1. 07 Jul, 2008 2 commits
    • Steven Whitehouse's avatar
      [GFS2] Allow local DF locks when holding a cached EX glock · 209806ab
      Steven Whitehouse authored
      We already allow local SH locks while we hold a cached EX glock, so here
      we allow DF locks as well. This works only because we rely on the VFS's
      invalidation for locally cached data, and because if we hold an EX lock,
      then we know that no other node can be caching data relating to this
      file.
      
      It dramatically speeds up initial writes to O_DIRECT files since we fall
      back to buffered I/O for this and would otherwise bounce between DF and
      EX modes on each and every write call. The lessons to be learned from
      that are to ensure that (for the time being anyway) O_DIRECT files are
      preallocated and that they are written to using reasonably large I/O
      sizes. Even so this change fixes that corner case nicely
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      209806ab
    • Steven Whitehouse's avatar
      [GFS2] Fix delayed demote race · 265d529c
      Steven Whitehouse authored
      There is a race in the delayed demote code where it does the wrong thing
      if a demotion to UN has occurred for other reasons before the delay has
      expired. This patch adds an assert to catch that condition as well as
      fixing the root cause by adding an additional check for the UN state.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      Cc: Bob Peterson <rpeterso@redhat.com>
      265d529c
  2. 03 Jul, 2008 1 commit
    • Miklos Szeredi's avatar
      [GFS2] don't call permission() · f58ba889
      Miklos Szeredi authored
      GFS2 calls permission() to verify permissions after locks on the files
      have been taken.
      
      For this it's sufficient to call gfs2_permission() instead.  This
      results in the following changes:
      
        - IS_RDONLY() check is not performed
        - IS_IMMUTABLE() check is not performed
        - devcgroup_inode_permission() is not called
        - security_inode_permission() is not called
      
      IS_RDONLY() should be unnecessary anyway, as the per-mount read-only
      flag should provide protection against read-only remounts during
      operations.  do_gfs2_set_flags() has been fixed to perform
      mnt_want_write()/mnt_drop_write() to protect against remounting
      read-only.
      
      IS_IMMUTABLE has been added to gfs2_permission()
      
      Repeating the security checks seems to be pointless, as they don't
      normally change, and if they do, it's independent of the filesystem
      state.
      Signed-off-by: default avatarMiklos Szeredi <mszeredi@suse.cz>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      f58ba889
  3. 27 Jun, 2008 12 commits
    • Steven Whitehouse's avatar
      [GFS2] Fix module building · f17172e0
      Steven Whitehouse authored
      Two lines missed from the previous patch.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      f17172e0
    • Steven Whitehouse's avatar
      [GFS2] Glock documentation · 9f1585cb
      Steven Whitehouse authored
      This patch adds a file describing the internals of GFS2's glock
      abstraction.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      9f1585cb
    • Steven Whitehouse's avatar
      [GFS2] Remove all_list from lock_dlm · 31fcba00
      Steven Whitehouse authored
      I discovered that we had a list onto which every lock_dlm
      lock was being put. Its only function was to discover whether
      we'd got any locks left after umount. Since there was already
      a counter for that purpose as well, I removed the list. The
      saving is sizeof(struct list_head) per glock - well worth
      having.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      31fcba00
    • Steven Whitehouse's avatar
      [GFS2] Remove obsolete conversion deadlock avoidance code · b2cad26c
      Steven Whitehouse authored
      This is only used by GFS1 so can be removed.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      b2cad26c
    • Steven Whitehouse's avatar
      [GFS2] Remove remote lock dropping code · 1bdad606
      Steven Whitehouse authored
      There are several reasons why this is undesirable:
      
       1. It never happens during normal operation anyway
       2. If it does happen it causes performance to be very, very poor
       3. It isn't likely to solve the original problem (memory shortage
          on remote DLM node) it was supposed to solve
       4. It uses a bunch of arbitrary constants which are unlikely to be
          correct for any particular situation and for which the tuning seems
          to be a black art.
       5. In an N node cluster, only 1/N of the dropped locked will actually
          contribute to solving the problem on average.
      
      So all in all we are better off without it. This also makes merging
      the lock_dlm module into GFS2 a bit easier.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      1bdad606
    • Bob Peterson's avatar
      [GFS2] kernel panic mounting volume · 9171f5a9
      Bob Peterson authored
      This patch fixes Red Hat bugzilla bug 450156.
      
      This started with a not-too-improbable mount failure because the
      locking protocol was never set back to its proper "lock_dlm" after the
      system was rebooted in the middle of a gfs2_fsck.  That left a
      (purposely) invalid locking protocol in the superblock, which caused an
      error when the file system was mounted the next time.
      
      When there's an error mounting, vfs calls DQUOT_OFF, which calls
      vfs_quota_off which calls gfs2_sync_fs.  Next, gfs2_sync_fs calls
      gfs2_log_flush passing s_fs_info.  But due to the error, s_fs_info
      had been previously set to NULL, and so we have the kernel oops.
      
      My solution in this patch is to test for the NULL value before passing
      it.  I tested this patch and it fixes the problem.
      Signed-off-by: default avatarBob Peterson <rpeterso@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      9171f5a9
    • Steven Whitehouse's avatar
      [GFS2] Revise readpage locking · 01b7c7ae
      Steven Whitehouse authored
      The previous attempt to fix the locking in readpage failed due
      to the use of a "try lock" which resulted in occasional high
      cpu usage during testing (due to repeated tries) and also it
      did not resolve all the ordering problems wrt the transaction
      lock (although it did solve all the inode lock ordering problems).
      
      This patch avoids the problem by unlocking the page and getting the
      locks in the correct order. This means that we have to retest the
      page to ensure that it hasn't changed when we relock the page.
      
      This now passes the tests which were previously failing.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      01b7c7ae
    • Steven Whitehouse's avatar
      [GFS2] Fix ordering of args for list_add · 80274737
      Steven Whitehouse authored
      The patch to remove lock_nolock managed to get the arguments
      of this list_add backwards. This fixes it.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      80274737
    • Harvey Harrison's avatar
      [GFS2] trivial sparse lock annotations · 2d81afb8
      Harvey Harrison authored
      Annotate the &sdp->sd_log_lock.
      Signed-off-by: default avatarHarvey Harrison <harvey.harrison@gmail.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      2d81afb8
    • Steven Whitehouse's avatar
      [GFS2] No lock_nolock · 048bca22
      Steven Whitehouse authored
      This patch merges the lock_nolock module into GFS2 itself. As well as removing
      some of the overhead of the module, it also means that its now impossible to
      build GFS2 without a lock module (which would be a pointless thing to do
      anyway).
      
      We also plan to merge lock_dlm into GFS2 in the future, but that is a more
      tricky task, and will therefore be a separate patch.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      Cc: David Teigland <teigland@redhat.com>
      048bca22
    • Steven Whitehouse's avatar
      [GFS2] Fix ordering bug in lock_dlm · f3c9d38a
      Steven Whitehouse authored
      This looks like a lot of change, but in fact its not. Mostly its
      things moving from one file to another. The change is just that
      instead of queuing lock completions and callbacks from the DLM
      we now pass them directly to GFS2.
      
      This gives us a net loss of two list heads per glock (a fair
      saving in memory) plus a reduction in the latency of delivering
      the messages to GFS2, plus we now have one thread fewer as well.
      There was a bug where callbacks and completions could be delivered
      in the wrong order due to this unnecessary queuing which is fixed
      by this patch.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      Cc: Bob Peterson <rpeterso@redhat.com>
      f3c9d38a
    • Steven Whitehouse's avatar
      [GFS2] Clean up the glock core · 6802e340
      Steven Whitehouse authored
      This patch implements a number of cleanups to the core of the
      GFS2 glock code. As a result a lot of code is removed. It looks
      like a really big change, but actually a large part of this patch
      is either removing or moving existing code.
      
      There are some new bits too though, such as the new run_queue()
      function which is considerably streamlined. Highlights of this
      patch include:
      
       o Fixes a cluster coherency bug during SH -> EX lock conversions
       o Removes the "glmutex" code in favour of a single bit lock
       o Removes the ->go_xmote_bh() for inodes since it was duplicating
         ->go_lock()
       o We now only use the ->lm_lock() function for both locks and
         unlocks (i.e. unlock is a lock with target mode LM_ST_UNLOCKED)
       o The fast path is considerably shortly, giving performance gains
         especially with lock_nolock
       o The glock_workqueue is now used for all the callbacks from the DLM
         which allows us to simplify the lock_dlm module (see following patch)
       o The way is now open to make further changes such as eliminating the two
         threads (gfs2_glockd and gfs2_scand) in favour of a more efficient
         scheme.
      
      This patch has undergone extensive testing with various test suites
      so it should be pretty stable by now.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      Cc: Bob Peterson <rpeterso@redhat.com>
      6802e340
  4. 25 Jun, 2008 4 commits
  5. 24 Jun, 2008 21 commits