my requirement is as follows.
I want disable preemption on all cpus. and then call a function
with on_each_cpu(preempt_disable, NULL, 1, 1); call I dont think it will work.
is there a way to achieve it ?
I have a problem I'm hoping someone can help me with...
I have an NFS server/client setup. On the server side, I export a romfs filesystem to the NFS. The client computers boot via PXE bootloader and mount their root filesystem via NFS, using tempfs/unionfs to make parts of the filesystem read/write (i.e., /etc, /var, etc)
I´m looking for this kernel messages. I would like to know how resolve this problem. Please help me. :)
My system is: CentOS 5.4 - kernel version 2.6.18-164.el5PAE
Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
eth0: Ethernet controller: Intel Corporation 82566DC-2 Gigabit Network Connection (rev 02)
Im' trying to upgrade a Linux kernel from 2.6.18 to 2.6.30.
The machine is a HP Proliant with Intel Xeon processor double six core. The 2.6.18 kernel work fine.
When booting with the 2.6.30, the kernel can not identify more than 8 CPU and i get this message :
checking TSC synchronization [CPU#0 -> CPU#8]: passed.
And the kernel could not boot.
Please can you help me with this
We're using a lot of different kernel configurations on our servers running Gentoo Linux and Linux VServer. Kernels' configs depend on hardware and functions of every server. Every time new kernel is released and/or we need to enable/disable some features for all servers' kernels we have to update .config's manually.
I have hacked a kernel and created a module that invokes some functions from this kernel. The mods work perfectly on my workstation, but I'm having several problems on a 64bit server which runs the exactly same Linux distribution.
The distro is a Ubuntu 7.04 and the kernel is 184.108.40.206-ubuntu1.
The only difference is that my workstation is i686 and the server is x86_64.
I am trying to write a MAC driver for Arm 11 MPcore in 2.6.23. The DMA'ble memory required is supposed to be non-cached for performance reasons.
A chunk of memory(~ 6MB) is allocated at startup using bigphys area patch. This physical area in the RAM is mmap'd to userspace as follows and thereafter carved into network buffers:
fd = open("/dev/mem", O_RDWR|O_SYNC);