Introduce ValidatorManager to track all requests and validators' scores #4752
There are no files selected for viewing
This file contains hidden or 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 hidden or 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 hidden or 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 hidden or 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 |
|---|---|---|
|
|
@@ -119,6 +119,7 @@ async fn test_chain_listener() -> anyhow::Result<()> { | |
| Duration::from_secs(30), | ||
| Duration::from_secs(1), | ||
| ChainClientOptions::test_default(), | ||
| linera_core::client::ValidatorManagerConfig::default(), | ||
| )), | ||
| }; | ||
| context | ||
|
|
@@ -204,6 +205,7 @@ async fn test_chain_listener_admin_chain() -> anyhow::Result<()> { | |
| Duration::from_secs(30), | ||
| Duration::from_secs(1), | ||
| ChainClientOptions::test_default(), | ||
| linera_core::client::ValidatorManagerConfig::default(), | ||
| )), | ||
| }; | ||
| let context = Arc::new(Mutex::new(context)); | ||
|
|
||
This file contains hidden or 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 |
|---|---|---|
|
|
@@ -86,6 +86,9 @@ mod chain_client_state; | |
| #[cfg(test)] | ||
| #[path = "../unit_tests/client_tests.rs"] | ||
| mod client_tests; | ||
| pub mod validator_manager; | ||
|
|
||
| pub use validator_manager::{ScoringWeights, ValidatorManager, ValidatorManagerConfig}; | ||
| mod received_log; | ||
| mod validator_trackers; | ||
|
|
||
|
|
@@ -149,6 +152,8 @@ pub struct Client<Env: Environment> { | |
| /// Local node to manage the execution state and the local storage of the chains that we are | ||
| /// tracking. | ||
| local_node: LocalNodeClient<Env::Storage>, | ||
| /// Manages the requests sent to validator nodes. | ||
| validator_manager: ValidatorManager<Env>, | ||
| /// The admin chain ID. | ||
| admin_id: ChainId, | ||
| /// Chains that should be tracked by the client. | ||
|
|
@@ -175,6 +180,7 @@ impl<Env: Environment> Client<Env> { | |
| chain_worker_ttl: Duration, | ||
| sender_chain_worker_ttl: Duration, | ||
| options: ChainClientOptions, | ||
| validator_manager_config: validator_manager::ValidatorManagerConfig, | ||
| ) -> Self { | ||
| let tracked_chains = Arc::new(RwLock::new(tracked_chains.into_iter().collect())); | ||
| let state = WorkerState::new_for_client( | ||
|
|
@@ -188,10 +194,12 @@ impl<Env: Environment> Client<Env> { | |
| .with_chain_worker_ttl(chain_worker_ttl) | ||
| .with_sender_chain_worker_ttl(sender_chain_worker_ttl); | ||
| let local_node = LocalNodeClient::new(state); | ||
| let validator_manager = ValidatorManager::new(vec![], validator_manager_config); | ||
|
|
||
| Self { | ||
| environment, | ||
| local_node, | ||
| validator_manager, | ||
| chains: papaya::HashMap::new(), | ||
| admin_id, | ||
| tracked_chains, | ||
|
|
@@ -347,8 +355,10 @@ impl<Env: Environment> Client<Env> { | |
| .checked_sub(u64::from(next_height)) | ||
| .ok_or(ArithmeticError::Overflow)? | ||
| .min(self.options.certificate_download_batch_size); | ||
|
|
||
| let certificates = self | ||
| .validator_manager | ||
| .download_certificates(remote_node, chain_id, next_height, limit) | ||
| .await?; | ||
| let Some(info) = self.process_certificates(remote_node, certificates).await? else { | ||
| break; | ||
|
|
@@ -362,17 +372,20 @@ impl<Env: Environment> Client<Env> { | |
|
|
||
| async fn download_blobs( | ||
| &self, | ||
| remote_nodes: &[RemoteNode<Env::ValidatorNode>], | ||
| blob_ids: &[BlobId], | ||
| ) -> Result<(), ChainClientError> { | ||
| self.local_node | ||
| .store_blobs( | ||
| &self | ||
| .validator_manager | ||
| .download_blobs(remote_nodes, blob_ids, self.options.blob_download_timeout) | ||
| .await? | ||
| .ok_or_else(|| { | ||
| ChainClientError::RemoteNodeError(NodeError::BlobsNotFound( | ||
| blob_ids.to_vec(), | ||
| )) | ||
| })?, | ||
|
Comment on lines
+380
to
+388
There was a problem hiding this comment. I'd put that in a local variable before we call There was a problem hiding this comment. OK, but that was already here – I just moved it around. |
||
| ) | ||
| .await | ||
| .map_err(Into::into) | ||
|
|
@@ -383,7 +396,7 @@ impl<Env: Environment> Client<Env> { | |
| #[instrument(level = "trace", skip_all)] | ||
| async fn process_certificates( | ||
| &self, | ||
| remote_node: &RemoteNode<Env::ValidatorNode>, | ||
| certificates: Vec<ConfirmedBlockCertificate>, | ||
| ) -> Result<Option<Box<ChainInfo>>, ChainClientError> { | ||
| let mut info = None; | ||
|
|
@@ -398,7 +411,8 @@ impl<Env: Environment> Client<Env> { | |
| .await | ||
| { | ||
| Err(LocalNodeError::BlobsNotFound(blob_ids)) => { | ||
| self.download_blobs(&[remote_node.clone()], &blob_ids) | ||
| .await?; | ||
| } | ||
| x => { | ||
| x?; | ||
|
|
@@ -409,7 +423,8 @@ impl<Env: Environment> Client<Env> { | |
| info = Some( | ||
| match self.handle_certificate(certificate.clone()).await { | ||
| Err(LocalNodeError::BlobsNotFound(blob_ids)) => { | ||
| self.download_blobs(&[remote_node.clone()], &blob_ids) | ||
| .await?; | ||
| self.handle_certificate(certificate).await? | ||
| } | ||
| x => x?, | ||
|
|
@@ -663,7 +678,6 @@ impl<Env: Environment> Client<Env> { | |
| ) -> Result<(), ChainClientError> { | ||
| let certificate = Box::new(certificate); | ||
| let block = certificate.block(); | ||
| // Recover history from the network. | ||
| self.download_certificates(block.header.chain_id, block.header.height) | ||
| .await?; | ||
|
|
@@ -672,14 +686,9 @@ impl<Env: Environment> Client<Env> { | |
| if let Err(err) = self.process_certificate(certificate.clone()).await { | ||
| match &err { | ||
| LocalNodeError::BlobsNotFound(blob_ids) => { | ||
| self.download_blobs(&self.validator_nodes().await?, blob_ids) | ||
| .await | ||
| .map_err(|_| err)?; | ||
| self.process_certificate(certificate).await?; | ||
| } | ||
| _ => { | ||
|
|
@@ -716,14 +725,7 @@ impl<Env: Environment> Client<Env> { | |
| if let Err(err) = self.handle_certificate(certificate.clone()).await { | ||
| match &err { | ||
| LocalNodeError::BlobsNotFound(blob_ids) => { | ||
| self.download_blobs(&nodes, blob_ids).await?; | ||
| self.handle_certificate(certificate.clone()).await?; | ||
| } | ||
| _ => { | ||
|
|
@@ -777,8 +779,13 @@ impl<Env: Environment> Client<Env> { | |
| // anything from the validator - let the function try the other validators | ||
| return Err(()); | ||
| } | ||
| let certificates = self | ||
| .validator_manager | ||
| .download_certificates_by_heights( | ||
| &remote_node, | ||
| sender_chain_id, | ||
| remote_heights, | ||
| ) | ||
| .await | ||
| .map_err(|_| ())?; | ||
| let mut certificates_with_check_results = vec![]; | ||
|
|
@@ -934,8 +941,13 @@ impl<Env: Environment> Client<Env> { | |
| // Stop if we've reached the height we've already processed. | ||
| while current_height >= next_outbox_height { | ||
| // Download the certificate for this height. | ||
| let downloaded = self | ||
| .validator_manager | ||
| .download_certificates_by_heights( | ||
| remote_node, | ||
| sender_chain_id, | ||
| vec![current_height], | ||
| ) | ||
| .await?; | ||
| let Some(certificate) = downloaded.into_iter().next() else { | ||
| return Err(ChainClientError::CannotDownloadMissingSenderBlock { | ||
|
|
@@ -1119,9 +1131,9 @@ impl<Env: Environment> Client<Env> { | |
| if !required_blob_ids.is_empty() { | ||
| let mut blobs = Vec::new(); | ||
| for blob_id in required_blob_ids { | ||
| let blob_content = match self | ||
| .validator_manager | ||
| .download_pending_blob(remote_node, chain_id, blob_id) | ||
| .await | ||
| { | ||
| Ok(content) => content, | ||
|
|
@@ -1217,9 +1229,9 @@ impl<Env: Environment> Client<Env> { | |
| Err(LocalNodeError::BlobsNotFound(blob_ids)) => { | ||
| let mut blobs = Vec::new(); | ||
| for blob_id in blob_ids { | ||
| let blob_content = self | ||
| .validator_manager | ||
| .download_pending_blob(remote_node, chain_id, blob_id) | ||
| .await?; | ||
| blobs.push(Blob::new(blob_content)); | ||
| } | ||
|
|
@@ -1248,7 +1260,10 @@ impl<Env: Environment> Client<Env> { | |
| communicate_concurrently( | ||
| remote_nodes, | ||
| async move |remote_node| { | ||
afck marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| let certificate = self | ||
| .validator_manager | ||
| .download_certificate_for_blob(&remote_node, blob_id) | ||
| .await?; | ||
| self.receive_sender_certificate( | ||
| certificate, | ||
| ReceiveCertificateMode::NeedsCheck, | ||
|
|
@@ -4123,7 +4138,7 @@ impl<Env: Environment> ChainClient<Env> { | |
| } | ||
|
|
||
| /// Performs `f` in parallel on multiple nodes, starting with a quadratically increasing delay on | ||
| /// each subsequent node. Returns error `err` if all of the nodes fail. | ||
| async fn communicate_concurrently<'a, A, E1, E2, F, G, R, V>( | ||
| nodes: &[RemoteNode<A>], | ||
| f: F, | ||
|
|
||
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.
Should we make that milliseconds, too? We use ms for almost all timing options.
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.
I thought that we'd never need anything less than 1 second but I agree with you we should be consistent. Will change.