Page 1 of 2 12 LastLast
Results 1 to 10 of 14

Thread: CleanCache Merged Into The Linux Kernel

  1. #1
    Join Date
    Jan 2007
    Posts
    14,340

    Default CleanCache Merged Into The Linux Kernel

    Phoronix: CleanCache Merged Into The Linux Kernel For File-Systems

    While the first Phoronix benchmarks of EXT4, Btrfs, and XFS on the Linux 2.6.39 kernel were just published this morning, an interesting change was just made for the next Linux kernel that will affect many of the file-systems living within the kernel. For what will be the Linux 2.6.40 kernel, or rather the Linux 3.0 kernel is the finally-merged support for CleanCache...

    http://www.phoronix.com/vr.php?view=OTQ5Mw

  2. #2
    Join Date
    Sep 2009
    Posts
    20

    Default

    If it's not addressable by the kernel (doesn't live in memory), and it's fast enough to be worth using a cache (doesn't live on the disk)... where, exactly, do the contents of the cache live?

  3. #3
    Join Date
    Aug 2009
    Posts
    2,264

    Default

    Quote Originally Posted by illissius View Post
    If it's not addressable by the kernel (doesn't live in memory), and it's fast enough to be worth using a cache (doesn't live on the disk)... where, exactly, do the contents of the cache live?
    Virtualized Windows 7 and Fedora 15 on a Dell PC with 4GB RAM;
    NT: "Hey I have 2 GB of RAM! I can't function properly because I suck!"
    Linux: "Wow 2GB of RAM? Yummy!"
    Physical RAM: "Why am I being raped?"

    Now cleancache does not live in NT's nor Linux' idea of RAM (virtual) or disk (virtual), but the actual pysical RAM, called the Transcendant Memory.

    NT is being pissed of by having slow RAM (they think) and Linux likes its (non existent) 2GB. NT and Linux try to manage their RAM, while the actual Dell RAM and HDD is being raped by two conflicting 'efficient' techniques that both NT and Linux think they are doing, not realizing that they are not realy managing it.

    Cleancache is a sort of conflict solver and RAM and HDD gangbang protector

  4. #4
    Join Date
    Sep 2009
    Posts
    20

    Default

    Ah, it's a virtualization thing. Makes sense.

  5. #5
    Join Date
    Aug 2009
    Posts
    2,264

    Default

    Quote Originally Posted by illissius View Post
    Ah, it's a virtualization thing. Makes sense.
    Yeah I was at first confused and then let down too

  6. #6
    Join Date
    Dec 2010
    Posts
    18

    Default

    It's not just for virtualization, it sounds like it's a generic interface for different backends that can provide cache-like services.

    For example: Nitin Gupta (of compcache and ramzswap fame) is implementing
    an in-kernel compression "backend" for cleancache; some believe
    cleancache will be a very nice interface for building RAM-like functionality
    for pseudo-RAM devices such as SSD or phase-change memory; and a Pune
    University team is looking at a backend for virtio (see OLS'2010).
    The doc is in the kernel tree: http://git.kernel.org/?p=linux/kerne...d8a536;hb=HEAD

  7. #7
    Join Date
    Jul 2009
    Posts
    240

    Default

    so if i get it right there are 2 possibilities of hardly noticing changes...
    1. few RAM
    2. SSD
    right?

  8. #8
    Join Date
    Feb 2008
    Posts
    52

    Default

    Also, this is a clean way to use excess video card memory.

  9. #9
    Join Date
    Jun 2008
    Location
    Perth, Scotland
    Posts
    435

    Default

    When would you use this over fscache/cachefilesd that was added to the kernel not so long ago? Or is it very different?

  10. #10
    Join Date
    Aug 2009
    Posts
    42

    Default

    This is more like anti-crash scenario, this would definitely help servers, if data can't be reached when required than system stuck and crash eventually on massive data overflow, did i get this right.

Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •