lkml.org 
[lkml]   [2022]   [May]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH V2] arch_topology: support parsing cluster_id from DT
From
On 12/05/2022 16:17, Sudeep Holla wrote:
> On Wed, May 11, 2022 at 02:52:56AM -0700, Qing Wang wrote:
>> From: Wang Qing <wangqing@vivo.com>
>>
>> Use nested cluster structures in DT to support describing multi-level
>> cluster topologies and increase the parsing of nested cluster.
>>
>> Notice: the clusters describing in DT currently are not physical
>> boundaries, since changing "cluster" to "socket" is too involved and error
>> prone, this patch will not have any effect on one-level cluster topo, but
>> can support the mutil-level cluster topo to support CLUSTER_SCHED.
>
> Sorry the socket/package_id is broken. If we are playing with cluster_id
> which is now wrongly presented as package_id, you are forced to fix that
> too. We don't want to break that in a different way or leave that as is
> since the cluster_id and package ids now show up as same now. Earlier the
> cluster_id was -1.

We can leave package_id=0 (and maybe add socket parsing later) and use
llc_id instead. Like some Arm server do via ACPI. This will leave
cluster_id for Armv9 L2 sharing. cluster_id is also used in servers for
2. level "clustering", e.g. Kunpeng920 L3-tags or Ampere Altra's SCU
boundaries.

This way we can achieve both. (1) not use package_id for cluster and (2)
have cluster_id available for 2. level cluster.

I just send out a lightly tested RFC:

https://lkml.kernel.org/r/20220513083400.343706-1-dietmar.eggemann@arm.com

>
> I had a look when I started reviewing your patch. Assuming we don't need
> nested cluster support yet, I have some patches(not built or tested
> unfortunately yet). Let me know your thoughts. If you think you still
> need support for some kind of nested cluster, build that on top of this.
> Also I haven't bothered about sched domains as this purely relates to
> topology and how this is mapped to sched domain is orthogonal.
>
> If anything is broken, that needs to be fixed separately there. I see the
> idea here is correct and would like to push the patches once I build/test
> and get some review/more testing.

\
 
 \ /
  Last update: 2022-05-13 10:38    [W:0.094 / U:0.188 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site