[lkml]   [2011]   [Jun]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    Patch in this message
    Subject[PATCH 11/12] vfs: increase shrinker batch size
    From: Dave Chinner <>

    Now that the per-sb shrinker is responsible for shrinking 2 or more
    caches, increase the batch size to keep econmies of scale for
    shrinking each cache. Increase the shrinker batch size to 1024

    To allow for a large increase in batch size, add a conditional
    reschedule to prune_icache_sb() so that we don't hold the LRU spin
    lock for too long. This mirrors the behaviour of the
    __shrink_dcache_sb(), and allows us to increase the batch size
    without needing to worry about problems caused by long lock hold

    To ensure that filesystems using the per-sb shrinker callouts don't
    cause problems, document that the object freeing method must
    reschedule appropriately inside loops.

    Signed-off-by: Dave Chinner <>
    Documentation/filesystems/vfs.txt | 5 +++++
    fs/super.c | 1 +
    2 files changed, 6 insertions(+), 0 deletions(-)

    diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
    index dc732d2..2e26973 100644
    --- a/Documentation/filesystems/vfs.txt
    +++ b/Documentation/filesystems/vfs.txt
    @@ -317,6 +317,11 @@ or bottom half).
    the VM is trying to reclaim under GFP_NOFS conditions, hence this
    method does not need to handle that situation itself.

    + Implementations must include conditional reschedule calls inside any
    + scanning loop that is done. This allows the VFS to determine
    + appropriate scan batch sizes without having to worry about whether
    + implementations will cause holdoff problems due ot large batch sizes.
    Whoever sets up the inode is responsible for filling in the "i_op" field. This
    is a pointer to a "struct inode_operations" which describes the methods that
    can be performed on individual inodes.
    diff --git a/fs/super.c b/fs/super.c
    index b55f968..323a63e 100644
    --- a/fs/super.c
    +++ b/fs/super.c
    @@ -184,6 +184,7 @@ static struct super_block *alloc_super(struct file_system_type *type)

    s->s_shrink.seeks = DEFAULT_SEEKS;
    s->s_shrink.shrink = prune_super;
    + s->s_shrink.batch = 1024;
    return s;

     \ /
      Last update: 2011-06-02 09:05    [W:0.021 / U:43.328 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site