Patch for CIFS vfs client

From: Nitin (nitin_gupta_mail_at_hotmail.com)
Date: 01/31/05

  • Next message: Parag Warudkar: "Re: [PATCH] ohci1394: dma_pool_destroy while in_atomic() && irqs_disabled()" 
    To: <linux-kernel@vger.kernel.org>
Date:	Mon, 31 Jan 2005 06:46:17 +0530

    This is the patch for CIFS ver 1.22 (included with linux-2.6.8)
    This improves cifs vfs client file read performance by 10-15%.

    Changes were made only to a single file in cifs tree
    (/usr/src/linux/fs/cifs/file.c)

    The function cifs_readpages() is modifed and cifs_readpages_threadfn() has
    been added.
     
    It implements sending back-to-back multiple read requests using single
    connection stream.

    To use it, replace existing file.c file with this file (as attachment)

    Still to do --
    -- submit multiple read requests in parallel using _multiple connections_
    -- dynamically control no. of threads operating depending on server response
    time

    I have tested it to be quite stable.

    Please give test results and comments to --

    nitin_gupta_mail@hotmail.com
    Nitin Gupta

    Thanks

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Parag Warudkar: "Re: [PATCH] ohci1394: dma_pool_destroy while in_atomic() && irqs_disabled()"

    Relevant Pages

    • Patch for CIFS vfs
      ... This is the patch for CIFS ver 1.22. ... Current implementation sends a read request to server and waits for data to ... It is implemented by starting multiple threads with each one sending a read ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [2.6.12-rc1-mm3] BUG: atomic counter underflow in smbfs
      ... problem - often it's fairly harmless. ... Did the filesytem misbehave in any ... cifs", but for some reason that doesn't seem to be happening. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • RE: [PATCH] Allow cluster-wide flock
      ... NFS currently has a test in nfs_lockthat causes it to return -ENOLCK ... but we need an interim solution that ... Any comment on the effects on CIFS, ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: CIFS improvements/wider testing needed
      ... >>Make sure that you let me know if your cat example works when mounted ... so I can see what cifs thinks the owner of the file is and the mode. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: New maintainer needed for the Linux smb filesystem
      ... > success trying to reach him, it seems we need a new maintainer for the ... I was hoping that by now we could simply deprecate smbfs and tell people to ... use CIFS, but I'm not sure that CIFS is ready for that yet. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)