, at: [<ffffffff810208c0>] do_page_fault+0x104/0x278
+[ 1615.331050] 
+[ 1615.331050] which lock already depends on the new lock.
+[ 1615.331050] 
+[ 1615.331050] 
+[ 1615.331050] the existing dependency chain (in reverse order) is:
+[ 1615.331050] 
+[ 1615.331050] -> #3 (&mm->mmap_sem){++++++}:
+[ 1615.331050]        [<ffffffff81059fd3>] validate_chain+0xa4d/0xd28
+[ 1615.331050]        [<ffffffff8105aa7f>] __lock_acquire+0x7d1/0x84e
+[ 1615.331050]        [<ffffffff8105ab84>] lock_acquire+0x88/0xa5
+[ 1615.331050]        [<ffffffff81094daf>] might_fault+0x90/0xb3
+[ 1615.331050]        [<ffffffff81390d1e>] memcpy_fromiovecend+0x54/0x8e
+[ 1615.331050]        [<ffffffff813b6ea7>] ip_generic_getfrag+0x2a/0x8f
+[ 1615.331050]        [<ffffffff813b5da2>] ip_append_data+0x5f6/0x971
+[ 1615.331050]        [<ffffffff813d35bf>] udp_sendmsg+0x4e8/0x603
+[ 1615.331050]        [<ffffffff813d91e3>] inet_sendmsg+0x46/0x53
+[ 1615.331050]        [<ffffffff813878c1>] sock_sendmsg+0xd4/0xf5
+[ 1615.331050]        [<ffffffff81387e0f>] sys_sendto+0xdf/0x107
+[ 1615.331050]        [<ffffffff810029eb>] system_call_fastpath+0x16/0x1b
+[ 1615.331050] 
+[ 1615.331050] -> #2 (sk_lock-AF_INET){+.+.+.}:
+[ 1615.331050]        [<ffffffff81059fd3>] validate_chain+0xa4d/0xd28
+[ 1615.331050]        [<ffffffff8105aa7f>] __lock_acquire+0x7d1/0x84e
+[ 1615.331050]        [<ffffffff8105ab84>] lock_acquire+0x88/0xa5
+[ 1615.331050]        [<ffffffff8138a562>] lock_sock_nested+0xeb/0xff
+[ 1615.331050]        [<ffffffff813da29d>] inet_stream_connect+0x2b/0x25c
+[ 1615.331050]        [<ffffffffa006eea6>] try_write+0x26e/0x102c [ceph]
+[ 1615.331050]        [<ffffffffa00705ba>] con_work+0x126/0x6bc [ceph]
+[ 1615.529553]        [<ffffffff8104774e>] worker_thread+0x1e8/0x2fa
+[ 1615.529553]        [<ffffffff8104a4aa>] kthread+0x7d/0x85
+[ 1615.529553]        [<ffffffff81003794>] kernel_thread_helper+0x4/0x10
+[ 1615.529553] 
+[ 1615.529553] -> #1 (&con->mutex){+.+.+.}:
+[ 1615.529553]        [<ffffffff81059fd3>] validate_chain+0xa4d/0xd28
+[ 1615.529553]        [<ffffffff8105aa7f>] __lock_acquire+0x7d1/0x84e
+[ 1615.529553]        [<ffffffff8105ab84>] lock_acquire+0x88/0xa5
+[ 1615.529553]        [<ffffffff81425727>] mutex_lock_nested+0x62/0x32c
+[ 1615.529553]        [<ffffffffa0070cd3>] ceph_con_send+0xb3/0x244 [ceph]
+[ 1615.529553]        [<ffffffffa007b591>] __send_request+0x108/0x196 [ceph]
+[ 1615.529553]        [<ffffffffa007b794>] ceph_osdc_start_request+0x175/0x278 [ceph]
+[ 1615.529553]        [<ffffffffa006029d>] ceph_writepages_start+0xb23/0x112a [ceph]
+[ 1615.529553]        [<ffffffff810849aa>] do_writepages+0x1f/0x28
+[ 1615.529553]        [<ffffffff810ca5e8>] writeback_single_inode+0xb6/0x1f5
+[ 1615.529553]        [<ffffffff810cad9b>] writeback_inodes_wb+0x2d1/0x378
+[ 1615.529553]        [<ffffffff810cafa8>] wb_writeback+0x166/0x1e0
+[ 1615.529553]        [<ffffffff810cb154>] wb_do_writeback+0x83/0x1d3
+[ 1615.529553]        [<ffffffff810cb2d2>] bdi_writeback_task+0x2e/0x9b
+[ 1615.529553]        [<ffffffff8108fd73>] bdi_start_fn+0x71/0xd2
+[ 1615.529553]        [<ffffffff8104a4aa>] kthread+0x7d/0x85
+[ 1615.529553]        [<ffffffff81003794>] kernel_thread_helper+0x4/0x10
+[ 1615.529553] 
+[ 1615.529553] -> #0 (&osdc->request_mutex){+.+...}:
+[ 1615.529553]        [<ffffffff81059cbf>] validate_chain+0x739/0xd28
+[ 1615.529553]        [<ffffffff8105aa7f>] __lock_acquire+0x7d1/0x84e
+[ 1615.529553]        [<ffffffff8105ab84>] lock_acquire+0x88/0xa5
+[ 1615.529553]        [<ffffffff81425727>] mutex_lock_nested+0x62/0x32c
+[ 1615.529553]        [<ffffffffa007b66c>] ceph_osdc_start_request+0x4d/0x278 [ceph]
+[ 1615.529553]        [<ffffffffa007d8b6>] ceph_osdc_readpages+0x123/0x222 [ceph]
+[ 1615.529553]        [<ffffffffa005f4b7>] ceph_readpages+0x193/0x456 [ceph]
+[ 1615.529553]        [<ffffffff81085bd1>] __do_page_cache_readahead+0x17d/0x1f5
+[ 1615.529553]        [<ffffffff81085c65>] ra_submit+0x1c/0x20
+[ 1615.529553]        [<ffffffff81085fab>] ondemand_readahead+0x264/0x277
+[ 1615.529553]        [<ffffffff81086092>] page_cache_sync_readahead+0x33/0x35
+[ 1615.529553]        [<ffffffff8107f0d7>] filemap_fault+0x143/0x31f
+[ 1615.529553]        [<ffffffff810913bf>] __do_fault+0x50/0x415
+[ 1615.529553]        [<ffffffff810934d9>] handle_mm_fault+0x334/0x6a6
+[ 1615.529553]        [<ffffffff810209af>] do_page_fault+0x1f3/0x278
+[ 1615.529553]        [<ffffffff814281ff>] page_fault+0x1f/0x30
+[ 1615.529553] 
+[ 1615.529553] other info that might help us debug this:
+[ 1615.529553] 
+[ 1615.529553] 1 lock held by fixdep/3263:
+[ 1615.529553]  #0:  (&mm->mmap_sem){++++++}, at: [<ffffffff810208c0>] do_page_fault+0x104/0x278
+[ 1615.529553] 
+[ 1615.529553] stack backtrace:
+[ 1615.529553] Pid: 3263, comm: fixdep Not tainted 2.6.34-rc2 #22
+[ 1615.529553] Call Trace:
+[ 1615.529553]  [<ffffffff81058f49>] print_circular_bug+0xb3/0xc1
+[ 1615.529553]  [<ffffffff81059cbf>] validate_chain+0x739/0xd28
+[ 1615.529553]  [<ffffffff810099d7>] ? native_sched_clock+0x37/0x71
+[ 1615.824177]  [<ffffffff8105aa7f>] __lock_acquire+0x7d1/0x84e
+[ 1615.824177]  [<ffffffff8105ab84>] lock_acquire+0x88/0xa5
+[ 1615.824177]  [<ffffffffa007b66c>] ? ceph_osdc_start_request+0x4d/0x278 [ceph]
+[ 1615.824177]  [<ffffffffa007b66c>] ? ceph_osdc_start_request+0x4d/0x278 [ceph]
+[ 1615.824177]  [<ffffffff81425727>] mutex_lock_nested+0x62/0x32c
+[ 1615.824177]  [<ffffffffa007b66c>] ? ceph_osdc_start_request+0x4d/0x278 [ceph]
+[ 1615.824177]  [<ffffffffa007b66c>] ceph_osdc_start_request+0x4d/0x278 [ceph]
+[ 1615.824177]  [<ffffffffa007d8b6>] ceph_osdc_readpages+0x123/0x222 [ceph]
+[ 1615.824177]  [<ffffffffa005f4b7>] ceph_readpages+0x193/0x456 [ceph]
+[ 1615.824177]  [<ffffffff810099d7>] ? native_sched_clock+0x37/0x71
+[ 1615.824177]  [<ffffffff81056580>] ? get_lock_stats+0x19/0x4c
+[ 1615.824177]  [<ffffffff81085bd1>] __do_page_cache_readahead+0x17d/0x1f5
+[ 1615.824177]  [<ffffffff81085ad0>] ? __do_page_cache_readahead+0x7c/0x1f5
+[ 1615.824177]  [<ffffffff8107d848>] ? find_get_page+0xd9/0x12d
+[ 1615.824177]  [<ffffffff81085c65>] ra_submit+0x1c/0x20
+[ 1615.916887]  [<ffffffff81085fab>] ondemand_readahead+0x264/0x277
+[ 1615.916887]  [<ffffffff81086092>] page_cache_sync_readahead+0x33/0x35
+[ 1615.931403]  [<ffffffff8107f0d7>] filemap_fault+0x143/0x31f
+[ 1615.931403]  [<ffffffff810913bf>] __do_fault+0x50/0x415
+[ 1615.931403]  [<ffffffff8105aa99>] ? __lock_acquire+0x7eb/0x84e
+[ 1615.946963]  [<ffffffff810934d9>] handle_mm_fault+0x334/0x6a6
+[ 1615.946963]  [<ffffffff810209af>] do_page_fault+0x1f3/0x278
+[ 1615.946963]  [<ffffffff814281ff>] page_fault+0x1f/0x30
+
 - kclient: moonbeamer gets this with iozone -a...
 [17608.696906] ------------[ cut here ]------------
 [17608.701761] WARNING: at lib/kref.c:43 kref_get+0x23/0x2a()
@@ -242,6 +358,8 @@ repair
 - mds scrubbing
 
 kclient
+- mdsc: preallocate reply(ies?)
+- kill msgpool for statfs
 - ENOMEM
   - message pools
   - sockets?  (this can actual generates a lockdep warning :/)
@@ -297,6 +415,7 @@ uclient
 - hadoop: clean up assert usage
 
 mds
+- should we occasionally journal session completed requests??
 - don't sync log on every clientreplay request?
 - pass issued, wanted into eval(lock) when eval() already has it?  (and otherwise optimize eval paths..)
 - add an up:shadow mode?