c++ - 服务器关闭永远不会完成

Question

我有异步 gRPC 服务器(gRPC 版本 1.40.X，Windows 10 x64)。

当我尝试关闭服务器时，有时会正常关闭，有时负责运行 gRPC 的线程会在关闭过程开始时卡住。向服务器发送垃圾邮件的客户端越多，这种情况发生的可能性就越大。

我的关机程序:

1. 等待当前Que->AsyncNext完成
2. 我在收到 AsyncNotifyWhenDone 的任何调用上都调用了 TryToCancel，这可能是导致问题的原因，因为我无法真正在所有调用中都调用它AsyncNotifyWhenDone 尚未收到，不确定如何处理此问题，因为调用 finish() 是在 GOT_EVENT 之后完成的
3. 我调用了 Server->Shutdown()，在这里它卡住了，线程永远挂起。
4. 然后 Que->Shutdown()
5. 然后是 DrainQue() 同步函数，通过 Que->Next
所有剩余的调用
6. 清除所有通话数据

这是它发生时的最后痕迹:

I0921 08:44:56.768000000 17588 init.cc:167] grpc_init(void)
I0921 08:44:56.768000000 17588 completion_queue.cc:522] grpc_completion_queue_create_internal(completion_type=0, polling_type=0)
I0921 08:44:56.768000000 17588 server.cc:1536] grpc_server_shutdown_and_notify(server=000001538016BEE8, cq=0000015415E29A90, tag=0000004D816FF208)
I0921 08:44:56.768000000 17588 completion_queue.cc:701] cq_end_op_for_next(cq=00000153AE87C900, tag=00000153800F7040, error={"created":"@1632206696.768000000","description":"Server Shutdown","file":"\grpc\src\core\lib\surface\server.cc","file_line":832}, done=00007FFD47DE9440, done_arg=0000015380133F40, storage=0000015380133F68)
I0921 08:44:56.768000000 17588 completion_queue.cc:701] cq_end_op_for_next(cq=00000153AE87C900, tag=00000153800EFE00, error={"created":"@1632206696.768000000","description":"Server Shutdown","file":"\grpc\src\core\lib\surface\server.cc","file_line":832}, done=00007FFD47DE9440, done_arg=0000015380133E80, storage=0000015380133EA8)
I0921 08:44:56.768000000 17588 completion_queue.cc:701] cq_end_op_for_next(cq=00000153AE87C900, tag=00000153800EFC00, error={"created":"@1632206696.768000000","description":"Server Shutdown","file":"\grpc\src\core\lib\surface\server.cc","file_line":832}, done=00007FFD47DE9440, done_arg=0000015380133DC0, storage=0000015380133DE8)
I0921 08:44:56.768000000 17588 chttp2_transport.cc:1752] ipv4:127.0.0.1:56702: Sending goaway err={"created":"@1632206696.768000000","description":"Server shutdown","file":"\grpc\src\core\lib\surface\server.cc","file_line":480,"grpc_status":0}
I0921 08:44:56.768000000 17588 completion_queue.cc:1419] grpc_completion_queue_shutdown(cq=0000015415E29A90)
I0921 08:44:56.768000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=0000015415E29A90, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 0 }, reserved=0000000000000000)

(为了尊重我的隐私，路径的开头部分已被删除)

当客户端完全断开连接时，它会解冻并继续:

I0921 08:47:02.540000000 17588 completion_queue.cc:701] cq_end_op_for_next(cq=0000015415E29A90, tag=0000004D816FF208, error="No Error", done=00007FFD47DE9450, done_arg=0000015380127F00, storage=0000015380137F90)
I0921 08:47:02.540000000 17588 completion_queue.cc:701] cq_end_op_for_next(cq=00000153AE87C900, tag=0000015421DDF220, error="No Error", done=00007FFD47DE07B0, done_arg=0000015421DDF3C0, storage=0000015421DDF408)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[0000015415E29A90]: OP_COMPLETE: tag:0x4d816ff208 OK
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=0000015415E29A90, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 0 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[0000015415E29A90]: QUEUE_SHUTDOWN
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=0000015415E29A90, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 1 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[0000015415E29A90]: QUEUE_SHUTDOWN
I0921 08:47:02.540000000 17588 completion_queue.cc:1425] grpc_completion_queue_destroy(cq=0000015415E29A90)
I0921 08:47:02.540000000 17588 completion_queue.cc:1419] grpc_completion_queue_shutdown(cq=0000015415E29A90)
I0921 08:47:02.540000000 17588 init.cc:213] grpc_shutdown(void)
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=00000153AE87C900, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 1 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[00000153AE87C900]: OP_COMPLETE: tag:0x153800f7040 ERROR
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=00000153800F7308)
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=00000153AE87C900, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 1 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[00000153AE87C900]: OP_COMPLETE: tag:0x153800efe00 ERROR
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=00000153AE87C900, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 1 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[00000153AE87C900]: OP_COMPLETE: tag:0x153800efc00 ERROR
I0921 08:47:02.540000000 17588 completion_queue.cc:1419] grpc_completion_queue_shutdown(cq=00000153AE87C900)
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=00000153AE87C900, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 1 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[00000153AE87C900]: OP_COMPLETE: tag:0x15421ddf220 OK
I0921 08:47:02.540000000 17588 completion_queue.cc:979] grpc_completion_queue_next(cq=00000153AE87C900, deadline=gpr_timespec { tv_sec: 9223372036854775807, tv_nsec: 0, clock_type: 1 }, reserved=0000000000000000)
I0921 08:47:02.540000000 17588 completion_queue.cc:1083] RETURN_EVENT[00000153AE87C900]: QUEUE_SHUTDOWN
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=00000153800FB660)
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=00000153800F96E0)
I0921 08:47:02.540000000 17588 call.cc:590] grpc_call_unref(c=0000015421DDCAE0)
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=0000015421DDD5C8)
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=00000153800FABE0)
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=00000153800FA160)
I0921 08:47:02.540000000 17588 call.cc:590] grpc_call_unref(c=00000154221F10E0)
I0921 08:47:02.540000000 17588 metadata_array.cc:34] grpc_metadata_array_destroy(array=00000154221F1BC8)
I0921 08:47:02.540000000 17588 init.cc:213] grpc_shutdown(void)
I0921 08:47:03.297000000 28004 server.cc:1550] grpc_server_destroy(server=000001538016BEE8)
I0921 08:47:03.297000000 28004 init.cc:213] grpc_shutdown(void)
I0921 08:47:03.297000000 28004 completion_queue.cc:1425] grpc_completion_queue_destroy(cq=00000153AE87C900)
I0921 08:47:03.297000000 28004 completion_queue.cc:1419] grpc_completion_queue_shutdown(cq=00000153AE87C900)
I0921 08:47:03.297000000 28004 init.cc:213] grpc_shutdown(void)

这与我之前的问题有些相关，我认为已经解决了:gRPC Server shutdown hangs forever

我真的不明白跟踪，它只给了我更多的问题然后是答案，例如为什么它调用 grpc_init，为什么 grpc_shutdown 被称为 3*，为什么它自己在关闭函数中做 next。

任何帮助将不胜感激

最好的，一月

Answer 1

经过一些挖掘我找到了一个解决方案，Shutdown() 有两个重载，有截止日期和没有截止日期，我一直在使用的(没有截止日期)只是永远等待，而有截止日期只等截止时间。

所以我的新关机看起来像这样:

const std::chrono::milliseconds WaitDuration = std::chrono::milliseconds(50);
const std::chrono::time_point<system_clock> Deadline = std::chrono::system_clock::now() + WaitDuration;

Server->Shutdown(Deadline);

50 毫秒目前是任意选择的，因为在文档中也没有建议或最佳实践，因此它可能会发生变化。