Re: [PATCH v2] mm/mempolicy: recompute automatic interleave weights on memory hotplug

[Joshua Hahn]

On Fri, Oct 30, 2026 at 7:43 PM Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
>
> On Fri, 30 Oct 2026 12:35:38 -0400 Joshua Hahn <joshua.hahnjy@xxxxxxxxx> wrote:
>
> > On Fri, Oct 30, 2026 at 12:12 PM Gregory Price (Meta) <gourry@xxxxxxxxxx> wrote:
> > >
> > > In auto mode, weighted interleave derives each node's weight from its
> > > bandwidth, reduced over the nodes in N_MEMORY. HMAT and CXL report a
> > > node's bandwidth once, when the node first gains memory, and nothing
> > > else on the hotplug path recomputes the weights.
> > >
> > > This can result in a major skew in distribution and overload tiers
> > > with more data than their respective bandwidth can support, resulting
> > > in a performance regression.
> >
> > ...
> >
> > I think you may have dropped my review tag from the previous
> > version!!! I believe the only thing that changes is the warn, so
> > please feel free to add:
> > Reviewed-by: Joshua Hahn <joshua.hahnjy@xxxxxxxxx>
>
> Actually, quite a lot changed, so dropping the v1 tags seems
> appropriate.

Hi Andrew,
Ah, thank you for the catch. Looking through the code again, I think
it still looks good to me so my review tag should stil stay. I'll be
more careful about stuff like this in the future!

> v1->v2:
>
>  mm/mempolicy.c |   36 ++++++++++++++++++++++++++++--------
>  1 file changed, 28 insertions(+), 8 deletions(-)
>
> --- a/mm/mempolicy.c~mm-mempolicy-recompute-automatic-interleave-weights-on-memory-hotplug-v2
> +++ a/mm/mempolicy.c
> @@ -261,7 +261,11 @@ static int wi_state_refresh(void)
>         mutex_lock(&wi_state_lock);
>         old_wi_state = rcu_dereference_protected(wi_state,
>                                         lockdep_is_held(&wi_state_lock));
> -       /* NULL wi_state assumes auto=true */
> +       /*
> +        * Hotplug events can arrive before any node reported its bandwidth,
> +        * leaving nothing to compute weights from. NULL wi_state assumes
> +        * auto=true.
> +        */
>         if (!node_bw_table || (old_wi_state && !old_wi_state->mode_auto)) {
>                 mutex_unlock(&wi_state_lock);
>                 kfree(new_wi_state);
> @@ -302,6 +306,28 @@ int mempolicy_set_node_perf(unsigned int
>         return wi_state_refresh();
>  }
>
> +/*
> + * HMAT and CXL report a node's bandwidth only when it first gains memory, so
> + * recompute the weights whenever N_MEMORY changes.
> + */
> +static int wi_state_node_notifier(struct notifier_block *nb,
> +                                 unsigned long action, void *data)
> +{
> +       struct node_notify *nn = data;
> +       int err;
> +
> +       if (action != NODE_ADDED_FIRST_MEMORY &&
> +           action != NODE_REMOVED_LAST_MEMORY)
> +               return NOTIFY_OK;
> +
> +       /* The hotplug is done, failing the notification would not undo it */
> +       err = wi_state_refresh();
> +       if (err)
> +               pr_warn_once("failed to recompute weighted interleave weights for node%d: %d\n",
> +                            nn->nid, err);
> +       return NOTIFY_OK;
> +}
> +
>  /**
>   * numa_nearest_node - Find nearest node by state
>   * @node: Node id to start the search
> @@ -3424,6 +3450,7 @@ void __init numa_policy_init(void)
>         if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
>                 pr_err("%s: interleaving failed\n", __func__);
>
> +       hotplug_node_notifier(wi_state_node_notifier, DEFAULT_CALLBACK_PRI);
>         check_numabalancing_enable();
>  }
>
> @@ -3910,15 +3937,8 @@ static int wi_node_notifier(struct notif
>         case NODE_REMOVED_LAST_MEMORY:
>                 sysfs_wi_node_delete(nid);
>                 break;
> -       default:
> -               return NOTIFY_OK;
>         }
>
> -       /*
> -        * HMAT and CXL report a node's bandwidth only when it first gains
> -        * memory, so recompute the weights whenever N_MEMORY changes.
> -        */
> -       wi_state_refresh();
>         return NOTIFY_OK;
>  }
>
> _
>