similar to: RE: [PATCH]Check the values of MAX_VIRT_CPUS and NR_CPUSfor SMP

>From: Tristan Gingold [mailto:Tristan.Gingold@bull.net] >Sent: 2006年4月21日 15:40 > >Le Vendredi 21 Avril 2006 09:28, Tian, Kevin a écrit : >> From: Tristan Gingold [mailto:Tristan.Gingold@bull.net] >> >> >Sent: 2006年4月21日 15:26 >> > >> >> >See how we solve this on x86 near the top of do_boot_cpu() in >> >> >arch/x86/smpboot.c.

>From: Keir Fraser >Sent: 2006年4月21日 14:41 > > >On 21 Apr 2006, at 02:31, Atsushi SAKAI wrote: > >> But the logical limit of the IA64 Max CPU is larger than 64. >> If someone change these values, some possibility make this error >again. >> >> To avoid this problem, I believe this check code should be exists. > >See how we solve this on x86 near

I''m working on a new hypercall, do_confer, which allows the directed yielding of a vcpu to another vcpu. It is mainly used when a vcpu fails to acquire a spinlock, yielding to the lock holder instead of spinning. I ported the ppc64 spinlock implementation for the i386 linux portion. In implementing the hypercall, I''ve been trying to figure out how to get the scheduler

As suggested by Andi Kleen, don't allocate a GDT page if there is already one present. Needed for CPU hotplug. Signed-off-by: Zachary Amsden <zach@vmware.com> Index: linux-2.6.14-rc1/arch/i386/kernel/smpboot.c =================================================================== --- linux-2.6.14-rc1.orig/arch/i386/kernel/smpboot.c 2005-09-20 20:38:22.000000000 -0700 +++

As suggested by Andi Kleen, don't allocate a GDT page if there is already one present. Needed for CPU hotplug. Signed-off-by: Zachary Amsden <zach@vmware.com> Index: linux-2.6.14-rc1/arch/i386/kernel/smpboot.c =================================================================== --- linux-2.6.14-rc1.orig/arch/i386/kernel/smpboot.c 2005-09-20 20:38:22.000000000 -0700 +++

# This is a BitKeeper generated diff -Nru style patch. # # ChangeSet # 2005/05/01 17:01:17-07:00 kmacy@curly.lab.netapp.com # add SMP support to evtchn # Signed-off-by: Kip Macy <kmacy@netapp.com> # # freebsd-5.3-xen-sparse/i386-xen/include/xen_intr.h # 2005/05/01 17:01:15-07:00 kmacy@curly.lab.netapp.com +3 -0 # add SMP interfaces # #

Hi, on ia64, the do_* functions for hypercalls are called in C. However, they are not declared in any .h file. I think it is cleaner to declare them in an header file rather than locally. The question is in which header file. Thank you for any suggestion. The do_* functions are at least: extern long do_ni_hypercall(void); extern long do_dom0_op(dom0_op_t *u_dom0_op); extern long

(CCed to xen-devel for completeness. ;) On Wed, 2006-08-16 at 17:24 +0200, Tristan Gingold wrote: > I am porting xen-ppc''s xencomm to xen/ia64. > Currently on xen/ia64 copy_from/to_guest uses guest virtual address. This > works well as long as the virtual addresses are in the TLB. When not in TLB > (or vTLB) the hypercall can''t success without domain help. The

Are there any examples of bvt scheduler parameters usage? If I understand it right, bvt provides me with option to scale domain''s CPU usage. Eg. I have 2 (non-zero) domains pinned to the same CPU. Can I assign eg. 30% of CPU time to domain 1 and 70% to domain 2? (I mean in peaks when both domains are not idle and require the CPU time) If yes, how should I build the "xm bvt"

On Apr 6, 2010, at 1:10 AM, Tristan Gingold wrote: > > On Apr 3, 2010, at 2:36 PM, Russell Wallace wrote: > >> On Fri, Apr 2, 2010 at 6:17 PM, Chris Lattner <clattner at apple.com> wrote: >>> No, please don't. This is something we specifically do not want to support. The issue is not the parser, the issue is that struct field offsets are no longer constant in

Hi folks BVT and EDF are both xen scheduler. It is expected that administrator will choose the scheduler most appropriate to their application and configure the machine to boot with that scheduler. I just wonder What''s the main difference between BVT and EDF? What kind of scenario to use them? Thanks _______________________________________________ Xen-tools mailing list

Hi, xencomm is the ppc infrastructure to do hypercalls with guest physical addresses instead of virtual address. Because ia64 should also use physicall address, I think it''s better to re-use the ppc code and to put into common code. I''d propose to submit this patch is every part is OK (ie no NAK). This patch creates include/xen/xencomm_access.h which is to be included by

Hello I''m in trouble using the bvt scheduler with the command line. the command "xm sched-bvt help" explain that it need 6 argument but that''s all. I have read a previous conversation for bvt example with command line, but it doesn''t work I try (5 is the id of the concerned

import include/asm-ia64/xen/interface.h to introduce introduce definitions necessary for ia64/xen hypercalls. They are basic structures to communicate with xen hypervisor and will be used later. Cc: Robin Holt <holt at sgi.com> Cc: Jeremy Fitzhardinge <jeremy at goop.org> Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> Cc: "Luck, Tony" <tony.luck at

import include/asm-ia64/xen/interface.h to introduce introduce definitions necessary for ia64/xen hypercalls. They are basic structures to communicate with xen hypervisor and will be used later. Cc: Robin Holt <holt at sgi.com> Cc: Jeremy Fitzhardinge <jeremy at goop.org> Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> Cc: "Luck, Tony" <tony.luck at

Hi, I have a naive question with the xen BVT scheduler. Supposing I have only one guest domain runnning on domain 0 and with the xm bvt command I have allocated cpu units in the ratio 9:1 to domain 0 and domain 1(say) respectively. Now I create another guest domain. How much CPU share it (or subsequent domains created after it) will get? ~$ubh _______________________________________________

Hi, on IA64 flushing the whole TLB is very expensive: this is a cpu tlb flush and clearing 16MB of memory (virtual tlb). However, flushing an address range is rather cheap. Flushing an address range on every processors is also cheap (no IPI). Unfortunatly Xen common code flushes the whole TLB after unmapping grant reference. Currently, this is not done on IA64 because domain_dirty_cpumask

Hi, I''m trying to boot up with lot more than 32 vcpus on this very large box. I overcame vcpu_info[MAX_VIRT_CPUS] by doing vcpu placement hypercall in guest, but now running into evt channel limit (lots of devices): unsigned long evtchn_pending[sizeof(unsigned long) * 8]; which limits to 512 max for my 64bit dom0. The only recourse seems to create a new struct shared_info_v2{},

Hi, taking into account Hollis comments I now submit this patch. IA64 specific stuff will be posted to xen-ia64-unstable after merge. Tristan. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

Signed-off-by: Jan Beulich <jbeulich@novell.com> Index: 2008-09-19/xen/arch/x86/platform_hypercall.c =================================================================== --- 2008-09-19.orig/xen/arch/x86/platform_hypercall.c 2008-09-19 14:12:02.000000000 +0200 +++ 2008-09-19/xen/arch/x86/platform_hypercall.c 2008-09-19 14:12:56.000000000 +0200 @@ -21,7 +21,7 @@ #include <xen/acpi.h>