Re: [PATCH] ipc/msg.c: mitigate the lock contention with percpu counter

[Sun, Jiebin]

On 9/4/2022 3:35 AM, Manfred Spraul wrote:
> Hi Jiebin,
>
> On 9/2/22 17:22, Jiebin Sun wrote:
> > The msg_bytes and msg_hdrs atomic counters are frequently
> > updated when IPC msg queue is in heavy use, causing heavy
> > cache bounce and overhead. Change them to percpu_counters
> > greatly improve the performance. Since there is one unique
> > ipc namespace, additional memory cost is minimal.
>
> With ipc namespaces, there is one struct per namespace, correct?
>
> The cost is probably still ok, but the change log should be correct.
Yes, that's what I want to summarize. The IPC msg namespace is unique

and there is only one percpu counter in IPC msg namespace.

Thanks.

> > @@ -1303,14 +1305,16 @@ void msg_init_ns(struct ipc_namespace *ns)
> >       ns->msg_ctlmnb = MSGMNB;
> >       ns->msg_ctlmni = MSGMNI;
> >   -    atomic_set(&ns->msg_bytes, 0);
> > -    atomic_set(&ns->msg_hdrs, 0);
> > +    percpu_counter_init(&ns->percpu_msg_bytes, 0, GFP_KERNEL);
> > +    percpu_counter_init(&ns->percpu_msg_hdrs, 0, GFP_KERNEL);
> >       ipc_init_ids(&ns->ids[IPC_MSG_IDS]);
>
> These calls can fail. You must add error handling.

I have add error handling for percpu_counter_init.

Thanks.

> --
>
>     Manfred