similar to: [PATCH] nr_cpus calculation problem due to incorrect sockets_per_node

Once Xen calculates nr_nodes properly, all nr_cpu calculations based on nr_nodes * sockets_per_node * cores_per_socket * threads_per_core are broken. The easy fix is to replace those calculations with a new field, nr_cpus in physinfo which is calculated by num_online_cpus(). This patch does so and attempts to change all users over to nr_cpus field in physinfo. This patch touches

This patch modifies the physinfo hcall to export NUMA CPU and Memory topology information. The new physinfo hcall is integrated into libxc and xend (xm info specifically). Included in this patch is a minor tweak to xm-test''s xm info testcase. The new fields in xm info are: nr_nodes : 4 mem_chunks : node0:0x0000000000000000-0x0000000190000000

This patch makes "xm info" show information on xen version, compile info, number of socket/core, etc... In order to do that, it extends physinfo hypercall to return number of socket, adds few functions to libxc and extends python wrapper correspondingly. Here is the output of new "xm info": -- system : Linux host : ubuntu xen_release

The patchset will add basic NUMA support to Xen (hypervisor only). We borrowed from Linux support for NUMA SRAT table parsing, discontiguous memory tracking (mem chunks), and cpu support (node_to_cpumask etc). The hypervisor parses the SRAT tables and constructs mappings for each node such as node to cpu mappings and memory range to node mappings. Using this information, we also modified the

The series introduces auto-generation of the type definitions used in the libxl interface followed by auto-generation of a destructor function for each type. In the future it may be possible to use the related data structures for other purposes, for example auto-generation of the functions to marshal between C and language binding data types. tools/_libxl_types.h should be identical both before

Please CC as I''m not subscribed to valgrind-developers. Under Xen the toolstack is responsible for managing the domains in the system, e.g. creating, destroying, and otherwise manipulating them. To do this it uses a number of ioctls on the /proc/xen/privcmd device. Most of these (the MMAPBATCH ones) simply set things up such that a subsequenct mmap call will map the desired guest

Hi, (please let me know if there is a better place to submit bugs) I run a FreeBSD box with stack-protector enabled, which raises a problem in the upsdrv_initups() function of the newhidups.c module; the regex_array variable is sized one item too small. Regards, Herve Masson <<<< void upsdrv_initups(void) { int i; #ifndef SHUT_MODE /*! * SHUT is only supported by

Hello, I am encountering a linking failure when using Control Flow Integrity while building a shared library. It looks like the wrong relocation type is being emitted for functions referenced via the PLT. I am using clang 3.9. The error message I get is: /usr/bin/ld.gold: error: /tmp/lto-llvm-df723d.o: requires dynamic R_X86_64_PC32 reloc against 'free' which may overflow at runtime;

Hello all,will_paginate don''t work on jruby platform, the Model.paginate find works ok, accepts all kinds of params, this is config.gem config.gem ''will_paginate'', :version => ''2.3.11'', :source => ''http://gemcutter.org'', but <%= will_paginate @collection %> doesn''t work it always produce nil(so nothing on page).

# HG changeset patch # User john.levon@sun.com # Date 1155596263 -3600 # Node ID dc12f0942649ee27ff2aec3e3d9c2d99746b9e58 # Parent 09bc238664cb7b6d0f960f5e135ac80a75b342f1 Remove another external-to-libxc user of xc_dom0_op(). Signed-off-by: John Levon <john.levon@sun.com> diff -r 09bc238664cb -r dc12f0942649 tools/xenmon/xenbaked.c --- a/tools/xenmon/xenbaked.c Mon Aug 14 15:40:36 2006

xc_dom_alloc_segment requires start address to be page align. Signed-off-by: Julien Grall <julien.grall@linaro.org> --- tools/libxc/xc_dom_arm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/libxc/xc_dom_arm.c b/tools/libxc/xc_dom_arm.c index ffe575b..366061d 100644 --- a/tools/libxc/xc_dom_arm.c +++ b/tools/libxc/xc_dom_arm.c @@ -290,6 +290,8 @@ int

The following dump-core patches changes its format into ELF, adds PFN-GMFN table, HVM support, and adds experimental IA64 support. - ELF format Program header and note section are adopted. - HVM domain support To know the memory area to dump, XENMEM_set_memory_map is added. XENMEM_memory_map hypercall is for current domain, so new one is created. and hvm domain builder tell xen its

Modify the cpufreq ondemand governor so that it can get idle and total ticks from the Xen hypervisor. Linux and Xen have different ideas of what an idle tick is, so the Xen values for both have to be returned in the same platform hypercall. Signed-off-by: Mark Langsdorf <mark.langsdorf@amd.com> diff -r b4278beaf354 xen/arch/x86/platform_hypercall.c --- a/xen/arch/x86/platform_hypercall.c

Hello, I am just installing XCP 0.1.1 on a server with 24GB RAM Normally XCP is a 64 bits version but * *uname -a* Linux node012 2.6.27.42-0.1.1.xs0.1.1.737.1065xen #1 SMP Fri Jan 15 16:20:16 EST 2010 i686 i686 i386 GNU/Linux (not a x86_64 version !!!!) * *cat /proc/meminfo* MemTotal: 746496 kB MemFree: 384332 kB Buffers:

is it possible to pass parameters from a .cfg file to the newly booted kernel? my setup is pxelinux where the relevent config is label fbsd63 kernel memdisk append initrd=/freebsd6.3.hd harddisk what i would like to do is pass in some parameter so the booted kernel can behave differently. i've looked in teh archives without success, although i did see an elliptic reference to

Hi, I''m trying to get parallelized ferret indexing working for my AAF indices, based on the example in the O''Reilly Ferret shortcut. However, the resulting indices after merging seem to have no actual documents. I went and made minimal changes to the example in the Ferret shortcut pdf, and indeed can''t get that to work either. I''d appreciate any help

This patch introduces a handful of new options, I mentioned earlier in: http://www.mail-archive.com/nut-upsdev at lists.alioth.debian.org/msg02088.html See the large commit message in the follow-up for the details and rationale. I realize it's a bit larger diff - so if it's required I can split it into few smaller ones. Michal Soltys (1): APC smart driver update and new features.

This patch adds a per-node bucket to the heap structure in Xen. During heap initialization the patch determines which bucket to place the memory. We reserve guard pages between node boundaries in the case that said boundary isn''t already guarded by the MAX_ORDER boundary to prevent the buddy allocator from merging pages between nodes. -- Ryan Harper Software Engineer; Linux Technology

Hello, Earlier this week I installed a test server with CentOS 5.6 with Virtualization enabled during the installer. Today I installed another server using the same method (they are identical servers). I just did a yum update and I found something curious. Both servers have a different kernel. Server 1 is at 9.1 version and server 2 at 5.1. How can this be? How to I get the latest version on

I got really strange situation with memory on host: xe host-list params=memory-free memory-free ( RO) : 10305536 (10Mb) xe host-compute-free-memory 3147059200 (3Gb) A huge difference! And xentop show different numbers too! I will keep this host online "as is" and I am ready to provide information for debbugging or perform needed actions. -- wBR,George.