Re: Intel G33 chipset with Linux - correction

Aragorn wrote:

[...]

Although this may not be related to your specific problem - I don't even
know what kernel you're running - there appears to be a patch to the SLUB
allocator in the 2.6.24.x generation of kernels which greatly slows down
multi-CPU machines. The patch has been reverted for the experimental
2.6.15-rc2 kernel, so chances are that the slightly older 2.6.23.x kernel
or an eventual upcoming 2.6.24.3 will have this fixed as well.

Oops, the experimental kernel mentioned there would of course be 2.6.25-rc2.
Typo, my mistake. ;-)

--
Aragorn
(registered GNU/Linux user #223157)
.

Relevant Pages

  • Re: [RFC PATCH] block: Fix bio merge induced high I/O latency
    ... On a 2.6.29-rc3 kernel. ... I get the following OOPS just after I start ... that the type of request (sync vs!sync) changes would not be taken care ... Just ignore the patch for now, I'm not going to be spending more time on ...
    (Linux-Kernel)
  • Re: RT patch acceptance
    ... judge the complexity of a design for that type of system. ... claim that you cannot judge the complexity of a kernel modification. ... Since the patch in question doesn't actually need that information to ... nanokernel's API up to date with additions to Linux's API that RT people ...
    (Linux-Kernel)
  • Re: 2.6.0-test8-mm1
    ... > Btw. a similar Oops at the same place occours when the uhci-hcd module is ... > The attached patch prevents the kernel from Oopsing, ... WARN_ONso we'd get a stack trace in addition to the printk). ... Unable to handle kernel NULL pointer dereference at virtual address ...
    (Linux-Kernel)
  • Re: inline asm semantics: output constraint width smaller than input
    ... Now in this case the patch you suggest might end up hurting the end result ... The below patch is to build the kernel for x86_64, ... # Device Drivers ... # PCI IDE chipsets support ...
    (Linux-Kernel)
  • [RFC] Making percpu module variables have their own memory.
    ... Someone using the -rt patch found that one of the tracing options caused ... 64K for every CPU to cover all the per_cpu variables used in the kernel ... static void wakeup_softirqd_prio ...
    (Linux-Kernel)