Craig Tiller
d720d5dd0a
Track zalloc times in microbenchmark
...
This forms our speed of light for call creation: at some point call
creation is dominated by zeroing memory and all we can do is reduce the
size of the call... let's track where that point is.
8 years ago
Craig Tiller
71c286466a
Dont use memory counters unless counters mode is on
8 years ago
Jan Tattermusch
0cb7fef406
Revert "Split bm_fullstack into pieces, reuse infrastructure across other microbenchmarks"
8 years ago
ncteisen
55337bb317
Error arena optimization
8 years ago
Yuxuan Li
bdc76ab37b
bug fix
8 years ago
Yuxuan Li
34894e4b1c
Implemented stream coalescing design
...
(RFC:https://github.com/grpc/proposal/pull/3 ). Add necessary
microbenchmarks to show reduced writes/iter for short streams. Add
necessary end2end test to test out newly added apis. Filter those tests
using *WithCoalescingApi*.
8 years ago
Craig Tiller
12352b2c5c
Add test of server builder, including channel args
8 years ago
Craig Tiller
b094b2c31e
Actually print error message
8 years ago
Yuchen Zeng
f0d6b88626
Avoid repetitive division calculations
8 years ago
Craig Tiller
8918aaeccd
Document status ordering rules
...
This documents a rule that's existed in a hard to find internal document
that's existed since Feb 2016 by abhikumar@google.com .
Since that rule is critical to untangling some gRPC C core behavior, we
should document it publically.
8 years ago
Yuchen Zeng
c65120526a
Use gpr_subprocess in fling_stream_test
8 years ago
Craig Tiller
e067b6e119
Resolve sanity failures
8 years ago
Craig Tiller
111db946b7
Add a test of creating a call on a lame channel in C++
8 years ago
yang-g
d0084c220e
Include x.pb.h instead of x.grpc.pb.h for message-only protos
8 years ago
Craig Tiller
055abd65fb
Fix linux
8 years ago
Craig Tiller
ab314ee9a6
Add some pollset benchmarks
8 years ago
Craig Tiller
f09ec59222
Fix mac build
8 years ago
Craig Tiller
1128d462c3
Pollset benchmark
8 years ago
Craig Tiller
cc928d6b71
Cleanup
8 years ago
Craig Tiller
52bd441b25
Get back trickle
8 years ago
Craig Tiller
12d22e472b
Further splitting
8 years ago
Craig Tiller
62ac65b183
Split bm_fullstack unary ping pong out
8 years ago
Craig Tiller
627a59892a
Prep for splitting bm_fullstack
8 years ago
Craig Tiller
e4a2419597
Bugfixes
8 years ago
Craig Tiller
5e3215338f
Move helpers to a common place, use them everywhere
8 years ago
Craig Tiller
19e6b88af0
Include build env
8 years ago
Yuchen Zeng
67951aaf5e
Avoid using oversized frames
8 years ago
Yuchen Zeng
5ede0e07a7
Use macros instead of const variables
8 years ago
ncteisen
ffe4f5e084
Fix mem leak in error_test
8 years ago
Yuchen Zeng
38c10bd6d9
Avoid variable length arrays
8 years ago
Yuchen Zeng
39514ccb29
Add licenses() in BUILD files
8 years ago
Eric Gribkoff
11a4ed80d6
refactor client
8 years ago
Eric Gribkoff
caf7ea53be
Enable C++ negative http2 test
8 years ago
Craig Tiller
8174cceb14
Generate CSV file
8 years ago
ncteisen
f8a7d93a2c
Fix mem leak in error_test
8 years ago
Craig Tiller
295df6da9a
Add a slice type that shares a refcount with a transport stream
8 years ago
Craig Tiller
2bfc3bcf8d
Add fixtures for call creation benchmarks
8 years ago
Yuchen Zeng
b4b6a0e5e1
Retry sending pings if they are delayed
8 years ago
Craig Tiller
7bc4d3edd8
Revert unnecessary change
8 years ago
Vijay Pai
24992060c8
Finish streams that error. Don't histogram failed ops.
...
Fail on failed write
8 years ago
Craig Tiller
a7ed26885c
Fix some bugs
8 years ago
Craig Tiller
7acc37e502
Trim deadline setting out of call creation path: reduces ClientChannelFilter init/destroy from 128ns to 46ns on my machine
8 years ago
Craig Tiller
b73ad23bd8
Fix memory leak
8 years ago
Matt Kwong
d9b257a154
Add fuzzer options for oss-fuzz
8 years ago
Matt Kwong
c5b3b25f8d
Change ssl_server_fuzzer.c to use ssl_test_data.h instead of loading mock SSL data from file
8 years ago
Yuchen Zeng
e0b1e46f0d
Address review comments
8 years ago
Craig Tiller
b843ff2ce4
Add more cq benchmarks
8 years ago
Craig Tiller
edbf2b9d13
Add a spinlock type.
...
Useful for situations where we need to repeatedly trylock, not useful
for cases where we need to lock (due to spinning).
Add a variant of sync_test to test it (with the same tests we run for
gpr_mu).
Add a benchmark to bm_closure to demonstrate single threaded performance.
8 years ago
Yuchen Zeng
efdf5a3903
Update with the new ping implementation
8 years ago
Yuchen Zeng
990d9fe146
Client-side keepalive ping
...
Based on soltanmm-google's #9114
8 years ago