xen-devel

[Top] [All Lists]

Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck

from [Jan Beulich]

[Permanent Link][Original]

To:	"Dan Magenheimer" <dan.magenheimer@xxxxxxxxxx>
Subject:	Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck
From:	"Jan Beulich" <jbeulich@xxxxxxxxxx>
Date:	Fri, 20 Mar 2009 08:30:22 +0000
Cc:	"Xen-Devel \(E-mail\)" <xen-devel@xxxxxxxxxxxxxxxxxxx>
Delivery-date:	Fri, 20 Mar 2009 01:36:03 -0700
Envelope-to:	www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to:	<9dff6961-7b13-4447-af9c-f51deef21882@default>
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>
References:	<9dff6961-7b13-4447-af9c-f51deef21882@default>
Sender:	xen-devel-bounces@xxxxxxxxxxxxxxxxxxx

>>> Dan Magenheimer <dan.magenheimer@xxxxxxxxxx> 19.03.09 18:52 >>>
>In per-cpu, I would allocate at system initialization one
>pair of buffers for each cpu (question: num_present_cpus,
>num_online_cpus, or num_possible_cpus?).  Then no lock
>is required.

It should certainly be num_possible_cpus(), which (hopefully) is identical to
num_present_cpus() until physical CPU hotplug gets supported, in which
case some infrastructure will need to be added anyway so that your and
other code could do such per-CPU allocations on demand.

Other than Keir suggested, I'd not recommend adding further NR_CPUS
sized arrays (based mostly on how long it took to mostly (fully?) get rid of
them in Linux in order to support huge systems) - just use per-CPU pointers
to dynamically allocated memory.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

[More with this subject...]

<Prev in Thread]	Current Thread	[Next in Thread>
[Xen-devel] [RFO] #2: removing a concurrency bottleneck, Dan Magenheimer Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck, Keir Fraser Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck, Jan Beulich <= Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck, Keir Fraser

Previous by Date:	Re: [Xen-devel] [PATCH] Fix domheap structure allocation when NUMA=on, Yang, Xiaowei
Next by Date:	Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck, Keir Fraser
Previous by Thread:	Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck, Keir Fraser
Next by Thread:	Re: [Xen-devel] [RFO] #2: removing a concurrency bottleneck, Keir Fraser
Indexes:	[Date] [Thread] [Top] [All Lists]