Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 1 Feb 2022 11:29:04 +0530
From:   Srikar Dronamraju <srikar@linux.vnet.ibm.com>
To:     "Huang, Ying" <ying.huang@intel.com>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Mel Gorman <mgorman@suse.de>, linux-kernel@vger.kernel.org,
        Ingo Molnar <mingo@redhat.com>, Rik van Riel <riel@surriel.com>
Subject: Re: [RFC PATCH 2/2] NUMA balancing: avoid to migrate task to
 CPU-less node
Message-ID: <20220201055904.GD618915@linux.vnet.ibm.com>
Reply-To: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
References: <20220128023842.1946583-1-ying.huang@intel.com>
 <20220128023842.1946583-2-ying.huang@intel.com>
 <20220128053341.GB618915@linux.vnet.ibm.com>
 <877dakti0n.fsf@yhuang6-desk2.ccr.corp.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
In-Reply-To: <877dakti0n.fsf@yhuang6-desk2.ccr.corp.intel.com>
Precedence: bulk

* Huang, Ying <ying.huang@intel.com> [2022-01-28 15:51:36]:

> Srikar Dronamraju <srikar@linux.vnet.ibm.com> writes:
> 
> > * Huang Ying <ying.huang@intel.com> [2022-01-28 10:38:42]:
> >
> This sounds reasonable.  How about the following solution?  If a
> CPU-less node is selected as migration target, we select a nearest node
> with CPU instead?  That is, something like the below patch.
> 
> Best Regards,
> Huang, Ying
> 
> ------------------------------8<---------------------------------
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 5146163bfabb..52d926d8cbdb 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -2401,6 +2401,23 @@ static void task_numa_placement(struct task_struct *p)
>  		}
>  	}
> 
> +	/* Cannot migrate task to CPU-less node */
> +	if (!node_state(max_nid, N_CPU)) {
> +		int near_nid = max_nid;
> +		int distance, near_distance = INT_MAX;
> +
> +		for_each_online_node(nid) {
> +			if (!node_state(nid, N_CPU))
> +				continue;
> +			distance = node_distance(max_nid, nid);
> +			if (distance < near_distance) {
> +				near_nid = nid;
> +				near_distance = distance;
> +			}
> +		}
> +		max_nid = near_nid;
> +	}
> +


This looks good. but should we move this into preferred_group_nid()?
i.e should we care for !ng case, since those would mean only private faults.

>  	if (ng) {
>  		numa_group_count_active_nodes(ng);
>  		spin_unlock_irq(group_lock);

-- 
Thanks and Regards
Srikar Dronamraju