Skip to content

fix async mode handle COMPLETE_MESSAGE (#13212) #13224

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 5, 2018
Merged

fix async mode handle COMPLETE_MESSAGE (#13212) #13224

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 25 additions & 24 deletions paddle/fluid/operators/distributed/request_handler_impl.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,19 +39,6 @@ bool RequestSendHandler::Handle(const std::string& varname,
const std::string& out_var_name) {
VLOG(4) << "RequestSendHandler:" << varname;

// Async
if (!sync_mode_) {
rpc_server_->Profiler().OneStep();
try {
executor_->RunPreparedContext((*grad_to_prepared_ctx_)[varname].get(),
scope);
} catch (std::exception& e) {
LOG(ERROR) << "async: run sub program error " << e.what();
return false;
}
return true;
}

// Sync
if (varname == BATCH_BARRIER_MESSAGE) {
VLOG(3) << "sync: recv BATCH_BARRIER_MESSAGE";
Expand All @@ -60,17 +47,31 @@ bool RequestSendHandler::Handle(const std::string& varname,
VLOG(3) << "sync: recv complete message";
rpc_server_->Complete();
} else {
VLOG(3) << "sync: received var_name: " << varname;
rpc_server_->WaitCond(kRequestSend);
VLOG(3) << "sync: processing received var: " << varname;

if (invar == nullptr) {
LOG(FATAL) << "sync: Can not find server side var: " << varname;
return false;
}
if (invar->IsType<framework::SelectedRows>()) {
std::unique_lock<std::mutex> lock(mutex_sparse_vars_);
sparse_vars_.push_back(invar);
// Async
if (!sync_mode_) {
VLOG(3) << "async process var: " << varname;
rpc_server_->Profiler().OneStep();
try {
executor_->RunPreparedContext((*grad_to_prepared_ctx_)[varname].get(),
scope);
} catch (std::exception& e) {
LOG(ERROR) << "async: run sub program error " << e.what();
return false;
}
return true;
} else { // sync
rpc_server_->WaitCond(kRequestSend);
VLOG(3) << "sync: processing received var: " << varname;

if (invar == nullptr) {
LOG(FATAL) << "sync: Can not find server side var: " << varname;
return false;
}

if (invar->IsType<framework::SelectedRows>()) {
std::unique_lock<std::mutex> lock(mutex_sparse_vars_);
sparse_vars_.push_back(invar);
}
}
}
return true;
Expand Down