* updating passthru endpoint to filter 0 length slices passed to endpoint write
* adding testcase which caused the failure
* fix minor bug in passthru endpoint to handle rare case where endpoint write is called with no data to be written
* Check if memory owner available prior to polling it
The transport may drop the memory owner during its destruction sequence
* tcp_fix
* Revert "Revert "New resource quota integration (#27643)" (#28014)"
This reverts commit 0ea2c37263.
* clang-format
* fix-path
* fix
* adding api_fuzzer changes
* adding api fuzzer changes
* updating some typos
* updating api_fuzzer and corpus entries
* updating api_fuzzer to fix crash due to two successive receive_op batches
* adding some reverted fixes to api_fuzzer.cc
* updating api_fuzzer and corpus as per initial comments
* fix some typos
* fix memory leaks and timeout issues
* adding some comments and removing debug strings
* updating api_fuzzer to remove previous edits to always add recv initial metadata ops for client calls
* updating passthru endpoint to account for erroneous initialization when channel effects are not simulated
* tidying up code
The urgent argument is a platform-specific flag that leaked into the (ideally) platform-independent HTTP/2 transport layer. In an effort to clean up the cross-platform API surface, it would be helpful if we can remove this argument from the TCP Read api without losing the performance optimization that was introduced along with it (see #18240).
TCP_INQ is a socket option we added to Linux to report pending bytes
on the socket as a control message.
Using TCP_INQ we can accurately decide whether to continue read or not.
Add an urgent parameter, when we do not want to wait for EPOLLIN.
This commit improves the latency of 1 RPC unary (minimal benchmark)
significantly:
Before:
l_50: 61.3584984733
l_90: 94.8328711277
l_99: 126.211351174
l_999: 158.722406029
After:
l_50: 51.3546011488 (-16%)
l_90: 72.3420731581 (-23%)
l_99: 103.280218974 (-18%)
l_999: 130.905689996 (-17%)
src/core. exec_ctx is now a thread_local pointer of type ExecCtx instead of
grpc_exec_ctx which is initialized whenever ExecCtx is instantiated. ExecCtx
also keeps track of the previous exec_ctx so that nesting of exec_ctx is
allowed. This means that there is only one exec_ctx being used at any
time. Also, grpc_exec_ctx_finish is called in the destructor of the
object, and the previous exec_ctx is restored to avoid breaking current
functionality. The code still explicitly calls grpc_exec_ctx_finish
because removing all such instances causes the code to break.
Vignesh Babu
Craig Tiller
AJ Heller
Esun Kim
Michael Wang
Mark D. Roth
Yash Tibrewal
Vijay Pai
Soheil Hassas Yeganeh
Jan Tattermusch
Noah Eisen
Jan Tattermusch
Yuchen Zeng
ncteisen
murgatroid99