Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | mon: fix allocation of low global_ids after mon restarthistoric/aleung_mds_security | Sage Weil | 2009-12-02 | 2 | -7/+10 |
| | | | | | We need to set last_allocated in init(). Also avoid the -1 casting and just use 0 instead. | ||||
* | test_ioctls: print preferred_osd value from GET_LAYOUT ioctl | Sage Weil | 2009-12-02 | 2 | -2/+3 |
| | |||||
* | hash: fix whitespace | Sage Weil | 2009-12-02 | 1 | -4/+4 |
| | |||||
* | mds: set mdr->in[n] in rdlock_path_xlock_dentry | Sage Weil | 2009-12-02 | 1 | -0/+1 |
| | | | | | | | | | | | | | | | This keeps things consistent with what we'd get with path_traverse. Namely, it means that if done_locking gets set to true, then a future call to rdlock_path_pin_ref can bail out and return mdr->in[n] and get a correct value. This fixes touch mnt/a ls mnt touch mnt/.ceph mds hang on the create request. | ||||
* | mds: do not include /.ceph in readdir results | Sage Weil | 2009-12-02 | 2 | -0/+4 |
| | |||||
* | librados: set id in messenger | Greg Farnum | 2009-12-01 | 1 | -1/+1 |
| | |||||
* | rados: read benchmark is asynchronous. | Greg Farnum | 2009-12-01 | 1 | -32/+157 |
| | |||||
* | Change hump-backed variable names. | Greg Farnum | 2009-12-01 | 1 | -19/+21 |
| | | | | Initialize data->in_flight! | ||||
* | rados: pull sequential benchmark into its own function | Greg Farnum | 2009-12-01 | 1 | -41/+56 |
| | |||||
* | rados: remove iTime from object names for complete determinism | Greg Farnum | 2009-12-01 | 1 | -6/+3 |
| | |||||
* | rados: Handle errors slightly better | Greg Farnum | 2009-12-01 | 2 | -13/+30 |
| | |||||
* | rados: split up function into more subfunctions | Greg Farnum | 2009-12-01 | 1 | -142/+159 |
| | |||||
* | rados: Deterministically fill data, reverse count:time order | Greg Farnum | 2009-12-01 | 1 | -3/+8 |
| | |||||
* | librados: minor comments | Greg Farnum | 2009-12-01 | 1 | -0/+3 |
| | |||||
* | rados: Move variables into data structure; rename to be generic | Greg Farnum | 2009-12-01 | 1 | -88/+85 |
| | |||||
* | rados: Move benchmark functions into separate file | Greg Farnum | 2009-12-01 | 2 | -269/+291 |
| | |||||
* | qa: Rename a file for future clarity. | Greg Farnum | 2009-12-01 | 1 | -0/+0 |
| | |||||
* | qa: specify test path as argument ot runallone.sh | Sage Weil | 2009-12-01 | 2 | -5/+5 |
| | |||||
* | config: preserve argv[0] if appropriate | Sage Weil | 2009-12-01 | 1 | -1/+4 |
| | | | | This makes 'cfuse' show up in 'df' output. | ||||
* | qa: test mdstable failures | Sage Weil | 2009-12-01 | 3 | -10/+27 |
| | |||||
* | todo | Sage Weil | 2009-12-01 | 1 | -173/+3 |
| | | | | the lockdep was probably due to the leak of request_mutex? | ||||
* | mds: inject mds failure during mdstable operations | Sage Weil | 2009-12-01 | 4 | -0/+23 |
| | |||||
* | mds: log successful client reconnect | Sage Weil | 2009-12-01 | 1 | -4/+8 |
| | |||||
* | sepia: asdf | Sage Weil | 2009-12-01 | 1 | -2/+2 |
| | |||||
* | mds: journal/replay rollback on MDSTableServer | Sage Weil | 2009-12-01 | 3 | -0/+9 |
| | | | | We journal prepare and commit; need to do rollback to! | ||||
* | mds: track _note_prepared/committed in normal path, too | Sage Weil | 2009-12-01 | 2 | -1/+5 |
| | | | | This was broken by cd6f3817. | ||||
* | mds: pass do_eval through to adjsut_subtreeauth | Sage Weil | 2009-12-01 | 1 | -1/+1 |
| | |||||
* | vstart: add [mds.a] section when no -x | Sage Weil | 2009-12-01 | 1 | -2/+6 |
| | |||||
* | mds: drop requests on closed|closing|etc sessions | Sage Weil | 2009-12-01 | 1 | -1/+7 |
| | |||||
* | ceph.spec: mostly in line with .deb | Sage Weil | 2009-11-25 | 1 | -61/+28 |
| | | | | No packages for radosgw or libcrush/ceph/rados, though. | ||||
* | object: add missing include | Sage Weil | 2009-11-25 | 1 | -0/+1 |
| | | | | For sprintf(). | ||||
* | mds: ignore reconnect if session state is closed | Sage Weil | 2009-11-25 | 1 | -1/+1 |
| | | | | | On reconnect, if we didn't have a session from the journal, our Session state will be 'closed'. Act accordingly. | ||||
* | todo | Sage Weil | 2009-11-24 | 1 | -0/+112 |
| | |||||
* | mds: don't renew caps (or touch_session) on closed session | Sage Weil | 2009-11-24 | 2 | -8/+16 |
| | | | | Also assert that we're on the state list before touching. | ||||
* | mds: less --, more - | Sage Weil | 2009-11-24 | 1 | -2/+2 |
| | |||||
* | mds: update pending_for_mds during table server replay | Sage Weil | 2009-11-24 | 3 | -4/+12 |
| | | | | | Otherwise we our replay of AGREE after recovery is wrong; we just replay what was saved, without taking additional journaled items into account. | ||||
* | mon: add 'mds set_state <gid> <stateid>' | Sage Weil | 2009-11-24 | 1 | -0/+14 |
| | | | | For mdsmon disaster recovery :) | ||||
* | mon: avoid mds state update when clearing laggy flag | Sage Weil | 2009-11-24 | 1 | -29/+25 |
| | | | | | | Do not clear laggy flag (or otherwise get into prepare_update) if the mds hasn't seen the latest map. Previously we could go to clear laggy and also revert to an old mds state. | ||||
* | vstart.sh: fix -k for mds loading | Yehuda Sadeh | 2009-11-23 | 1 | -4/+2 |
| | |||||
* | vstart.sh: fix -k (cmds init) | Yehuda Sadeh | 2009-11-23 | 1 | -2/+2 |
| | |||||
* | msgr: fix bad unlock on tcp_write error | Sage Weil | 2009-11-23 | 1 | -4/+2 |
| | |||||
* | mds: fix replay of hard links | Sage Weil | 2009-11-23 | 1 | -1/+1 |
| | | | | | Use dir->link_remote_inode, not raw function, so that the CDir accounting gets set up. | ||||
* | mds: clear session before remove_session | Sage Weil | 2009-11-20 | 1 | -2/+1 |
| | | | | remove_session may drop the last ref. | ||||
* | mds: do not eval subtree root during rename_prepare | Sage Weil | 2009-11-20 | 3 | -11/+12 |
| | | | | | | | | | | | The eval may lead to a scatter_writebehind, which screws up the journal ordering. Since the inode is also locked, we will end up evaling it later anyway, so don't worry about it. I'm a bit unsure about the adjust_subtree_after_rename... that is during the rename_apply stage (after the log entry committed), so i think it's safe to do a scatter_writebehind here.. since we're not between a predirty and submit_entry. | ||||
* | todo | Sage Weil | 2009-11-20 | 1 | -54/+73 |
| | |||||
* | mds: fix client purge crash | Sage Weil | 2009-11-20 | 1 | -11/+1 |
| | | | | | | | | | | | | | | | | | | | | | | set_state moves the session to the per-session lists; do this _before_ remove_session (which removes the session entirely). Otherwise we fail an assert when deleting the session: mds/SessionMap.h: In function 'virtual Session::~Session()': mds/SessionMap.h:141: FAILED assert(!session_list_item.is_on_xlist()) 1: ./cmds(_Z18__ceph_assert_failPKcS0_iS0_+0x36) [0x97fc87] 2: ./cmds(_ZN7SessionD0Ev+0x47) [0x73d817] 3: ./cmds(_ZN16RefCountedObject3putEv+0xdb) [0x712c3b] 4: ./cmds(_ZN10ConnectionD0Ev+0x3a) [0x713f88] 5: ./cmds(_ZN10Connection3putEv+0x3d) [0x71294b] 6: ./cmds(_ZN15SimpleMessenger4PipeD1Ev+0x7f) [0x7130e1] 7: ./cmds(_ZN15SimpleMessenger6reaperEv+0x228) [0x7048ba] 8: ./cmds(_ZN15SimpleMessenger4waitEv+0x28) [0x7059dc] 9: ./cmds(main+0x305) [0x6f9345] 10: /lib/libc.so.6(__libc_start_main+0xe6) [0x7f2091e715c6] 11: ./cmds [0x6f8e39] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. | ||||
* | mon: fix use-after-free in mds mon blacklisting | Sage Weil | 2009-11-20 | 1 | -1/+1 |
| | |||||
* | mds: warn if replay used ino doesn't match session's next | Sage Weil | 2009-11-20 | 2 | -1/+12 |
| | |||||
* | mds: fix reconnect race | Sage Weil | 2009-11-20 | 3 | -2/+12 |
| | | | | | | | Don't ignore client replay or session msgs if we are moving to reconnect state. The client may get the mdsmap before us and send things our way, so take them if we are reconnect, or if we want reconnect. | ||||
* | mds: remove dead session request list trim waiter code | Sage Weil | 2009-11-20 | 1 | -14/+0 |
| | | | | I don't even remember what this was originally for. |