[core] Only get single node info rather then all when needed #49727
+143
−145
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -396,145 +396,106 @@ std::string GlobalStateAccessor::GetSystemConfig() { | |
| return future.get(); | ||
| } | ||
|
|
||
| ray::Status GlobalStateAccessor::GetNode(const std::string &node_id_hex_str, | ||
| std::string *node_info) { | ||
| const auto end_time_point = | ||
| current_time_ms() + RayConfig::instance().raylet_start_wait_time_s() * 1000; | ||
| const auto node_id_binary = NodeID::FromHex(node_id_hex_str).Binary(); | ||
|
|
||
| std::vector<rpc::GcsNodeInfo> node_infos; | ||
| while (true) { | ||
| rpc::GetAllNodeInfoRequest_Filters filters; | ||
| filters.set_state(rpc::GcsNodeInfo_GcsNodeState::GcsNodeInfo_GcsNodeState_ALIVE); | ||
| filters.set_node_id(node_id_binary); | ||
| { | ||
| absl::ReaderMutexLock lock(&mutex_); | ||
| auto timeout_ms = | ||
| std::max(end_time_point - current_time_ms(), static_cast<int64_t>(0)); | ||
| RAY_ASSIGN_OR_RETURN( | ||
| node_infos, | ||
| gcs_client_->Nodes().GetAllNoCacheWithFilters(timeout_ms, std::move(filters))); | ||
| } | ||
| if (!node_infos.empty()) { | ||
| *node_info = node_infos[0].SerializeAsString(); | ||
| return Status::OK(); | ||
| } | ||
|
|
||
| if (current_time_ms() >= end_time_point) { | ||
| return Status::NotFound( | ||
| "GCS cannot find the node with node ID " + node_id_hex_str + | ||
| ". The node registration may not be complete yet before the timeout." + | ||
| " Try increase the RAY_raylet_start_wait_time_s config."); | ||
| } | ||
| RAY_LOG(WARNING) << "Retrying to get node with node ID " << node_id_hex_str; | ||
| // Some of the information may not be in GCS yet, so wait a little bit. | ||
| std::this_thread::sleep_for(std::chrono::seconds(1)); | ||
| } | ||
| } | ||
|
|
||
| ray::Status GlobalStateAccessor::GetNodeToConnectForDriver( | ||
| const std::string &node_ip_address, std::string *node_to_connect) { | ||
| const auto end_time_point = | ||
| current_time_ms() + RayConfig::instance().raylet_start_wait_time_s() * 1000; | ||
|
|
||
| std::vector<rpc::GcsNodeInfo> node_infos; | ||
| rpc::GetAllNodeInfoRequest_Filters filters; | ||
| filters.set_state(rpc::GcsNodeInfo_GcsNodeState::GcsNodeInfo_GcsNodeState_ALIVE); | ||
| filters.set_node_ip_address(node_ip_address); | ||
| while (true) { | ||
| { | ||
| absl::ReaderMutexLock lock(&mutex_); | ||
| auto timeout_ms = | ||
| std::max(end_time_point - current_time_ms(), static_cast<int64_t>(0)); | ||
| RAY_ASSIGN_OR_RETURN( | ||
| node_infos, gcs_client_->Nodes().GetAllNoCacheWithFilters(timeout_ms, filters)); | ||
| } | ||
| if (!node_infos.empty()) { | ||
| *node_to_connect = node_infos[0].SerializeAsString(); | ||
| return Status::OK(); | ||
| } | ||
|
|
||
| std::string gcs_address; | ||
| { | ||
| absl::WriterMutexLock lock(&mutex_); | ||
| auto [address, _] = gcs_client_->GetGcsServerAddress(); | ||
| gcs_address = std::move(address); | ||
| } | ||
| filters.set_node_ip_address(gcs_address); | ||
| { | ||
| absl::ReaderMutexLock lock(&mutex_); | ||
| auto timeout_ms = end_time_point - current_time_ms(); | ||
| RAY_ASSIGN_OR_RETURN( | ||
| node_infos, gcs_client_->Nodes().GetAllNoCacheWithFilters(timeout_ms, filters)); | ||
| } | ||
| if (node_infos.empty() && node_ip_address == gcs_address) { | ||
| filters.set_node_ip_address("127.0.0.1"); | ||
|
Comment on lines
+470
to
+471
There was a problem hiding this comment. If you know, can you comment on what this case is? There was a problem hiding this comment. Related code (listen_to_localhost_only sets GrpcServer to listen to 127.0.0.1) with and pr that introduced this #16810. Don't see a concrete reason to have this last case anywhere, ideally the above case of looking for gcs_address should cover it, but maybe some case of container or something? |
||
| { | ||
|
There was a problem hiding this comment. i feel like the error messages don't totally align with the error messages, here we'll just return a node_info as long it matches the gcs_address we fetched |
||
| absl::ReaderMutexLock lock(&mutex_); | ||
| auto timeout_ms = | ||
| std::max(end_time_point - current_time_ms(), static_cast<int64_t>(0)); | ||
| RAY_ASSIGN_OR_RETURN( | ||
| node_infos, | ||
| gcs_client_->Nodes().GetAllNoCacheWithFilters(timeout_ms, filters)); | ||
| } | ||
| } | ||
| if (!node_infos.empty()) { | ||
| RAY_LOG(INFO) << "This node has an IP address of " << node_ip_address | ||
| << ", but we cannot find a local Raylet with the same address. " | ||
| << "This can happen when you connect to the Ray cluster " | ||
| << "with a different IP address or when connecting to a container."; | ||
|
Comment on lines
+482
to
+485
There was a problem hiding this comment. previously we were still logging this if we don't get any node info that matches with the node_ip_address id and have to resort to using the gcs_address we fetched instead of the node_ip_address passed into the function |
||
| *node_to_connect = node_infos[0].SerializeAsString(); | ||
| return Status::OK(); | ||
| } | ||
|
|
||
| if (current_time_ms() >= end_time_point) { | ||
| std::ostringstream oss; | ||
| oss << "This node has an IP address of " << node_ip_address << ", and Ray " | ||
| << "expects this IP address to be either the GCS address or one of" | ||
| << " the Raylet addresses. Connected to GCS at " << gcs_address | ||
| << ", and found no Raylet with this IP address. " | ||
| << "You might need to provide --node-ip-address to specify the IP " | ||
| << "address that the head should use when sending to this node."; | ||
| return Status::NotFound(oss.str()); | ||
| } | ||
| RAY_LOG(WARNING) << "Some processes that the driver needs to connect to have " | ||
| "not registered with GCS, so retrying. Have you run " | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why lock?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
gcs_client_ is protected by mutex, this is how it's used throughout