 Home |
Products |
Support |
Community |
News |
xen-devel
Re: [Xen-devel] [PATCH] VMX: avoid taking locks with irqs disabled
| To: | "Tian, Kevin" <kevin.tian@xxxxxxxxx>, Tim Deegan <Tim.Deegan@xxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [Xen-devel] [PATCH] VMX: avoid taking locks with irqs disabled |
| From: | Keir Fraser <keir.fraser@xxxxxxxxxxxxx> |
| Date: | Tue, 21 Oct 2008 14:08:48 +0100 |
| Cc: | "Wei, Gang" <gang.wei@xxxxxxxxx> |
| Delivery-date: | Tue, 21 Oct 2008 06:09:12 -0700 |
| Envelope-to: | www-data@xxxxxxxxxxxxxxxxxxx |
| In-reply-to: | <D8078B8B3B09934AA9F8F2D5FB3F28CE08A6C5A921@xxxxxxxxxxxxxxxxxxxxxxxxxxxx> |
| List-help: | <mailto:xen-devel-request@lists.xensource.com?subject=help> |
| List-id: | Xen developer discussion <xen-devel.lists.xensource.com> |
| List-post: | <mailto:xen-devel@lists.xensource.com> |
| List-subscribe: | <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe> |
| List-unsubscribe: | <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe> |
| Sender: | xen-devel-bounces@xxxxxxxxxxxxxxxxxxx |
| Thread-index: | Ackym9FTECaiOJ6PEd2A7gAWy6hiGQA2pAsQAADZPOMAAAQKkAABFEDA |
| Thread-topic: | [Xen-devel] [PATCH] VMX: avoid taking locks with irqs disabled |
| User-agent: | Microsoft-Entourage/11.4.0.080122 |
On 21/10/08 13:50, "Tian, Kevin" <kevin.tian@xxxxxxxxx> wrote: > > I'm a bit curious why call funtion ipi is required here, or why > rendezvous is required here. All the rendezvous stuff in current > ipi function is just: > a) cpu0 waits for all other cpus entering rendezvous loop, and > then update master_stime > b) other cpus enter loop and wait for cpu0 to update master_stime > > Then each cpu continues with rest stuff independently. In this > case, it seems enough to just ensure master_stime updated > before sending softirq, and thus ipi is actually not required. > Do I miss anything? :-) We want to gather all timestamps as close together as possible. Dan measured that this produced vastly less system-time skew across CPUs. Hence we do all the stamp gathering in IRQ context. -- Keir _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxxxxxxxx http://lists.xensource.com/xen-devel |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | RE: [Xen-devel] [PATCH] VMX: avoid taking locks with irqs disabled, Tian, Kevin |
|---|---|
| Next by Date: | Re: [Xen-devel] HVM page table management, Emre Can Sezer |
| Previous by Thread: | RE: [Xen-devel] [PATCH] VMX: avoid taking locks with irqs disabled, Tian, Kevin |
| Next by Thread: | [Xen-devel] supervisor_mode_kernel and hypercall, Yanjun Wu |
| Indexes: | [Date] [Thread] [Top] [All Lists] |
