Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Fix end2end leaks | Craig Tiller | 2015-02-12 |
| | |||
* | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-12 |
|\ | |||
| * | Added useful behavior for empty batch | murgatroid99 | 2015-02-12 |
| | | |||
* | | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-12 |
|\| | |||
| * | Fix race in call.c | murgatroid99 | 2015-02-12 |
| | | |||
* | | Multi-completion-queue-server | Craig Tiller | 2015-02-12 |
| | | | | | | | | | | | | Allow binding a different completion queue to each registered method. This will allow multiplexing for the C++ server between sync & async methods more easily. | ||
* | | Finish streaming, lame client | Craig Tiller | 2015-02-11 |
| | | |||
* | | Remove debug | Craig Tiller | 2015-02-11 |
| | | |||
* | | Some streaming progress | Craig Tiller | 2015-02-11 |
| | | |||
* | | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-11 |
|\| | |||
| * | Merge pull request #475 from dklempner/epoll | Craig Tiller | 2015-02-11 |
| |\ | | | | | | | Epoll based multipoller | ||
* | | | Fix server shutdown issues | Craig Tiller | 2015-02-11 |
| | | | | | | | | | | | | First end2end test passes | ||
| | * | Destroy the wakeup fd in the right function | David Klempner | 2015-02-11 |
| | | | |||
* | | | Fix hash table | Craig Tiller | 2015-02-11 |
| | | | |||
* | | | Fix race | Craig Tiller | 2015-02-11 |
| | | | |||
| * | | Freeing the proper string in gpr_tmpfile. | Nicolas Noble | 2015-02-11 |
| | | | | | | | | | | | | | | | | | | Fixes #478. (oops) | ||
| * | | Merge pull request #489 from jtattermusch/cpu_windows | Nicolas Noble | 2015-02-11 |
| |\ \ | | | | | | | | | Added placeholder for cpu_windows.c implementation | ||
| | * | | added log messages for cpu_windows.c | Jan Tattermusch | 2015-02-11 |
| | | | | |||
| | * | | added cpu_windows.c | Jan Tattermusch | 2015-02-11 |
| | | | | |||
| * | | | Merge pull request #471 from jboeuf/call_host_name_check | Nicolas Noble | 2015-02-11 |
| |\ \ \ | | |/ / | |/| | | Adding call host (:authority header) check in the secure channel. | ||
| | | * | Clean up the epoll wakeup fd too. | David Klempner | 2015-02-11 |
| | | | | |||
| | | * | Address pull request thread comments | David Klempner | 2015-02-11 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | 1. Close the epoll_fd at destroy 2. Finish the comment about signal/broadcast on the cv 3. Rename GPR_POSIX_MULTIPOLL_WITH_EPOLL to GPR_LINUX_MULTIPOLL_WITH_EPOLL | ||
* | | | | Fix typo causing crash | Craig Tiller | 2015-02-11 |
| | | | | |||
| | | * | Remove now unnecessary check that incoming epoll fds are not orphaned | David Klempner | 2015-02-11 |
| | | | | |||
| | | * | Merge branch 'master' into epoll | David Klempner | 2015-02-11 |
| | | |\ | | |_|/ | |/| | | |||
* | | | | Just use one completion queue per server for delivering completions | Craig Tiller | 2015-02-11 |
| | | | | | | | | | | | | | | | | | | | | This simplifies (drastically) the polling story, although will slightly complicate mixing sync & async servers - but we're not there yet. | ||
* | | | | Implement FinalizeResult | Yang Gao | 2015-02-11 |
| | | | | |||
* | | | | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-11 |
|\| | | | |||
| * | | | Merge pull request #448 from nicolasnoble/grpc-win32 | Craig Tiller | 2015-02-11 |
| |\ \ \ | | | | | | | | | | | Windows port of iomgr. | ||
* | | | | | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-11 |
|\| | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: test/cpp/qps/server.cc | ||
| | | | * | Epoll based multipoller | David Klempner | 2015-02-10 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a multipoller based on epoll rather than poll. Note that this implementation is aimed at correctness rather than performance, although it should immediately have better scalability to large numbers of FDs, both due to epoll's O(1) sized API and due to not needing to wake up polling threads to do interest set changes. One notable difference here is that we directly attach a wakeup fd rather than using the freelisting kick mechanism that the poll() based implementations use, because modifying the epoll set to use a different kick fd each time isn't free. | ||
| * | | | | Have unary pollset check to see if the existing fd is orphaned | David Klempner | 2015-02-10 |
| | |_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | This avoids an unnecessary upgrade to multipoller if there was no do_work called between an orphan and a subsequent add. Additionally, it avoids the need for epoll based multipoller to check for this case in its upgrade code by ensuring all existing fds are valid at upgrade time. | ||
* | | | | Allow two completion queues on request call | Craig Tiller | 2015-02-10 |
| | | | | | | | | | | | | | | | | | | | | One for the new rpc notification, the other is bound to the new call. This will make async c++ soooo much easier. | ||
* | | | | First draft registered methods | Craig Tiller | 2015-02-10 |
| | | | | |||
| * | | | Merge pull request #428 from ctiller/clientlock2 | Nicolas Noble | 2015-02-10 |
| |\ \ \ | | | | | | | | | | | Work towards removing some contention | ||
| | | | * | Adding call host (:authority header) check in the secure channel. | Julien Boeuf | 2015-02-10 |
| | |_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | - Fixes #405. - This change is not tested as it should (only end to end and no negative testing). Will do better when we have testing framework for filters. | ||
* | | | | Remove dead code | Craig Tiller | 2015-02-10 |
| | | | | |||
* | | | | Rewrite server request startup path | Craig Tiller | 2015-02-10 |
| | | | | | | | | | | | | | | | | | | | | Stub in registered methods, cleanup to the point I understand this code again. | ||
* | | | | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-10 |
|\| | | | |||
| * | | | Correctly handle large headers in HPACK table | Craig Tiller | 2015-02-10 |
| | | | | | | | | | | | | | | | | | | | | | | | | I missed a clause in section 4.4 of the HPACK spec when implementing this stuff. Removes an errant assert and correctly handles adding large entries to the HPACK table by flushing it and leaving it empty. | ||
* | | | | Merge github.com:grpc/grpc into c++api | Craig Tiller | 2015-02-10 |
|\| | | | |||
| | | * | Rewording comment :-) | Nicolas "Pixel" Noble | 2015-02-10 |
| | | | | |||
| * | | | Return OK on server if there's no explicit status set | Craig Tiller | 2015-02-09 |
| | | | | | | | | | | | | | | | | Fixes #451 | ||
| | | * | Merge cleanup. | Nicolas Noble | 2015-02-09 |
| | | | | |||
| | | * | Merge branch 'master' of github.com:google/grpc into grpc-win32 | Nicolas "Pixel" Noble | 2015-02-10 |
| | | |\ | | |_|/ | |/| | | |||
| | | * | Addressing comments. | Nicolas Noble | 2015-02-10 |
| | | | | |||
* | | | | Fix include paths | Craig Tiller | 2015-02-09 |
| | | | | |||
* | | | | Progress | Craig Tiller | 2015-02-09 |
|/ / / | |||
| * | | Reduce contention on lock | Craig Tiller | 2015-02-09 |
| | | | | | | | | | | | | Change the fd watcher from being O(active_pollers) to O(1), reducing time spent under the fd->watcher_mu lock, and ultimately scaling us much better. | ||
| * | | Add missing unlock | Craig Tiller | 2015-02-08 |
| | | |