Unverified Commit 5005b7be authored by Wenjun Si's avatar Wenjun Si Committed by GitHub
Browse files

Create a new TcpSocket when connection failed (#3840)

parent 0235050e
...@@ -197,20 +197,21 @@ void Linkers::Construct() { ...@@ -197,20 +197,21 @@ void Linkers::Construct() {
int out_rank = it->first; int out_rank = it->first;
// let smaller rank connect to larger rank // let smaller rank connect to larger rank
if (out_rank > rank_) { if (out_rank > rank_) {
TcpSocket cur_socket;
int connect_fail_delay_time = connect_fail_retry_first_delay_interval; int connect_fail_delay_time = connect_fail_retry_first_delay_interval;
for (int i = 0; i < connect_fail_retry_cnt; ++i) { for (int i = 0; i < connect_fail_retry_cnt; ++i) {
TcpSocket cur_socket;
if (cur_socket.Connect(client_ips_[out_rank].c_str(), client_ports_[out_rank])) { if (cur_socket.Connect(client_ips_[out_rank].c_str(), client_ports_[out_rank])) {
// send local rank
cur_socket.Send(reinterpret_cast<const char*>(&rank_), sizeof(rank_));
SetLinker(out_rank, cur_socket);
break; break;
} else { } else {
Log::Warning("Connecting to rank %d failed, waiting for %d milliseconds", out_rank, connect_fail_delay_time); Log::Warning("Connecting to rank %d failed, waiting for %d milliseconds", out_rank, connect_fail_delay_time);
cur_socket.Close();
std::this_thread::sleep_for(std::chrono::milliseconds(connect_fail_delay_time)); std::this_thread::sleep_for(std::chrono::milliseconds(connect_fail_delay_time));
connect_fail_delay_time = static_cast<int>(connect_fail_delay_time * connect_fail_retry_delay_factor); connect_fail_delay_time = static_cast<int>(connect_fail_delay_time * connect_fail_retry_delay_factor);
} }
} }
// send local rank
cur_socket.Send(reinterpret_cast<const char*>(&rank_), sizeof(rank_));
SetLinker(out_rank, cur_socket);
} }
} }
// wait for listener // wait for listener
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment