Re: [PATCH v6 2/2] ipc/msg: mitigate the lock contention with percpu counter

[Manfred Spraul <manfred@colorfullife.com>]

Hi Jiebin,

On 9/13/22 21:25, 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_counter
> greatly improve the performance. Since there is one percpu
> struct per namespace, additional memory cost is minimal.
> Reading of the count done in msgctl call, which is infrequent.
> So the need to sum up the counts in each CPU is infrequent.
>
> Apply the patch and test the pts/stress-ng-1.4.0
> -- system v message passing (160 threads).
>
> Score gain: 3.99x
>
> CPU: ICX 8380 x 2 sockets
> Core number: 40 x 2 physical cores
> Benchmark: pts/stress-ng-1.4.0
> -- system v message passing (160 threads)
>
> Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Reviewed-by: Manfred Spraul <manfred@colorfullif.com>
> @@ -495,17 +496,18 @@ static int msgctl_info(struct ipc_namespace *ns, int msqid,
>   	msginfo->msgssz = MSGSSZ;
>   	msginfo->msgseg = MSGSEG;
>   	down_read(&msg_ids(ns).rwsem);
> -	if (cmd == MSG_INFO) {
> +	if (cmd == MSG_INFO)
>   		msginfo->msgpool = msg_ids(ns).in_use;
> -		msginfo->msgmap = atomic_read(&ns->msg_hdrs);
> -		msginfo->msgtql = atomic_read(&ns->msg_bytes);
> +	max_idx = ipc_get_maxidx(&msg_ids(ns));
> +	up_read(&msg_ids(ns).rwsem);
> +	if (cmd == MSG_INFO) {
> +		msginfo->msgmap = percpu_counter_sum(&ns->percpu_msg_hdrs);
> +		msginfo->msgtql = percpu_counter_sum(&ns->percpu_msg_bytes);

Not caused by your change, it just now becomes obvious:

msginfo->msgmap and ->msgtql are type int, i.e. signed 32-bit, and the 
actual counters are 64-bit.
This can overflow - and I think the code should handle this. Just clamp 
the values to INT_MAX.

-- 

     Manfred