[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <52CAF8BD.90201@arm.com>
Date: Mon, 06 Jan 2014 18:41:01 +0000
From: Dietmar Eggemann <dietmar.eggemann@....com>
To: Peter Zijlstra <peterz@...radead.org>
CC: "mingo@...hat.com" <mingo@...hat.com>,
"vincent.guittot@...aro.org" <vincent.guittot@...aro.org>,
Morten Rasmussen <Morten.Rasmussen@....com>,
Chris Redpath <Chris.Redpath@....com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH 5/8] sched: introduce common topology level init function
On 20/12/13 14:04, Peter Zijlstra wrote:
>> +/*
>> + * SD_flags allowed in topology descriptions.
>> + *
>> + * SD_SHARE_CPUPOWER - describes SMT topologies
>> + * SD_SHARE_PKG_RESOURCES - describes shared caches
>> + * SD_NUMA - describes NUMA topologies
>> + *
>> + * Odd one out:
>> + * SD_ASYM_PACKING - describes SMT quirks
>> + *
>> + * SD_PREFER_SIBLING - describes preference for sibling domain
>> + */
>> +#define TOPOLOGY_SD_FLAGS \
>> + (SD_SHARE_CPUPOWER | \
>> + SD_SHARE_PKG_RESOURCES | \
>> + SD_NUMA | \
>> + SD_ASYM_PACKING | \
>> + SD_PREFER_SIBLING)
>
> See SD_PREFER_SIBLING is behavioural, the exact kinda thing we want to
> keep out of this mask,
Understood.
Since this flag is only set for the CPU level, it will only effect the
first NUMA level because sd->child has to have this flag set.
Unfortunately, I don't have a NUMA system.
AFAICS, we get some level of packing in sd->parent when this flag is set.
-- Dietmar
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists