Skip to content
Commits on Jul 30, 2011
  1. @liewegas

    v0.32

    liewegas committed Jul 29, 2011
Commits on Jul 25, 2011
  1. @liewegas

    sync_filesystem: er, fix #define

    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 25, 2011
  2. @liewegas

    sync_files: #include _GNU_SOURCE for syncfs()

    Hopefully fixes: #1316
    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 25, 2011
  3. @liewegas

    admin_socket: no sock for unprivileged daemons; rename default

    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 25, 2011
  4. @liewegas

    osd: verify src range exists for CLONERANGE

    Make sure the source object extent does not extend past EOF when doing a
    CLONERANGE.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed with liewegas Jul 23, 2011
  5. @liewegas

    objecter: treat RESETSESSION like a reset

    Commit 065cdf5 rewrote ms_handle_reset but didn't adjust
    ms_handle_remote_reset (they used to be identical).  The result is lost
    MOSDOps if the osd ever sends a RESETSESSION.
    
    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 25, 2011
  6. Add more debugging for pthread_create failures

    Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
    Colin Patrick McCabe committed Jul 25, 2011
  7. @liewegas

    perfcounters: no more stat/ dir, yay!

    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 25, 2011
  8. @liewegas

    mds: be careful about calls to try_subtree_merge

    try_subtree_merge will, on occasion, journal something.  And anytime we
    journal something we may open a new segment and journal an ESubtreeMap.
    That means we subtree state needs to be consistent with any in-progress
    or finishing migrations.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  9. @liewegas

    mds: fix subtree_map simplify, again

    Erasing from the vector<> seems to be clobbering the iterator, even when it
    preceeds the deletion point.  Use integer index instead. Yuck!
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
Commits on Jul 24, 2011
  1. @liewegas

    mds: journal EImportFinish after updating subtree/import state

    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  2. @liewegas

    mds: journal copious ESubtreeMaps if mds_debug_subtrees

    Journal a new subtree map after every event if subtree debugging is
    enabled.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  3. @liewegas

    mds: fix stl iterator misuse in create_subtree_map

    q might be the first element, so we can't blindly --q; ++q.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  4. @liewegas

    perfcounters: remove stray #includes

    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  5. @liewegas

    admin_socket: fix EINTR check

    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  6. @liewegas

    admin_socket: fix busy loop

    Passing timeout==0 will return immediately.  Pass -1 to block until
    interesting happens.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  7. @liewegas

    mds: kill useless MDLog::writing_subtree_map

    No reason we can't have multiple maps in flight to the journal.  This looks
    like baggage from when subtree_map_expire_waiters was used.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  8. @liewegas

    mds: submit_entry last

    MDLog::submit_entry() may journal an ESubtreeMap as a side-effect, so make
    sure we have updated our state correctly _before_ calling it.  The safest
    is to just do it last.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  9. @liewegas

    mon: simplify 'mon tell ...'

    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 24, 2011
  10. @liewegas

    mon: rip out injectargs command(s)

    Use 'ceph [osd|mds|mon] tell <who> injectargs ...'
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 23, 2011
Commits on Jul 23, 2011
  1. @liewegas

    osd: fix OSDOp printer for CLONERANGE

    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 23, 2011
Commits on Jul 22, 2011
  1. @liewegas

    mon: 'dump [--format=json]'

    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 22, 2011
  2. @mlsorensen @liewegas

    auth: fix compile error when using nss libs

    auth/Crypto.cc:218: error: expected primary-expression before ?}? token
    auth/Crypto.cc:218: error: expected ?;? before ?}? token
    
    Signed-off-by: Marcus Sorensen <shadowsor@gmail.com>
    mlsorensen committed with liewegas Jul 22, 2011
  3. @gregsfortytwo

    mds: remove broken delay of cap releases from a replica.

    This hasn't worked in a very long time and serves little purpose
    since the clients will have their own cap delay releases.
    Nix a few of the repeated asserts while we're at it.
    
    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 22, 2011
  4. @gregsfortytwo

    Revert "mds: Only change in->replica_caps_wanted when actually messag…

    …ing"
    
    This reverts commit a2c761e. We actually
    want to change this whenever we try to send a message, and we do want
    to send messages during state REJOIN (the auth MDS will take the message if it's
    appropriate to do so; otherwise it drops the message because the information
    it contains is going to arrive anyway when we tell the MDS our entire
    replicated state as part of its rejoin). Instead, we're going to fix when we
    send messages so that it's not broken.
    
    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 22, 2011
  5. @gregsfortytwo

    mds: reorder timing checks in request_inode_file_caps

    We do want to hold onto caps for a few seconds after the client
    closes it, just in case it decides to re-open again! With the
    old arrangement the keep time was never moved off of zero.
    
    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 22, 2011
  6. @gregsfortytwo

    mds: Only change in->replica_caps_wanted when actually messaging

    Also, only send the message if the auth is past the REJOIN state.
    The auth will just drop it if it gets this request while in rejoin.
    
    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 22, 2011
  7. @gregsfortytwo

    mds: fix keep caps test.

    I think this has just been broken since it was written: previously it
    dropped the caps if the keep time was after current time. Since the
    keep time was never set to non-zero except after failing this test,
    and only changed once, if you didn't come into this function again
    within the 2-second window then you would never drop the caps.
    
    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 22, 2011
  8. @gregsfortytwo

    mds: rename cache expire variables for clarity

    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 22, 2011
  9. @gregsfortytwo

    update documentation on cache expires during exports

    Add an assert to check conditions.
    
    Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
    gregsfortytwo committed Jul 21, 2011
  10. @liewegas

    mon: 'pg dump [--format=json] [all|sum|pools|pgs|osds]'

    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 22, 2011
  11. @yehudasa

    librados: async pool creation

    yehudasa committed Jul 21, 2011
  12. @liewegas

    ceph: understand -- argument

    Signed-off-by: Sage Weil <sage@newdream.net>
    liewegas committed Jul 21, 2011
  13. @liewegas

    mds: cleanup-let: use is_leased() for lease revocation checks

    And add const-ness.
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 22, 2011
  14. @liewegas

    mds: revoke client leases on replica dn lock

    If a replica dentry gets a LOCK message, revoke client leases.  Don't just
    wait for them to expire!
    
    Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
    liewegas committed Jul 22, 2011
Something went wrong with that request. Please try again.