Re: [PATCH v5 1/3] ipc/sem: account dynamically allocated sops arrays to memcg
From: Andrew Morton
Date: Mon Nov 16 2026 - 11:00:20 EST
On Mon, 16 Nov 2026 08:20:52 +0000 Yingjie Wang <x-professor@xxxxxxxxxxx> wrote:
> > There is no kmem accounting in root cgroup, do you know why there is an increase
> > of 2.3% there?
>
> I think the 2.3% mainly reflects boot-to-boot variation. The unchanged
> 64-operation stack path also slowed down by 1.9%, even though it does
> not reach the changed allocation.
>
> For successful calls, the per-boot medians were:
>
> nops V4 boots (ns) V5 boots (ns)
> 64 230.5 229.4 230.0 231.2 235.0 235.4
> 65 546.0 551.2 548.2 551.2 562.6 566.3
>
> The first V5 boot was very close to the upper end of the V4 results at
> 65 operations, while the later two boots were slower at both sizes.
> That is why I interpret the increase mainly as boot-to-boot variation,
> rather than root-cgroup charging.
>
> __GFP_ACCOUNT does still change the allocation path, including selecting
> the kmalloc-cg cache, so a small contribution from that is also possible.
>
> Andrew, could we clarify the root-cgroup result in the [1/3] changelog?
> Please change
>
> and successful calls in the root cgroup by at most 2.3%.
>
> to
>
> and successful calls in the root cgroup by at most 2.3%, which
> appears to be mainly boot-to-boot variation.
Yes, I have made both requested edits.