Fix HTTP/2 PROTOCOL_ERROR by configuring connection pool lifetimes #570
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Outdated suggestions cannot be applied.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.
Long-lived HTTP/2 connections can become corrupted, causing
PROTOCOL_ERROR (0x1)failures in gRPC calls. This manifests asHttpProtocolException: The HTTP/2 server sent invalid data on the connectionduring streaming operations like Topic reads/writes.Per grpc-dotnet#2641, the fix is to configure connection pool timeouts on
SocketsHttpHandler.Changes
Added connection lifecycle settings to
DriverConfigPooledConnectionIdleTimeout(default: 60s) - closes idle connectionsPooledConnectionLifetime(default: 300s) - maximum connection ageApplied settings in
GrpcChannelFactory.CreateChannel()Exposed via connection string properties
PooledConnectionIdleTimeout=60;PooledConnectionLifetime=300Values are configurable but defaults should handle most cases. Connection refresh happens transparently without disrupting active streams.
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.