Re: [PATCH v2 2/7] sched: rework of sched_domain topology definition

From: Dietmar Eggemann
Date: Wed Mar 19 2014 - 09:46:55 EST


On 19/03/14 12:41, Peter Zijlstra wrote:
>
> The keyboard deity gave us delete, please apply graciously when replying
> to large emails.

Sorry about that, will do next time.

>
> On Wed, Mar 19, 2014 at 11:27:12AM +0000, Dietmar Eggemann wrote:
>> On 18/03/14 17:56, Vincent Guittot wrote:
>>> + if (sd->flags & SD_SHARE_CPUPOWER) {
>>> + sd->imbalance_pct = 110;
>>> + sd->smt_gain = 1178; /* ~15% */
>>> + sd->flags |= arch_sd_sibling_asym_packing();
>>> +
>>> + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
>>> + sd->imbalance_pct = 117;
>>> + sd->cache_nice_tries = 1;
>>> + sd->busy_idx = 2;
>>> +
>>> +#ifdef CONFIG_NUMA
>>> + } else if (sd->flags & SD_NUMA) {
>>> + sd->cache_nice_tries = 2;
>>> + sd->busy_idx = 3;
>>> + sd->idle_idx = 2;
>>> +
>>> + sd->flags |= SD_SERIALIZE;
>>> + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
>>> + sd->flags &= ~(SD_BALANCE_EXEC |
>>> + SD_BALANCE_FORK |
>>> + SD_WAKE_AFFINE);
>>> + }
>>> +
>>> +#endif
>>> + } else {
>>> + sd->flags |= SD_PREFER_SIBLING;
>>> + sd->cache_nice_tries = 1;
>>> + sd->busy_idx = 2;
>>> + sd->idle_idx = 1;
>>> + }
>>
>> This 'if ... else statement' is still a weak point from the perspective
>> of making the code robust:
>
> <snip>
>
>> Is there a way to check that MC and GMC have to have
>> SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?
>
> So from the core codes perspective those names mean less than nothing.
> Its just a string to carry along for us meat-bags. The string isn't even
> there when !SCHED_DEBUG.
>
> So from this codes POV you told it it had a domain without PKGSHARE,
> that's fine.

I see your point. So what we want to avoid is to enable archs to create
different (per-cpu) set-ups inside a domain (as a specific set of cpu's
from a viewpoint of a cpu) but misconfiguration of the whole domain is a
different story. Got it!

>
> That said; yeah the thing isn't the prettiest piece of code. But it has
> the big advantage of being the one place where we convert topology into
> behaviour.
>


--
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/