aboutsummaryrefslogtreecommitdiffhomepage
path: root/src/core/lib/transport/bdp_estimator.h
Commit message (Collapse)AuthorAge
* Change trace logging to use GPR_INFO instead of GPR_DEBUG.Gravatar Mark D. Roth2018-04-25
|
* Revert "Revert "All instances of exec_ctx being passed around in src/core ↵Gravatar Yash Tibrewal2017-12-06
| | | | removed""
* Revert "All instances of exec_ctx being passed around in src/core removed"Gravatar Yash Tibrewal2017-12-06
|
* Merge masterGravatar Yash Tibrewal2017-11-21
|\
| * Merge branch 'master' of https://github.com/grpc/grpc into tracing++Gravatar ncteisen2017-11-10
| |\ | | | | | | | | | Lot's of manual work to make this merge work
* | \ Merge with masterGravatar Yash Tibrewal2017-11-09
|\ \ \ | | |/ | |/|
| * | Update clang-format to 5.0Gravatar Craig Tiller2017-11-03
| | |
* | | Removing instances of exec_ctx being passed around in functions inGravatar Yash Tibrewal2017-10-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
| | * Better nameGravatar Craig Tiller2017-10-18
| | |
| | * Merge github.com:grpc/grpc into tracerGravatar Craig Tiller2017-10-18
| | |\ | | |/ | |/|
| * | Reflow to remove boolGravatar Craig Tiller2017-10-18
|/ /
| * C++ize tracingGravatar Craig Tiller2017-10-16
| |
* | Merge github.com:grpc/grpc into timerGravatar Craig Tiller2017-10-13
|\|
| * include port_platform.h for bdp estimatorGravatar Yash Tibrewal2017-10-13
| |
* | Merge branch 'chttp2_timer' into timerGravatar Craig Tiller2017-10-12
|\|
| * Fix compilationGravatar Craig Tiller2017-10-12
| |
* | Fix testGravatar Craig Tiller2017-10-09
| |
* | Have BDP estimator schedule timersGravatar Craig Tiller2017-10-08
|/
* Missing destructorGravatar Craig Tiller2017-10-08
|
* Const correctnessGravatar Craig Tiller2017-10-08
|
* C++ize BDP estimator, introduce ManualConstructorGravatar Craig Tiller2017-10-08
|
* Merge github.com:grpc/grpc into flowctl+millisGravatar Craig Tiller2017-10-05
|\
| * Changes for C to C++. Adding extern C to header files for compatibility.Gravatar Yash Tibrewal2017-10-02
| |
* | FixesGravatar Craig Tiller2017-10-02
| |
* | Squash ping queues, make BDP pings non-initiating, make BDP queries ↵Gravatar Craig Tiller2017-09-15
|/ | | | speedup/slowdown
* Pull bdp estimation into flowctl moduleGravatar ncteisen2017-08-13
|
* auto-fix most of licensesGravatar Jan Tattermusch2017-06-08
|
* Merge pull request #10930 from ncteisen/frame-sizeGravatar Noah Eisen2017-05-18
|\ | | | | Set Frame Size to Bytes per Microsecond
* \ Merge github.com:grpc/grpc into uberpollGravatar Craig Tiller2017-05-07
|\ \
| | * Set frame size to B/usGravatar ncteisen2017-05-04
| |/
* | Fix ASAN/TSAN failuresGravatar Craig Tiller2017-05-03
| | | | | | | | | | | | - trace system is now thread safe when run with TSAN - fix a race in client_auth_filter.c - allow timer manager to run in single threaded mode for fuzzers
| * Use bandwidth estimate to stop increasing bdp estimate (avoids buffer bloat ↵Gravatar Craig Tiller2017-04-19
|/ | | | spiral of death)
* Sanity fixesGravatar Craig Tiller2017-03-29
|
* Bug fixes, tracing for bdp estimationGravatar Craig Tiller2017-01-27
|
* PID controller stabilizationGravatar Craig Tiller2016-12-29
|
* Ping progressGravatar Craig Tiller2016-12-29
|
* Cleanup ping story: part 0Gravatar Craig Tiller2016-12-28
|
* Add estimator testGravatar Craig Tiller2016-10-20
|
* Complete code (no tests yet)Gravatar Craig Tiller2016-10-20
|
* Initial sketch of bdp estimatorGravatar Craig Tiller2016-10-20