Messages in this thread | | | Date | Sun, 18 Sep 2022 14:53:48 +0200 | Subject | Re: [PATCH v6 2/2] ipc/msg: mitigate the lock contention with percpu counter | From | Manfred Spraul <> |
| |
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
| |