1. 09 Jul, 2007 3 commits
    • Robert Peterson's avatar
      [GFS2] Addendum patch 2 for gfs2_grow · cd81a4ba
      Robert Peterson authored
      This addendum patch 2 corrects three things:
      
      1. It fixes a stupid mistake in the previous addendum that broke gfs2.
         Ref: https://www.redhat.com/archives/cluster-devel/2007-May/msg00162.html
      
      
      2. It fixes a problem that Dave Teigland pointed out regarding the
         external declarations in ops_address.h being in the wrong place.
      3. It recasts a couple more %llu printks to (unsigned long long)
         as requested by Steve Whitehouse.
      
      I would have loved to put this all in one revised patch, but there was
      a rush to get some patches for RHEL5.	Therefore, the previous patches
      were applied to the git tree "as is" and therefore, I'm posting another
      addendum.  Sorry.
      Signed-off-by: default avatarBob Peterson <rpeterso@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      cd81a4ba
    • Robert Peterson's avatar
      [GFS2] Kernel changes to support new gfs2_grow command (part 2) · 6c53267f
      Robert Peterson authored
      
      
      To avoid code redundancy, I separated out the operational "guts" into
      a new function called read_rindex_entry.  Then I made two functions:
      the closer-to-original gfs2_ri_update (without the special condition
      checks) and gfs2_ri_update_special that's designed with that condition
      in mind.  (I don't like the name, but if you have a suggestion, I'm
      all ears).
      
      Oh, and there's an added benefit:  we don't need all the ugly gotos
      anymore.  ;)
      
      This patch has been tested with gfs2_fsck_hellfire (which runs for
      three and a half hours, btw).
      Signed-off-By: default avatarBob Peterson <rpeterso@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      6c53267f
    • Robert Peterson's avatar
      [GFS2] kernel changes to support new gfs2_grow command · 7ae8fa84
      Robert Peterson authored
      
      
      This is another revision of my gfs2 kernel patch that allows
      gfs2_grow to function properly.
      
      Steve Whitehouse expressed some concerns about the previous
      patch and I restructured it based on his comments.
      The previous patch was doing the statfs_change at file close time,
      under its own transaction.  The current patch does the statfs_change
      inside the gfs2_commit_write function, which keeps it under the
      umbrella of the inode transaction.
      
      I can't call ri_update to re-read the rindex file during the
      transaction because the transaction may have outstanding unwritten
      buffers attached to the rgrps that would be otherwise blown away.
      So instead, I created a new function, gfs2_ri_total, that will
      re-read the rindex file just to total the file system space
      for the sake of the statfs_change.  The ri_update will happen
      later, when gfs2 realizes the version number has changed, as it
      happened before my patch.
      
      Since the statfs_change is happening at write_commit time and there
      may be multiple writes to the rindex file for one grow operation.
      So one consequence of this restructuring is that instead of getting
      one kernel message to indicate the change, you may see several.
      For example, before when you did a gfs2_grow, you'd get a single
      message like:
      
      GFS2: File system extended by 247876 blocks (968MB)
      
      Now you get something like:
      
      GFS2: File system extended by 207896 blocks (812MB)
      GFS2: File system extended by 39980 blocks (156MB)
      
      This version has also been successfully run against the hours-long
      "gfs2_fsck_hellfire" test that does several gfs2_grow and gfs2_fsck
      while interjecting file system damage.  It does this repeatedly
      under a variety Resource Group conditions.
      Signed-off-By: default avatarBob Peterson <rpeterso@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      7ae8fa84
  2. 01 May, 2007 2 commits
    • Steven Whitehouse's avatar
      [GFS2] Patch to fix mmap of stuffed files · bf126aee
      Steven Whitehouse authored
      
      
      If a stuffed file is mmaped and a page fault is generated at some offset
      above the initial page, we need to create a zero page to hang the buffer
      heads off before we can unstuff the file. This is a fix for bz #236087
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      bf126aee
    • Josef Whiter's avatar
      [GFS2] Fix bz 231380, unlock page before dequeing glocks in gfs2_commit_write · 1de91390
      Josef Whiter authored
      
      
      If we are writing a file, and in the middle of writing the file
      another node attempts to get a shared lock on that file (by doing a du for
      example) the process doing the writing will hang waiting on lock_page.  The
      reason for this is because when we have waiters on a exclusive glock, we will go
      through and flush out all dirty pages associated with that inode and release the
      lock.  The problem is that when we flush the dirty pages, we could hit a page
      that we have locked durring the generic_file_buffered_write part of this
      operation.  This patch unlocks the page before we go to dequeue the lock and
      locks it immediatly afterwards, since generic_file_buffered_write needs the page
      locked when the commit_write is completed.  This patch resolves the problem,
      however if somebody sees a better way to do this please don't hesistate to yell.
      Signed-off-by: default avatarJosef Whiter <jwhiter@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      1de91390
  3. 07 Mar, 2007 1 commit
    • Josef Whiter's avatar
      [GFS2] fix hangup when multiple processes are trying to write to the same file · a13cbe37
      Josef Whiter authored
      
      
      This fixes a problem I encountered while running bonnie++.  When you have one
      thread that opens a file and starts to write to it, and then another thread that
      tries to open and write to the same file, the second thread will loop forever
      trying to grab the inode lock for that inode.  Basically we come in through
      generic_buffered_file_write, which calls gfs2_prepare_write, which then attempts
      to grab the glock.  Because we don't own the lock, gfs2_prepare_write gets
      GLR_TRYFAILED, which returns AOP_TRUNCATED_PAGE to generic_buffered_file_write.
      At this point generic_buffered_file_write loops around again and immediately
      retries the prepare_write.  This means that the second process never gets off of
      the processor in order to allow the process that holds the lock to finish its
      work and let go of the lock.  This patch makes gfs2_glock_nq schedule() if it
      gets back a GLR_TRYFAILED, which resolves this problem.
      Signed-off-by: default avatarJosef Whiter <jwhiter@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      a13cbe37
  4. 07 Feb, 2007 2 commits
  5. 05 Feb, 2007 3 commits
    • Steven Whitehouse's avatar
      [GFS2] Add writepages for "data=writeback" mounts · a8d638e3
      Steven Whitehouse authored
      
      
      It occurred to me that although a gfs2 specific writepages for ordered
      writes and journaled data would be tricky, by hooking writepages only
      for "data=writeback" mounts we could take advantage of not needing
      buffer heads (we don't use them on the read side, nor have we for some
      time) and create much larger I/Os for the block layer.
      
      Using blktrace both before and after, its possible to see that for large
      I/Os, most of the requests generated through writepages are now 1024
      sectors after this patch is applied as opposed to 8 sectors before.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      a8d638e3
    • Steven Whitehouse's avatar
      [GFS2] Fail over to readpage for stuffed files · e1d5b18a
      Steven Whitehouse authored
      
      
      This is partially derrived from a patch written by Russell Cattelan.
      It fixes a bug where there is a race between readpages and truncate
      by ignoring readpages for stuffed files. This is ok because a stuffed
      file will never be more than one block (minus sizeof(struct gfs2_dinode))
      in size and block size is always less than page size, so we do not lose
      anything efficiency-wise by not doing readahead for stuffed files. They
      will have already been "read ahead" by the action of reading the inode
      in, in the first place.
      
      This is the remaining part of the fix for Red Hat bugzilla #218966
      which had not yet made it upstream.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      Cc: Russell Cattelan <cattelan@redhat.com>
      e1d5b18a
    • Steven Whitehouse's avatar
      [GFS2] Fix DIO deadlock · c7b33834
      Steven Whitehouse authored
      
      
      This patch fixes Red Hat bugzilla #212627 in which a deadlock occurs
      due to trying to take the i_mutex while holding a glock. The correct
      locking order is defined as i_mutex -> glock in all cases.
      
      I've left dealing with allocating writes. I know that we need to do
      that, but for now this should do the trick. We don't need to take the
      i_mutex on write, because the VFS has already taken it for us. On read
      we don't need it since the glock is enough protection. The reason that
      I've made some of the checks into a separate function is that we'll need
      to do the checks again in the allocating write case eventually, so this
      is partly in preparation for this. Likewise the return value test of !=
      1 might look a bit odd and thats because we'll need a third return value
      in case of requiring an allocation.
      
      I've made the change to deferred mode on the glock to ensure flushing
      read caches on other nodes. I notice that (using blktrace to look at
      whats going on) we appear to do a better job of large I/Os than ext3
      after this patch (in terms of not splitting up the I/Os).
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      Cc: Wendy Cheng <wcheng@redhat.com>
      c7b33834
  6. 30 Nov, 2006 7 commits
  7. 03 Nov, 2006 1 commit
  8. 20 Oct, 2006 1 commit
  9. 12 Oct, 2006 3 commits
  10. 02 Oct, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Remove uneeded endian conversion · 48516ced
      Steven Whitehouse authored
      
      
      In many places GFS2 was calling the endian conversion routines
      for an inode even when only a single field, or a few fields might
      have changed. As a result we were copying lots of data needlessly.
      
      This patch replaces those calls with conversion of just the
      required fields in each case. This should be faster and easier
      to understand. There are still other places which suffer from this
      problem, but this is a start in the right direction.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      48516ced
  11. 25 Sep, 2006 1 commit
  12. 21 Sep, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Tidy up meta_io code · 7276b3b0
      Steven Whitehouse authored
      
      
      Fix a bug in the directory reading code, where we might have dereferenced
      a NULL pointer in case of OOM. Updated the directory code to use the new
      & improved version of gfs2_meta_ra() which now returns the first block
      that was being read. Previously it was releasing it requiring following
      code to grab the block again at each point it was called.
      
      Also turned off readahead on directory lookups since we are reading a
      hash table, and therefore reading the entries in order is very
      unlikely. Readahead is still used for all other calls to the
      directory reading function (e.g. when growing the hash table).
      
      Removed the DIO_START constant. Everywhere this was used, it was
      used to unconditionally start i/o aside from a couple of places, so
      I've removed it and made the couple of exceptions to this rule into
      separate functions.
      
      Also hunted through the other DIO flags and removed them as arguments
      from functions which were always called with the same combination of
      arguments.
      
      Updated gfs2_meta_indirect_buffer to be a bit more efficient and
      hopefully also be a bit easier to read.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      7276b3b0
  13. 20 Sep, 2006 1 commit
  14. 19 Sep, 2006 1 commit
  15. 18 Sep, 2006 3 commits
    • Steven Whitehouse's avatar
      [GFS2] Tweek unlock test in readpage() · 07903c02
      Steven Whitehouse authored
      
      
      This make the unlock test a bit simpler.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      07903c02
    • Russell Cattelan's avatar
      [GFS2] Fix for mmap() bug in readpage · dc41aeed
      Russell Cattelan authored
      
      
      Fix for Red Hat bz 205307. Don't need to lock in readpage if
      the higher level code has already grabbed the lock.
      Signed-off-by: default avatarRussell Cattelan <cattelan@redhat.com>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      dc41aeed
    • Steven Whitehouse's avatar
      [GFS2] Map multiple blocks at once where possible · 7a6bbacb
      Steven Whitehouse authored
      
      
      This is a tidy up of the GFS2 bmap code. The main change is that the
      bh is passed to gfs2_block_map allowing the flags to be set directly
      rather than having to repeat that code several times in ops_address.c.
      
      At the same time, the extent mapping code from gfs2_extent_map has
      been moved into gfs2_block_map. This allows all calls to gfs2_block_map
      to map extents in the case that no allocation is taking place. As a
      result reads and non-allocating writes should be faster. A quick test
      with postmark appears to support this.
      
      There is a limit on the number of blocks mapped in a single bmap
      call in that it will only ever map blocks which are pointed to
      from a single pointer block. So in other words, it will never try
      to do additional i/o in order to satisfy read-ahead. The maximum
      number of blocks is thus somewhat less than 512 (the GFS2 4k block
      size minus the header divided by sizeof(u64)). I've further limited
      the mapping of "normal" blocks to 32 blocks (to avoid extra work)
      since readpages() will currently read a maximum of 32 blocks ahead (128k).
      
      Some further work will probably be needed to set a suitable value
      for DIO as well, but for now thats left at the maximum 512 (see
      ops_address.c:gfs2_get_block_direct).
      
      There is probably a lot more that can be done to improve bmap for GFS2,
      but this is a good first step.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      7a6bbacb
  16. 04 Sep, 2006 3 commits
  17. 01 Sep, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Update copyright, tidy up incore.h · e9fc2aa0
      Steven Whitehouse authored
      
      
      As per comments from Jan Engelhardt <jengelh@linux01.gwdg.de> this
      updates the copyright message to say "version" in full rather than
      "v.2". Also incore.h has been updated to remove forward structure
      declarations which are not required.
      
      The gfs2_quota_lvb structure has now had endianess annotations added
      to it. Also quota.c has been updated so that we now store the
      lvb data locally in endian independant format to avoid needing
      a structure in host endianess too. As a result the endianess
      conversions are done as required at various points and thus the
      conversion routines in lvb.[ch] are no longer required. I've
      moved the one remaining constant in lvb.h thats used into lm.h
      and removed the unused lvb.[ch].
      
      I have not changed the HIF_ constants. That is left to a later patch
      which I hope will unify the gh_flags and gh_iflags fields of the
      struct gfs2_holder.
      
      Cc: Jan Engelhardt <jengelh@linux01.gwdg.de>
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      e9fc2aa0
  18. 31 Aug, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Fix releasepage bug (fixes direct i/o writes) · 623d9355
      Steven Whitehouse authored
      
      
      This patch fixes three main bugs. Firstly the direct i/o get_block
      was returning the wrong return code in certain cases. Secondly, the
      GFS2's releasepage function was not dealing with cases when clean,
      ordered buffers were found still queued on a transaction (which can
      happen depending on the ordering of journal flushes). Thirdly, the
      journaling code itself needed altering to take account of the
      after effects of removing the clean ordered buffers from the transactions
      before a journal flush.
      
      The releasepage bug did also show up under "normal" buffered i/o
      as well, so its not just a fix for direct i/o. In fact its not
      normally used in the direct i/o path at all, except when flushing
      existing buffers after performing a direct i/o write, but that was
      the code path that led us to spot this.
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      623d9355
  19. 24 Aug, 2006 1 commit
  20. 18 Aug, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Fix leak of gfs2_bufdata · 15d00c0b
      Steven Whitehouse authored
      
      
      This fixes a memory leak of struct gfs2_bufdata and also some
      problems in the ordered write handling code. It needs a bit
      more testing, but I believe that the reference counting of
      ordered write buffers should now be correct.
      
      This is aimed at fixing Red Hat bugzilla: #201028 and #201082
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      15d00c0b
  21. 08 Aug, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Fix lack of buffers in writepage bug · f4387149
      Steven Whitehouse authored
      
      
      In some cases we can enter write page without there being buffers
      attached to the page. In this case the function to add gfs2_bufdata
      to the buffers fails sliently causing further failures down the
      stack.
      
      This fix ensures that we always add buffers in writepage if they
      didn't already exist (mmap is one way to trigger this).
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      f4387149
  22. 04 Aug, 2006 1 commit
    • Steven Whitehouse's avatar
      [GFS2] Fix lock ordering bug in page fault path · 59a1cc6b
      Steven Whitehouse authored
      
      
      Mmapped files were able to trigger a lock ordering bug. Private
      maps do not need to take the glock so early on. Shared maps do
      unfortunately, however we can get around that by adding a flag
      into the flags for the struct gfs2_file. This only works because
      we are taking an exclusive lock at this point, so we know that
      nobody else can be racing with us.
      
      Fixes Red Hat bugzilla: #201196
      Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
      59a1cc6b