Re: [RFC PATCH 5/8] sched: introduce common topology level init function

[Dietmar Eggemann]

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@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/