RE: [Lhms-devel] RE: memory hotremove prototype, take 3

From: Perez-Gonzalez, Inaky (inaky.perez-gonzalez_at_intel.com)
Date: 12/04/03

  • Next message: fengxj: "system() return different value under 2.4.23 and 2.6.0-test11" 
    Date:	Wed, 3 Dec 2003 20:59:04 -0800
To: "Yasunori Goto" <ygoto@fsw.fujitsu.com>

    > -----Original Message-----
    > From: linux-kernel-owner@vger.kernel.org [mailto:linux-kernel-owner@vger.kernel.org] On Behalf Of Yasunori Goto
    > Sent: Wednesday, December 03, 2003 1:23 PM
    > To: Perez-Gonzalez, Inaky
    > Cc: Pavel Machek; linux-kernel@vger.kernel.org; Luck, Tony; IWAMOTO Toshihiro; Hirokazu Takahashi; Linux Hotplug Memory Support
    > Subject: Re: [Lhms-devel] RE: memory hotremove prototype, take 3
    >
    >
    > > > IMHO, To hot-remove memory, memory attribute should be divided
    > > > into Hotpluggable and no-Hotpluggable, and each attribute memory
    > > > should be allocated each unit(ex. node).
    > >
    > > Why? I still don't get that -- we should be able to use the virtual
    > > addressing mechanism of any CPU to swap under the rug any virtual
    > > address without needing to do anything more than allocate a page frame
    > > for the new physical location
    >
    > My understanding is that the kernel and device drivers sometimes
    > assume physical memory address is not changed.
    > For example, IA32 kernel often uses __PAGE_OFFSET.
    > I suppose that there are many case which the kernel and device drivers
    > assume physical address is not changed like this.
    > Even if we use Mr. Iwamoto's method use, some memories will remain.

    Grrrr ... my concern is that Murphy's Law says that we'll need to hotplug
    the memory that we cannot in most of the cases (pray not). I guess I will
    need to research some more to think how to do it.

    I still think we could use the CPU's virtualization mechanism--of course,
    and as you and Tony Luck mention, we'd had to track down and modify the
    parts that assume physical memory et al. That they use large pages or
    not doesn't seem to be such a big problem (other than allocating a bigger
    chunk for transfer) and that performance wise, it'd take longer to
    do _that_ part, but still I prefer it to taking the machine down.

    Iñaky Pérez-González -- Not speaking for Intel -- all opinions are my own (and my fault)
    -
    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: fengxj: "system() return different value under 2.4.23 and 2.6.0-test11"

    Relevant Pages

    • Re: Is there a maximum contiguous memory allocation?
      ... but could ALLOCATE it! ... do a simple allocation. ... the amount of physical memory I have installed. ... Would Windows arbitrarily ...
      (microsoft.public.vc.mfc)
    • Re: Kernel: /dev/ram1 (rd.c) not releasing unused memory automatically any more?
      ... >> does not allocate physical memory at allocation time. ... disk never gets to see the writes to buffers that are aimed at the IDE ...
      (comp.os.linux.misc)
    • Re: variables in memory
      ... > If I declare a variable, will the system allocate physical memory for ... physical memory is only allocated the first time you access a variable. ...
      (comp.os.linux.development.apps)
    • Re: AllocateCommonBuffer slow on AMD Opteron
      ... physical memory is too fragmented at the time you allocate the buffer. ... suballocate my contiguous memory from that slab. ...
      (microsoft.public.development.device.drivers)
    • Oracle memory allocation on Linux 2.6
      ... With the latest Linux kernels, things have gotten hard to tune ... regarding the SGA/PGA we can allocate. ... SGA locking is not possible (or rather not advised by Oracle ... support) and it is really difficult to check how much physical memory ...
      (comp.databases.oracle.server)