From bd43b3a26345ab8824378e0e5c43c7a7ecf8c8c0 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 31 Mar 2010 15:30:29 -0700 Subject: [PATCH] todo: updates --- src/TODO | 95 +++++++++----------------------------------------------- 1 file changed, 14 insertions(+), 81 deletions(-) diff --git a/src/TODO b/src/TODO index eb8e5865a9c72..4e967c779c9fe 100644 --- a/src/TODO +++ b/src/TODO @@ -42,9 +42,17 @@ v0.19 - debian: packaging fixes v0.20 -- new filestore, journaling +- osd: new filestore, journaling infrastructure +- msgr: wire protocol improvements (lower per-message overhead) +- mds: reduced memory utilization (still more to do!) +- mds: many single mds fixes +- mds: many clustered mds fixes +- auth: many auth_x cleanups, fixes, improvements +- kclient: many bug fixes -- multiple mds fixes +v0.21 + +- - qa: snap test. maybe walk through 2.6.* kernel trees? - osd: rebuild pg log @@ -52,13 +60,6 @@ v0.20 - rebuild mds hierarchy - kclient: retry alloc on ENOMEM when reading from connection? -filestore -- throttling -- flush objects onto primary during recovery -- audit queue_transaction calls for dependencies -- convert apply_transaction calls in handle_map to queue? - - need an osdmap cache layer? - bugs - mds rejoin: invented dirfrags (MDCache.cc:3469) have version=0; subsequent modification of dentries/inodes predirty a bad (small) version #. - rm -r failure (on kernel tree) @@ -234,74 +235,6 @@ bugs [ 2793.950108] RSP [ 2794.275464] ---[ end trace e39f19630a44d9a2 ]--- -- kclient: moonbeamer gets this with iozone -a... -[17608.696906] ------------[ cut here ]------------ -[17608.701761] WARNING: at lib/kref.c:43 kref_get+0x23/0x2a() -[17608.707584] Hardware name: PDSMi -[17608.711056] Modules linked in: aes_x86_64 aes_generic ceph fan ac battery ehci_hcd container uhci_hcd thermal button processor - -[17608.723268] Pid: 19594, comm: sync Not tainted 2.6.32-rc2 #12 -[17608.729255] Call Trace: -[17608.731835] [] ? kref_get+0x23/0x2a -[17608.737209] [] warn_slowpath_common+0x77/0x8f -[17608.743457] [] warn_slowpath_null+0xf/0x11 -[17608.749395] [] kref_get+0x23/0x2a -[17608.754634] [] ceph_mdsc_sync+0xd7/0x305 [ceph] -[17608.761061] [] ? mutex_unlock+0x9/0xb -[17608.766618] [] ? ceph_osdc_sync+0xe7/0x173 [ceph] -[17608.773199] [] ceph_syncfs+0x4e/0xc8 [ceph] -[17608.779235] [] __sync_filesystem+0x5e/0x72 -[17608.785195] [] sync_filesystems+0xaa/0x101 -[17608.791122] [] sys_sync+0x12/0x2e -[17608.796331] [] system_call_fastpath+0x16/0x1b -[17608.802560] ---[ end trace 36481c4089b3d493 ]--- -[17608.807461] BUG: unable to handle kernel paging request at 0000001200000635 -[17608.811372] IP: [] kref_put+0x31/0x4f -[17608.811372] PGD 11c7c8067 PUD 0 -[17608.811372] Oops: 0002 [#1] PREEMPT SMP -[17608.811372] last sysfs file: /sys/kernel/uevent_seqnum -[17608.811372] CPU 0 -[17608.811372] Modules linked in: aes_x86_64 aes_generic ceph fan ac battery ehci_hcd container uhci_hcd thermal button processor - -[17608.811372] Pid: 19594, comm: sync Tainted: G W 2.6.32-rc2 #12 PDSMi -[17608.811372] RIP: 0010:[] [] kref_put+0x31/0x4f -[17608.811372] RSP: 0018:ffff8801137f5e28 EFLAGS: 00010206 -[17608.811372] RAX: 0000001200000495 RBX: 0000001200000635 RCX: 0000000000000000 -[17608.811372] RDX: 0000000000000000 RSI: 0000000000000040 RDI: 0000001200000635 -[17608.811372] RBP: ffff8801137f5e38 R08: 0000000000000000 R09: ffff8801137f5e28 -[17608.811372] R10: ffff8801137f5e38 R11: ffffffff8145c5ad R12: ffffffffa00675ae -[17608.811372] R13: ffff880119d02508 R14: ffff880119d02510 R15: 0000000000055fad -[17608.811372] FS: 00007fadcfcd96e0(0000) GS:ffff88002f000000(0000) knlGS:0000000000000000 -[17608.811372] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b -[17608.811372] CR2: 0000001200000635 CR3: 00000001136cd000 CR4: 00000000000006f0 -[17608.811372] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 -[17608.811372] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 - -[17608.811372] Process sync (pid: 19594, threadinfo ffff8801137f4000, task ffff88011bf70480) -[17608.811372] Stack: -[17608.811372] ffff880103726e18 ffff880103726c00 ffff8801137f5e58 ffffffffa00733f1 -[17608.811372] <0> ffff880103726e18 ffffffffa00733a2 ffff8801137f5e78 ffffffff81252a3e -[17608.811372] <0> 0000000000000000 ffff880103726c00 ffff8801137f5ef8 ffffffffa006ea19 -[17608.811372] Call Trace: -[17608.811372] [] ceph_mdsc_release_request+0x4f/0x12a [ceph] -[17608.811372] [] ? ceph_mdsc_release_request+0x0/0x12a [ceph] -[17608.811372] [] kref_put+0x43/0x4f -[17608.811372] [] ceph_mdsc_sync+0x132/0x305 [ceph] -[17608.811372] [] ? mutex_unlock+0x9/0xb -[17608.811372] [] ? ceph_osdc_sync+0xe7/0x173 [ceph] -[17608.811372] [] ceph_syncfs+0x4e/0xc8 [ceph] -[17608.811372] [] __sync_filesystem+0x5e/0x72 -[17608.811372] [] sync_filesystems+0xaa/0x101 -[17608.811372] [] sys_sync+0x12/0x2e - -[17608.811372] [] system_call_fastpath+0x16/0x1b -[17608.811372] Code: 49 89 f4 4d 85 e4 be 40 00 00 00 53 48 89 fb 74 0e 49 81 fc 2d 09 0d 81 75 11 be 41 00 00 00 48 c7 c7 62 f8 5c 81 e8 86 25 df ff ff 0b 0f 94 c0 31 d2 84 c0 74 0b 48 89 df 41 ff d4 ba 01 00 -[17608.811372] RIP [] kref_put+0x31/0x4f -[17608.811372] RSP -[17608.811372] CR2: 0000001200000635 -[17609.074355] ---[ end trace 36481c4089b3d494 ]--- - - ?- bonnie++ -u root -d /mnt/ceph/ -s 0 -n 1 (03:35:29 PM) Isteriat: Using uid:0, gid:0. (03:35:29 PM) Isteriat: Create files in sequential order...done. @@ -310,9 +243,7 @@ bugs - osd pg split breaks if not all osds are up... -- mds recovery flag set on inode that didn't get recovered?? - osd pg split breaks if not all osds are up... -- mislinked directory? (cpusr.sh, mv /c/* /c/t, more cpusr, ls /c/t) filestore performance notes @@ -387,6 +318,9 @@ later and make get/put usage more consistent/stringently mandated. rados +- snapc interface + - mon: allocate snapid, adjust pool_t seq + - librados: snapc manipulation, set pool handle snapc - make rest interface superset of s3? - create/delete snapshots - list, access snapped version @@ -412,13 +346,12 @@ repair kclient - mdsc: preallocate reply(ies?) -- kill msgpool for statfs +- osdc: combine request, request+reply messages into single pool. - ENOMEM - message pools - sockets? (this can actual generates a lockdep warning :/) - fs-portable file layout virtual xattr (see Andreas' -fsdevel thread) - statlite -- audit/combine/rework/whatever invalidate, writeback threads and associated invariants - add cap to release if we get fouled up in fill_inode et al? - fix up ESTALE handling - don't retry on ENOMEM on non-nofail requests in kick_requests -- 2.39.5