Doug / smarc-fsl-linux-kernel

10 Oct, 2007

1 commit

15 Jul, 2007

2 commits

  • 9523a841b   9p: cache meta-data when cache=loose ... Browse Code »

    This patch expands the impact of the loose cache mode to allow for cached
    metadata increasing the performance of directory listings and other metadata
    read operations.

    Signed-off-by: Eric Van Hensbergen

    Eric Van Hensbergen
     
  • bd238fb43   9p: Reorganization of 9p file system code ... Browse Code »

    This patchset moves non-filesystem interfaces of v9fs from fs/9p to net/9p.
    It moves the transport, packet marshalling and connection layers to net/9p
    leaving only the VFS related files in fs/9p. This work is being done in
    preparation for in-kernel 9p servers as well as alternate 9p clients (other
    than VFS).

    Signed-off-by: Latchesar Ionkov
    Signed-off-by: Eric Van Hensbergen

    Latchesar Ionkov
     

09 May, 2007

1 commit

27 Mar, 2007

1 commit

19 Feb, 2007

1 commit

  • e03abc0c9   9p: implement optional loose read cache ... Browse Code »

    While cacheing is generally frowned upon in the 9p world, it has its
    place -- particularly in situations where the remote file system is
    exclusive and/or read-only. The vacfs views of venti content addressable
    store are a real-world instance of such a situation. To facilitate higher
    performance for these workloads (and eventually use the fscache patches),
    we have enabled a "loose" cache mode which does not attempt to maintain
    any form of consistency on the page-cache or dcache. This results in over
    two orders of magnitude performance improvement for cacheable block reads
    in the Bonnie benchmark. The more aggressive use of the dcache also seems
    to improve metadata operational performance.

    Signed-off-by: Eric Van Hensbergen

    Eric Van Hensbergen
     

12 Feb, 2007

1 commit

27 Jan, 2007

1 commit

09 Dec, 2006

1 commit

04 Dec, 2006

1 commit

01 Jul, 2006

1 commit

16 May, 2006

1 commit

  • 41e5a6ac8   [PATCH] v9fs: signal handling fixes ... Browse Code »

    Multiple races can happen when v9fs is interrupted by a signal and Tflush
    message is sent to the server. After v9fs sends Tflush it doesn't wait
    until it receives Rflush, and possibly the response of the original
    message. This behavior may confuse v9fs what fids are allocated by the
    file server.

    This patch fixes the races and the fid allocation.

    Signed-off-by: Latchesar Ionkov
    Cc: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Latchesar Ionkov
     

29 Mar, 2006

1 commit

  • 4b6f5d20b   [PATCH] Make most file operations structs in fs/ const ... Browse Code »

    This is a conversion to make the various file_operations structs in fs/
    const. Basically a regexp job, with a few manual fixups

    The goal is both to increase correctness (harder to accidentally write to
    shared datastructures) and reducing the false sharing of cachelines with
    things that get dirty in .data (while .rodata is nicely read only and thus
    cache clean)

    Signed-off-by: Arjan van de Ven
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Arjan van de Ven
     

26 Mar, 2006

2 commits

  • 42e8c509c   [PATCH] v9fs: update license boilerplate ... Browse Code »

    Update license boilerplate to specify GPLv2 and remove the (at your option
    clause). This change was agreed to by all the copyright holders (approvals
    can be found on v9fs-developer mailing list).

    Signed-off-by: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Eric Van Hensbergen
     
  • 16cce6d27   [PATCH] v9fs: add extension field to Tcreate ... Browse Code »

    Implement a new way of creating special files. Instead of Tcreate+Twstat,
    add one more field to Tcreate that contains special file description.

    Signed-off-by: Latchesar Ionkov
    Signed-off-by: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Latchesar Ionkov
     

03 Mar, 2006

1 commit

  • 6a3124a39   [PATCH] v9fs: fix atomic create open ... Browse Code »

    In order to assure atomic create+open v9fs stores the open fid produced by
    v9fs_vfs_create in the dentry, from where v9fs_file_open retrieves it and
    associates it with the open file.

    This patch modifies v9fs to use nameidata.intent.open values to do the atomic
    create+open.

    Signed-off-by: Latchesar Ionkov
    Signed-off-by: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Latchesar Ionkov
     

19 Jan, 2006

1 commit

  • 147b31cf0   [PATCH] v9fs: add readpage support ... Browse Code »

    v9fs mmap support was originally removed from v9fs at Al Viro's request,
    but recently there have been requests from folks who want readpage
    functionality (primarily to enable execution of files mounted via 9P).
    This patch adds readpage support (but not writepage which contained most of
    the objectionable code). It passes fsx-linux (and other regressions) so it
    should be relatively safe.

    Signed-off-by: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Eric Van Hensbergen
     

09 Jan, 2006

2 commits

  • 531b1094b   [PATCH] v9fs: zero copy implementation ... Browse Code »

    Performance enhancement reducing the number of copies in the data and
    stat paths.

    Signed-off-by: Latchesar Ionkov
    Cc: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Latchesar Ionkov
     
  • 28fd12982   [PATCH] Fix and add EXPORT_SYMBOL(filemap_write_and_wait) ... Browse Code »

    This patch add EXPORT_SYMBOL(filemap_write_and_wait) and use it.

    See mm/filemap.c:

    And changes the filemap_write_and_wait() and filemap_write_and_wait_range().

    Current filemap_write_and_wait() doesn't wait if filemap_fdatawrite()
    returns error. However, even if filemap_fdatawrite() returned an
    error, it may have submitted the partially data pages to the device.
    (e.g. in the case of -ENOSPC)

    Andrew Morton writes,

    If filemap_fdatawrite() returns an error, this might be due to some
    I/O problem: dead disk, unplugged cable, etc. Given the generally
    crappy quality of the kernel's handling of such exceptions, there's a
    good chance that the filemap_fdatawait() will get stuck in D state
    forever.

    So, this patch doesn't wait if filemap_fdatawrite() returns the -EIO.

    Trond, could you please review the nfs part? Especially I'm not sure,
    nfs must use the "filemap_fdatawrite(inode->i_mapping) == 0", or not.

    Acked-by: Trond Myklebust
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    OGAWA Hirofumi
     

09 Nov, 2005

1 commit

  • 733482e44   [PATCH] changing CONFIG_LOCALVERSION rebuilds too much, for no good reason ... Browse Code »

    This patch removes almost all inclusions of linux/version.h. The 3
    #defines are unused in most of the touched files.

    A few drivers use the simple KERNEL_VERSION(a,b,c) macro, which is
    unfortunatly in linux/version.h.

    There are also lots of #ifdef for long obsolete kernels, this was not
    touched. In a few places, the linux/version.h include was move to where
    the LINUX_VERSION_CODE was used.

    quilt vi `find * -type f -name "*.[ch]"|xargs grep -El '(UTS_RELEASE|LINUX_VERSION_CODE|KERNEL_VERSION|linux/version.h)'|grep -Ev '(/(boot|coda|drm)/|~$)'`

    search pattern:
    /UTS_RELEASE\|LINUX_VERSION_CODE\|KERNEL_VERSION\|linux\/\(utsname\|version\).h

    Signed-off-by: Olaf Hering
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Olaf Hering
     

12 Oct, 2005

1 commit

  • 19cba8abd   [PATCH] v9fs: remove additional buffer allocation from v9fs_file_read and v9fs_file_write ... Browse Code »

    v9fs_file_read and v9fs_file_write use kmalloc to allocate buffers as big
    as the data buffer received as parameter. kmalloc cannot be used to
    allocate buffers bigger than 128K, so reading/writing data in chunks bigger
    than 128k fails.

    This patch reorganizes v9fs_file_read and v9fs_file_write to allocate only
    buffers as big as the maximum data that can be sent in one 9P message.

    Signed-off-by: Latchesar Ionkov
    Cc: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Latchesar Ionkov
     

28 Sep, 2005

1 commit

  • 0b8dd1776   [PATCH] v9fs: fix races in fid allocation ... Browse Code »

    Fid management cleanup. The patch attempts to fix the races in dentry's
    fid management.

    Dentries don't keep the opened fids anymore, they are moved to the file
    structs. Ideally there should be no more than one fid with fidcreate equal
    to zero in the dentry's list of fids.

    v9fs_fid_create initializes the important fields (fid, fidcreated) before
    v9fs_fid is added to the list. v9fs_fid_lookup returns only fids that are
    not created by v9fs_create. v9fs_fid_get_created returns the fid created
    by the same process by v9fs_create (if any) and removes it from dentry's
    list

    Signed-off-by: Latchesar Ionkov
    Cc: Eric Van Hensbergen
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    Latchesar Ionkov
     

10 Sep, 2005

1 commit