Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Remove subchannel args | Juanli Shen | 2019-01-08 |
| | |||
* | Fix error | Yash Tibrewal | 2018-12-21 |
| | |||
* | Revert changes to Context list cleanup | Yash Tibrewal | 2018-12-20 |
| | |||
* | Fix compiler error | Yash Tibrewal | 2018-12-19 |
| | |||
* | Add error details on context list clearing | Yash Tibrewal | 2018-12-17 |
| | |||
* | Avoid taking refs on the stream by getting a copy of the context | Yash Tibrewal | 2018-12-17 |
| | |||
* | Move security credentials, connectors, and auth context to C++ | Soheil Hassas Yeganeh | 2018-12-13 |
| | | | | | | | This is to use `grpc_core::RefCount` to improve performnace. This commit also replaces explicit C vtables, with C++ vtable with its own compile time assertions and performance benefits. It also makes use of `RefCountedPtr` wherever possible. | ||
* | clang tidy and clang format | ncteisen | 2018-12-07 |
| | |||
* | reviewer feedback | ncteisen | 2018-12-07 |
| | |||
* | Surface socket name | ncteisen | 2018-12-06 |
| | |||
* | Add debug-only tracing to grpc_core::RefCount | Soheil Hassas Yeganeh | 2018-12-01 |
| | | | | | Also, this patch removes the *WithTracing variants in favor of the new API. | ||
* | Explicit conversion | Yash Tibrewal | 2018-11-29 |
| | |||
* | Add a byte counter to chttp2_stream and use that for timestamps | Yash Tibrewal | 2018-11-29 |
| | |||
* | Circumvent padding issues and make traced the second last field | Yash Tibrewal | 2018-11-27 |
| | |||
* | Add traced information to stream op | Yash Tibrewal | 2018-11-27 |
| | |||
* | Move HTTP2 transport and byte stream to grpc_core::RefCount. | Soheil Hassas Yeganeh | 2018-11-27 |
| | | | | | Also, added a TODO to move `grpc_transport` to C++. I believe that's doable, which would requires significant change in all transports. | ||
* | Reviewer comments | Yash Tibrewal | 2018-11-20 |
| | |||
* | Cleanup | Yash Tibrewal | 2018-11-16 |
| | |||
* | Merge master | Yash Tibrewal | 2018-11-16 |
|\ | |||
| * | Eliminate function pointers in hpack_enc(). | Soheil Hassas Yeganeh | 2018-11-05 |
| | | | | | | | | | | | | | | | | | | | | | | | | Using a conditional branch to set a function pointer will prevent the compiler to inline the function and worse it would jump based on a register value killing the pipline. Here is a short example to demonstrate the variants: https://godbolt.org/z/radfZg Remove `add_nothing` and add a lambda when necessary to make sure everything is inlined. | ||
| * | Remeve memset(0) from arena allocated memory. | Soheil Hassas Yeganeh | 2018-11-05 |
| | | | | | | | | | | | | | | Callers are updated to properly initialize the memory. This behavior can be overridden using GRPC_ARENA_INIT_STRATEGY environment variable. | ||
| * | Use correct macro | ncteisen | 2018-11-02 |
| | | |||
| * | Add TODO | ncteisen | 2018-11-01 |
| | | |||
| * | Handle uri parsing in channelz module | ncteisen | 2018-10-31 |
| | | |||
| * | Move uri_parser to lib | ncteisen | 2018-10-31 |
| | | |||
| * | Add AddressType | ncteisen | 2018-10-31 |
| | | |||
| * | supress errors for uri parser | ncteisen | 2018-10-30 |
| | | |||
| * | Move uri_parser to common spot | ncteisen | 2018-10-30 |
| | | |||
| * | Support direct channels peer_string | ncteisen | 2018-10-30 |
| | | |||
| * | reviewer feedback, debuging helper | ncteisen | 2018-10-30 |
| | | |||
| * | Socket tracks remote address | ncteisen | 2018-10-29 |
| | | |||
| * | reviewer commetns | ncteisen | 2018-10-29 |
| | | |||
| * | Merge branch 'master' of https://github.com/grpc/grpc into ↵ | ncteisen | 2018-10-29 |
| |\ | | | | | | | | | | channelz-listen-sockets | ||
| * | | Actually track listening address | ncteisen | 2018-10-29 |
| | | | |||
| * | | Listen sockets track their port | ncteisen | 2018-10-29 |
| | | | |||
| | * | Fix resource quota related leak | Juanli Shen | 2018-10-26 |
| |/ | |||
| * | Merge pull request #16823 from AspirinSJL/rq | Juanli Shen | 2018-10-25 |
| |\ | | | | | | | Account the memory usage of channel and call by resource quota | ||
| * \ | Merge pull request #16979 from yashykt/connector_deadlock | Yash Tibrewal | 2018-10-25 |
| |\ \ | | | | | | | | | Fix deadlock issue in HTTP2 connector | ||
| | | * | Fix OOM by expanding resource quota coverage | Juanli Shen | 2018-10-25 |
| | |/ | |/| | |||
| | * | Add comments about the fix | Yash Tibrewal | 2018-10-25 |
| | | | |||
| | * | Fix deadlock issue in connector | Yash Tibrewal | 2018-10-23 |
| | | | |||
| * | | Merge pull request #16869 from yihuazhang/revert_pollset_set_change | yihuaz | 2018-10-23 |
| |\ \ | | |/ | |/| | Do not pass interested_parties during handshake | ||
| * | | Optimize error handling for special cases. | Soheil Hassas Yeganeh | 2018-10-18 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This commit contains a few improvements: 1. Using a consequetive range of [0..4], will allow us to merge all branches of error_is_special into one comparison. 2. With (1), we can remove the for loops to find entries in error_status_map with a single O(1) lookup. 3. grpc_error_is_special() code paths should be inlined for ref and unref to avoid callq for the majority of cases where speical error is used. 4. grpc_error_get_int() should never accept a nullptr argument to avoid an expensive branch in the hot path. Callers should all allocate a dummy int on the stack when calling. | ||
| * | | Merge pull request #16801 from soheilhy/worktree-slice | Soheil Hassas Yeganeh | 2018-10-15 |
| |\ \ | | | | | | | | | Avoid unnecessary ref/unref calls to get mdelem from slices. | ||
| | * | | Use grpc_mdelem_create() directly. | Soheil Hassas Yeganeh | 2018-10-14 |
| | | | | | | | | | | | | | | | | | | | | Remove grpc_mdelem_from_slices_no_unref() since it's a wrapper around grpc_mdelem_create(). | ||
| | | * | Do not pass interested_parties during handshake | Yihua Zhang | 2018-10-12 |
| | |/ | |/| | |||
| * | | Merge pull request #16792 from ↵ | yihuaz | 2018-10-11 |
| |\ \ | | | | | | | | | | | | | | | | | grpc/revert-16791-revert-16695-pass_pollset_set_tsi_handshaker Revert "Revert "Create and pass pollset_set to ALTS TSI handshaker"" | ||
| * | | | Add skeleton listen socket support | ncteisen | 2018-10-09 |
| | | | | |||
| * | | | Merge pull request #16760 from ncteisen/channelz-server-sockets | Noah Eisen | 2018-10-09 |
| |\ \ \ | | | | | | | | | | | Channelz Part 8: Get Server Sockets | ||
| | | | * | Avoid unnecessary ref/unref calls to get mdelem from slices. | Soheil Hassas Yeganeh | 2018-10-07 |
| | |_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | grpc_mdelem_from_slices() unref's the key and value. As a result, in quite a few cases on the hot path, we first ref slice, so that grpc_mdelem_from_slices() can unref them. Add grpc_mdelem_from_slices_no_unref() which does not unref() the input slices. This cuts 0.5% - 1.0% across app benchmarks. |