ssk015
/
mindspore2022
forked from huawei/mindspore2022
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bugfix: recovery fail when kill and pull worker twice

This commit is contained in:
lizhenyu 2022-03-31 18:44:30 +08:00
parent 1ec280b0e5
commit 0aae542f4f
2 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
mindspore/ccsrc/distributed/collective/collective_manager.cc
View File

@ -277,6 +277,7 @@ bool CollectiveManager::Finalize() {
MS_LOG(WARNING) << "Failed to finalize device communication library.";
}
inited_ = false;
finalized_ = true;
return true;
};

1
mindspore/ccsrc/plugin/device/gpu/hal/hardware/nvidia_collective_comm_lib.cc
View File

@ -29,6 +29,7 @@ bool NvidiaCollectiveCommLib::Initialize(uint32_t global_rank, uint32_t global_r
global_rank_id_ = global_rank;
global_rank_size_ = global_rank_size;
initialized_ = true;
finalized_ = false;
return true;
}