649c95eadc
Make sure to get all PHP dependences set up properly
2017-09-12 11:42:47 -07:00
f9da3a7bc4
Start setting up files for autorun of php_to_cpp qps tests
2017-09-12 11:42:47 -07:00
f11a40d23b
Upload core stats to qps_test
2017-09-12 10:54:20 -07:00
f97a4836d5
Merge github.com:grpc/grpc into tpcq
2017-09-11 12:17:13 -07:00
2426163b31
Switch to three threads per cq for unconstrained benchmarks
2017-09-08 16:12:05 -07:00
ebec0dba9f
Select better arguments
2017-09-07 12:47:35 -07:00
0fda880c75
Enable epoll1
2017-08-30 20:34:51 -07:00
3d3403d3a8
Update the scenario result schema
2017-07-24 19:44:01 -07:00
1cb30c2764
Merge github.com:grpc/grpc into min_stack
2017-07-12 15:44:10 -07:00
bb3d95b643
Use https://grpc.io consistently as the canonical URL
2017-07-10 22:24:28 +00:00
1d85332481
Merge pull request #11532 from ctiller/optimize_for
...
Allow application optimization targets to be hinted to grpc (prefer latency over throughput for now)
2017-07-06 15:35:12 -07:00
e9089624fe
Merge pull request #11627 from murgatroid99/node_consistent_runtime_version
...
Make various scripts use the same version of Node
2017-07-05 10:26:56 -07:00
8551e4d687
Merge github.com:grpc/grpc into min_stack
2017-07-05 09:30:36 -07:00
a1a3f363ee
Merge github.com:grpc/grpc into optimize_for
2017-07-05 08:37:09 -07:00
7ad758cd84
Make various scripts use the same version of Node
2017-06-27 13:54:22 -07:00
58ca8beb16
add script for patching perf benchmark schema
2017-06-27 13:45:46 +02:00
3598ac81b0
update scenario result schema
2017-06-27 12:49:40 +02:00
f1633a9bec
Allow application optimization targets to be hinted to grpc (prefer latency over throughput for now)
2017-06-19 10:01:52 -07:00
4536138eef
disable unconstrained_1cq test
2017-06-15 09:38:52 -07:00
c8e7a52fc7
Merge remote-tracking branch 'origin/master' into HEAD
2017-06-13 02:52:13 +00:00
7897ae9308
auto-fix most of licenses
2017-06-08 11:22:41 +02:00
ed32b78778
Switch node_to_cpp unary benchmark to async
2017-06-01 10:44:39 -07:00
648832fd28
Enable more Node performance tests, fix streaming test implementation
2017-05-23 17:20:38 -07:00
fba000c8ec
Reduce outstanding RPCs for 1cq tests
2017-05-23 14:17:17 -07:00
4b07aab513
Support multiple threads per cq sharing, add tests
2017-05-23 09:20:56 -07:00
248e90196c
Merge github.com:grpc/grpc into min_stack
2017-05-11 12:21:44 -07:00
f6f28a781d
Add 2 new scenarios for better bw measurement
2017-05-09 10:31:48 -07:00
98a501f435
Reduce concurrent RPCs for single-core tests since some were timing out
...
or otherwise taking long to complete
2017-05-08 11:23:06 -07:00
ea4adc1508
Merge pull request #10313 from vjpai/onesided
...
Add QPS tests for 1-sided unconstrained streaming
2017-05-05 11:24:07 -07:00
c2ad372d43
Merge pull request #10912 from dgquintas/trying-to-fix-stuff
...
Upmerge from 1.3.0 to master
2017-05-04 10:44:03 -07:00
eea8cf0fe3
Add QPS tests for one-sided streaming
2017-05-02 09:26:12 -07:00
aba4ee2f76
add C# generic insecure scenarios
2017-05-02 10:23:40 +02:00
277b1fa361
Enable minimal stack for insecure tests
2017-04-26 08:31:47 -07:00
bac1c1b6bf
Removed another couple of uses of '--iomgr_platform=uv'
2017-04-25 10:20:37 -07:00
bf33410411
Add Node and Express benchmarks for various response sizes
2017-04-18 11:11:28 -07:00
58aa2cb8f1
fix 1MB perf scenarios
2017-04-07 13:54:51 +02:00
500e361826
Merge pull request #10416 from murgatroid99/node_performance_tests
...
Node performance tests and improvements
2017-04-04 17:05:22 -07:00
45a9abae95
Add option to limit # of messages per stream with tests
2017-04-03 14:24:53 -07:00
ef0b2ed1c3
Merge pull request #10380 from jtattermusch/ping_pong_1mb
...
Add 1MB ping pong scenarios
2017-04-03 18:02:49 +02:00
59f036dc52
Merge pull request #9875 from vjpai/unary
...
Synthetic benchmark for coordinator-worker workload
2017-03-31 16:05:58 -07:00
09ed43f1d1
Merge pull request #10311 from apolcyn/doc_perf_tests
...
add doc for perf qps tests with steps for running
2017-03-31 12:13:49 -07:00
a1eefcea5f
Improve Node benchmarks, add generic unary test
2017-03-31 11:17:28 -07:00
47fc606d11
Performance model of coordinator-worker use case
2017-03-31 11:03:16 -07:00
46df13b4a3
add 1mb ping pong scenarios
2017-03-31 10:32:23 +02:00
05222512d7
Add C++ large message tests to PRs and master
2017-03-30 10:18:29 -07:00
679981069d
add notes to build and run workers in different languages
2017-03-29 21:37:04 -07:00
b9d9512d8a
Doc perf tests
2017-03-29 10:13:20 -07:00
264a210878
Merge pull request #10115 from thunderboltsid/update-run-tests-scripts-to-python3.x
...
Make testing scripts python3.x compatible.
2017-03-13 22:38:12 -07:00
8e64d901fd
Modify shebang on python scripts
...
Change shebangs to `#!/usr/bin/env python` instead of
`#!/usr/bin/env python2.7`.
2017-03-12 19:53:12 +01:00
d194f59939
Make testing scripts python3.x compatible
...
Update run_tests/*.py to use six based isomorphisms and print function
from __future__ module.
2017-03-12 17:47:53 +01:00
a582defdad
Temporarily disable resource quota QPS tests
2017-03-10 13:05:08 -08:00
8a0ec8866e
Merge remote-tracking branch 'upstream/v1.1.x' into 1.1.x_to_master
2017-03-03 17:04:45 -08:00
faaa8b8913
Disable node_protobuf_async_unary_qps_unconstrained benchmark test
2017-03-02 10:50:34 -08:00
98cdf3b3e6
Merge remote-tracking branch 'upstream/v1.1.x' into merge_1.1.x_master
2017-02-23 14:59:45 -08:00
1191b7202d
Improve Node and libuv testing and test coverage
...
Allow Node tests to run with or without UV, change default version to 7, add some portability tests. Also make some more core tests work with libuv
2017-02-17 12:10:26 -08:00
f797c65160
make the change in scenario config rather than c#
2017-02-09 11:22:49 -08:00
c6e333e25b
add missing return statement
2017-02-03 09:31:31 -08:00
6b446b601e
Merge branch 'master' into poll-cv-disable
2017-01-30 09:17:12 -08:00
70d9ca402a
Excluded async_client_sync_server_* tests for poll-cv engine since it
...
sometimes get stuck (or extremely slow).
(https://github.com/grpc/grpc/issues/8545 ) created to debug poll-cv
issues with async_client_sync_server perf tests
2017-01-27 10:54:05 -08:00
faa835c308
Add message sizes to sweeps
2017-01-18 15:28:44 -08:00
412fa2a0b7
Support setting request, response size
2017-01-18 15:21:54 -08:00
44e907af0e
Merge pull request #9322 from apolcyn/deprecate_benchmark_core_lists
...
Don't configure core lists in in benchmark driver
2017-01-17 17:30:41 -08:00
a6e796f58f
ignore core counts and core lists in qps json driver
2017-01-11 13:49:43 -08:00
ac87a46225
enable uploading server cpu usage data from performance tests to big query
2017-01-11 10:01:16 +00:00
9f08d110f8
add a "perf" option to benchmarks script, generate profile text reports and flamegraphs
2016-12-08 16:03:19 -08:00
2de47cba05
enable running windows perf tests
2016-11-16 18:46:18 +01:00
1731a41cff
Merge branch 'master' into node_express_run_perf_tests
2016-11-09 17:14:08 -08:00
e8f9cbbd68
Remove some disabled copied Node Express perf tests
2016-11-09 17:13:45 -08:00
d885a27ccb
fix repeated field
2016-11-09 15:46:06 -08:00
317f60b98e
add a blank line back
2016-11-09 15:08:26 -08:00
2b4d372620
hiding totalCpuTime and idleCpuTime from ServerStatus proto message
2016-11-09 15:06:00 -08:00
9ba52e7aa9
unblock the performance tests. hide the cpu usage field for now.
2016-11-09 14:45:25 -08:00
dabe6bd2af
Enable Node Express benchmarks, fix copy/paste errors
2016-11-09 11:03:32 -08:00
c939022dd5
More data massaging
2016-11-01 15:47:24 -07:00
ed531b8e82
More data massaging
2016-11-01 10:27:18 -07:00
77fbc1ca2a
Fix some typos
2016-10-31 14:04:03 -07:00
263459577a
Merge pull request #8583 from ctiller/new_fields
...
Add some fields to bigquery
2016-10-31 13:04:00 -07:00
bd3ab19a95
Add some fields to bigquery
2016-10-31 12:53:40 -07:00
bba5285df0
Merge github.com:grpc/grpc into buffer_pools_for_realsies
2016-10-27 22:23:27 -07:00
51fc01dffa
Merge pull request #8419 from murgatroid99/node_express_benchmark
...
Add benchmark client and server for Node Express
2016-10-27 17:43:03 -07:00
eebc8c8600
Merge pull request #8498 from sreecha/sync_streaming
...
New streaming perf scenario for sync server
2016-10-27 14:47:18 -07:00
3d357d901c
Merge github.com:grpc/grpc into buffer_pools_for_realsies
2016-10-26 20:52:03 -07:00
a83ee60b93
New streaming scenario
2016-10-25 14:08:02 -07:00
fe8c5012d3
Merge github.com:grpc/grpc into buffer_pools_for_realsies
2016-10-24 14:49:18 -07:00
b516cadc2a
Merge branch 'master' into uv_core_transport
2016-10-21 15:54:42 -07:00
b73a654450
Merge branch 'master' into new_scenario
2016-10-20 11:19:45 -07:00
59f347e125
Merge branch 'master' into uv_core_transport
2016-10-19 13:53:21 -07:00
b53e5d1f2b
Create benchmark client and server for Node Express
2016-10-18 09:55:28 -07:00
50d6f7b60f
Merge github.com:grpc/grpc into buffer_pools_for_realsies
2016-10-18 09:54:51 -07:00
20afa3d7c9
BufferPool --> ResourceQuota
2016-10-17 14:52:14 -07:00
bba2f47e8f
remove formatting noise
2016-10-17 14:42:16 -07:00
34ad82d6f6
Merge branch 'master' into new_scenario
2016-10-17 14:15:50 -07:00
d13fbca136
switch C# benchmark to coreclr
2016-10-14 16:44:49 +02:00
fde76d7996
Merge branch 'master' into uv_core_transport
2016-10-07 15:09:53 -07:00
1bb0ce5e23
Merge branch 'direct-calls' into buffer_pools_for_realsies
2016-10-03 12:58:02 -07:00
c9742d37ac
Merge pull request #8202 from ctiller/perf-wha
...
Be explicit as to which tests to run
2016-10-03 10:56:21 -07:00
0c80c7d12c
Collecting failure status progress
2016-09-28 16:30:55 -07:00
923d641c27
Add a new scenario: Async-Client/Sync-Server
2016-09-26 19:32:17 -07:00
677966a257
Be explicit as to which tests to run
2016-09-26 07:37:28 -07:00
08b0fab426
Merge branch 'master' into uv_core_transport
2016-09-23 14:35:49 -07:00
601cff4018
More programmatically generate scenarios
2016-09-19 07:30:45 -07:00
bcc60f75d4
Merge branch 'master' into uv_core_transport
2016-09-16 13:44:28 -07:00
bf4939fd22
Extend sweeps further, add streaming
2016-09-16 13:41:00 -07:00
232ca0275e
Removed unnecessary notes from scenario_config.py
2016-09-16 13:30:19 -07:00
9030c81f20
Add a libuv endpoint to the C core, for use in the Node library
2016-09-16 13:25:08 -07:00
8c985c2866
Allow more sync threads
2016-09-16 11:25:32 -07:00
5709469c46
Fix sync/async
2016-09-16 11:22:42 -07:00
86cf6dcb1c
Remove some scenarios we can't run yet
2016-09-13 10:33:29 -07:00
0c98675e54
Fix outstanding calls
2016-09-13 10:01:26 -07:00
1423a63db9
Lets not do payload sweeps just yet
2016-09-13 09:54:21 -07:00
b6df24765f
Properly categorize tests to allow sweeps to be run by adhoc
2016-09-13 09:41:26 -07:00
c5aa700538
Significantly increase sweep space
2016-09-13 09:36:09 -07:00
6c38c1be30
Reduce outstanding request count
2016-09-13 08:34:27 -07:00
15372a3f22
Use a # of total outstanding requests to drive benchmark config
...
Instead of specifying # of outstanding requests/channel, specify a total
outstanding size, and try to fit that to the number of channels.
2016-09-08 09:21:55 -07:00
4f2d9ae8e2
Add sync variants of important tests, add sweeps across different channel counts
2016-07-17 14:07:18 -07:00
6dbfce0a9d
Add clientSuccess and serverSuccess to BQ schema
2016-07-15 11:05:24 -07:00
45c0f2b305
Migrated python performance tests to use GA API
2016-07-06 19:26:09 -07:00
3b5b20682b
Make running individual Python tests less painful
...
Before this change, running Python tests individually required
building a tox environment via the run_tests script and then specifying
long environment variables to filter out just the test we wanted to run
(and then we wouldn't be able to get the output on interrupt, nor would
we have an easy way of determining the PID of the process for debugger
attachment). Now invoking the build_python.sh script creates a workable
python virtual environment that includes all necessary libraries and
tests (s.t. running a single test is now possible by just knowing the
module name). This does not change existing supported means of running
tests (e.g. through run_tests.py).
An additional way of running individual tests has been introduced.
Following invocation of `./tools/run_tests/build_python.sh` (or
run_tests.py), one may invoke
./$VENV/bin/python -m $TEST_MODULE_NAME
and acquire a single running process that *is* the test process (rather
than a parent of the process). $VENV is the virtual environment name
specified to `build_python.sh` (defaults to `py27`) and
$TEST_MODULE_NAME is what it says on the tin.
2016-07-01 10:18:45 -07:00
1ff429da2a
Organize Python tests to use grpcio-tools directly
...
Moves all tests into a separate package. This does not change existing
supported means of running tests (e.g. through run_tests.py).
2016-07-01 10:18:45 -07:00
a286b040a9
small fixes
2016-06-13 15:20:39 +00:00
9a36e6c7cd
Changed Python Sync streaming qps to follow spec
2016-06-07 17:49:03 -07:00
571c12ef18
Remove AsyncStreaming client from python qps tests
2016-06-06 23:13:27 -07:00
28f6c01d76
Revert "Revive C++ large-message throughput tests"
2016-05-22 21:23:43 -04:00
33b7361126
Merge pull request #6661 from vjpai/throughput_fix
...
Revive C++ large-message throughput tests
2016-05-22 17:29:05 -04:00
3fe694fa35
Revive throughput tests .
2016-05-19 17:51:45 -07:00
d27888b6db
mark unconstrained scenarios with scalable category
2016-05-19 16:15:01 -07:00
5cbccd0781
set client params differently for sync and async client
2016-05-13 16:26:42 -07:00
37a907e471
add support for CLIENT_LANGUAGE setting
2016-05-13 15:09:32 -07:00
649d126ed3
set GOPATH when executing go worker
2016-05-11 12:26:39 -07:00
4bd3a7cecb
change go scenarios to use sync api
2016-05-11 09:37:12 -07:00
3b59b0f417
integrate Go qps worker
2016-05-11 09:37:12 -07:00
594ff2054a
Merge pull request #6524 from kpayson64/qps_improvements
...
Added true async qps streaming client
2016-05-11 09:11:24 -07:00
7363674e11
Merge pull request #6477 from jtattermusch/benchmarking_add_netperf
...
Add support for running netperf as part of benchmarks.
2016-05-10 20:33:02 -07:00
1eb8d54a19
Added true async qps client
2016-05-10 16:57:14 -07:00
6de6971bdc
explicitly specify request and response size for netperf
2016-05-10 14:33:21 -07:00
4de2c3254b
add support for running netperf scenario
2016-05-10 14:33:07 -07:00
92d9106a35
dont use corelimit for throughput tests
2016-05-10 11:53:19 -07:00
16713b91cc
enable previously disabled C# scenarios
2016-05-09 15:42:32 -07:00
abd1b38885
comment out the right scenario
2016-05-08 18:47:40 -07:00
ed4c3f17dd
disable some C# scenarios
2016-05-06 15:39:08 -07:00
427699b638
mark some scenarios as smoketest and add a cmdline flag
2016-05-05 18:10:35 -07:00
a21c7e9207
add support for scenario categories
2016-05-05 18:10:35 -07:00
d7b162f601
add some more scenarios
2016-05-05 16:16:12 -07:00
957fe8dc5d
Updated a couple more scripts
2016-05-02 15:03:55 -07:00
501ca57665
kill pending python workers on start
2016-04-29 09:35:44 -07:00
b8c44438b3
Merge pull request #6298 from grpc/python_qps_tests
...
Python QPS Tests
2016-04-28 21:48:13 -07:00
0482c1046b
Python QPS Worker/initial scenarios
2016-04-28 20:01:06 -07:00
1408920ab9
get rid of local qpsworkers before starting the tests
2016-04-27 18:26:53 -07:00
ab8b9f5143
Merge pull request #6271 from jtattermusch/temporarily_disable_csharp_qps_unconstrained
...
temporarily disable csharp_protobuf_async_streaming_qps_unconstrained
2016-04-23 07:30:26 -07:00
fa8d5b3ef7
temporarily disable csharp_protobuf_async_streaming_qps_unconstrained
2016-04-22 16:23:44 -07:00
Vijay Pai