multithreading - “Got unknown event 17 … continuing …”对MPI意味着什么

Question

我正在运行MPI作业，并收到以下警告消息:

[comet-05-08.sdsc.edu:mpi_rank_10][async_thread] Got unknown event 17 ... continuing ...

我正在使用MVAPICH 2.1使用icc(ICC)15.0.2 20150121进行编译。

该消息是什么意思？有害吗？

Answer 1

从this邮件列表:

this error message is being printed by the asynchronous progress thread because of receving an IBV_EVENT_CLIENT_REREGISTER event (event #17).

建议您更新到最新版本。我链接的邮件建议使用MVAPICH2 1.4(比您的邮件更新)，尽管该邮件来自2009年。

可能生成的代码是:

switch (event.event_type) {
        ...

        break; 
    default:
        NEM_IB_ERR("Got unknown event %d ... continuing ...",
                event.event_type);
}

您可以在其中找到完整的代码 here。

如评论部分所示:

IBV_EVENT_CLIENT_REREGISTER

The SM requests that the client will reregister to all subscriptions previously requested from this port, for example (but not limited to) join a multicast group. This event may be generated when the SM suffered from a failure, which caused it to lose his records or when there is new SM in the subnet.

This event will be generated by the device only if the bit that indicates that client reregister is supported set in port_attr.port_cap_flags.

Source

我不会对那个事件感到满意，所以如果我是你，我会更新的。如果问题仍然存在，我将与MVAPICH2人员联系。