Arjun Roy
|
b6514a6438
|
Merge pull request #19487 from arjunroy/static_md_idx_v2
Pre-compute static metadata index for hpack_encoder.
|
5 years ago |
|
Arjun Roy
|
d527c1fbda
|
Pre-compute static metadata index for hpack_encoder.
Originally, hpack_encoder would check if a metadata was static or not by
comparing its pointer to the known static metadata global table and checking if
it was within bounds. This check was performed regardless of if the metadata was
static or not, and is somewhat costly.
Instead, we now pre-compute the static metadata index during code generation
time, and store it with static metadata objects. We read that value only if we
are dealing with a static metadata flag (which we know from the storage type of
the grpc_mdelem).
This yields slightly faster metadata encoding:
BM_HpackEncoderEncodeHeader<EmptyBatch>/0/16384
[framing_bytes/iter:9 header_bytes/iter:0 ] 34.9ns ± 2%
34.2ns ± 1% -2.04% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<EmptyBatch>/1/16384
[framing_bytes/iter:9 header_bytes/iter:0 ] 34.9ns ± 2%
34.2ns ± 1% -2.01% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleStaticElem>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.6ns ± 0%
49.2ns ± 2% -2.74% (p=0.000 n=18+20)
BM_HpackEncoderEncodeHeader<SingleInternedKeyElem>/0/16384
[framing_bytes/iter:9 header_bytes/iter:6 ] 84.7ns ± 1%
83.5ns ± 1% -1.43% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<SingleInternedElem>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.4ns ± 0%
47.9ns ± 0% -4.83% (p=0.000 n=18+17)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<1, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 51.1ns ± 2%
48.9ns ± 1% -4.32% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<3, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.8ns ± 2%
48.8ns ± 2% -3.88% (p=0.000 n=19+20)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<10, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.2ns ± 1%
47.9ns ± 0% -4.47% (p=0.000 n=19+16)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<31, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.2ns ± 0%
47.9ns ± 0% -4.46% (p=0.000 n=18+16)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<100, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.2ns ± 0%
47.9ns ± 0% -4.40% (p=0.000 n=19+17)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<1, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.7ns ± 2%
48.8ns ± 2% -3.81% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<3, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.9ns ± 2%
48.8ns ± 2% -4.05% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<10, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.1ns ± 0%
48.0ns ± 1% -4.27% (p=0.000 n=17+17)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<31, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.1ns ± 0%
48.0ns ± 1% -4.28% (p=0.000 n=18+17)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<100, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.1ns ± 0%
48.0ns ± 0% -4.33% (p=0.000 n=18+17)
BM_HpackEncoderEncodeHeader<SingleNonInternedElem>/0/16384
[framing_bytes/iter:9 header_bytes/iter:9 ] 91.4ns ± 1%
90.7ns ± 1% -0.79% (p=0.000 n=18+20)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<1, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:12 ] 116ns ± 1%
116ns ± 1% -0.46% (p=0.002 n=20+20)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<3, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:14 ] 122ns ± 0%
121ns ± 0% -0.69% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<10, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:23 ] 144ns ± 1%
144ns ± 0% -0.23% (p=0.009 n=20+20)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<31, false>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:46 ] 232ns ± 0%
232ns ± 1% -0.26% (p=0.021 n=18+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<1, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:12 ] 92.9ns ± 1%
92.0ns ± 1% -0.97% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<3, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:14 ] 94.0ns ± 1%
92.6ns ± 1% -1.45% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<10, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:21 ] 93.9ns ± 2%
92.8ns ± 1% -1.17% (p=0.001 n=20+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<100, true>>/0/16384
[framing_bytes/iter:9 header_bytes/iter:111 ] 106ns ± 0%
105ns ± 3% -1.15% (p=0.000 n=18+20)
BM_HpackEncoderEncodeHeader<SingleNonInternedElem>/0/1
[framing_bytes/iter:81 header_bytes/iter:9 ] 355ns ± 1%
354ns ± 0% -0.35% (p=0.015 n=19+20)
BM_HpackEncoderEncodeHeader<RepresentativeClientInitialMetadata>/0/16384
[framing_bytes/iter:9 header_bytes/iter:8.00002 ] 139ns ± 1%
133ns ± 1% -4.46% (p=0.000 n=19+20)
BM_HpackEncoderEncodeHeader<MoreRepresentativeClientInitialMetadata>/0/16384
[framing_bytes/iter:9 header_bytes/iter:16 ] 236ns ± 1%
231ns ± 1% -2.24% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<RepresentativeServerInitialMetadata>/0/16384
[framing_bytes/iter:9 header_bytes/iter:3 ] 73.6ns ± 1%
70.5ns ± 1% -4.14% (p=0.000 n=20+20)
BM_HpackEncoderEncodeHeader<RepresentativeServerTrailingMetadata>/1/16384
[framing_bytes/iter:9 header_bytes/iter:1 ] 50.5ns ± 0%
49.2ns ± 2% -2.60% (p=0.000 n=16+20)
|
5 years ago |
|
Arjun Roy
|
920bacf11d
|
Merge pull request #19498 from arjunroy/hpack_parser_on_hdr_v2
Codegen optimizations for hpack_parser on_hdr().
|
5 years ago |
rmstar
|
ce282e7d7e
|
Merge pull request #19395 from rmstar/c++_on_ios
Fix C++ tests to run on iOS
|
5 years ago |
Yang Gao
|
a0e76c0300
|
Merge pull request #19484 from yang-g/oauth
Update oauth2 token endpoints
|
5 years ago |
Jan Tattermusch
|
8fe1abebbf
|
Merge pull request #19419 from mit-mit/bumpdart
Roll Dart to 2.3
|
5 years ago |
|
Jan Tattermusch
|
0a43bd0008
|
Merge pull request #19503 from iamrare/patch-1
fix link in doc
|
5 years ago |
モハメド
|
743be2ba94
|
fix link
|
5 years ago |
apolcyn
|
58ed35407a
|
Merge pull request #19489 from apolcyn/fix_ares_throttle
Fix DNS resolver cooldown
|
6 years ago |
nanahpang
|
3a33fccb3a
|
Merge pull request #19499 from nanahpang/fix_typo_cl_255487586
fix typo "transfered" to "transferred"
|
6 years ago |
|
Arjun Roy
|
80d1aec021
|
Codegen optimizations for hpack_parser on_hdr.
Currently, the log statements for on_hdr clobber some registers even if it is
disabled by default. Additionally, the no-error path is doing some unnecessary
jumps. This PR separates out and un-inlines the logging code, and marks the
no-error case as likely to occur.
This results in slightly faster hpack_parsing, e.g.:
BM_HpackParserParseHeader<IndexedSingleStaticElem, UnrefHeader>
23.8ns ± 0% 19.8ns ± 0% -16.81% (p=0.000 n=17+17)
BM_HpackParserParseHeader<AddIndexedSingleStaticElem, UnrefHeader>
160ns ± 0% 154ns ± 0% -3.18% (p=0.000 n=19+20)
BM_HpackParserParseHeader<KeyIndexedSingleStaticElem, UnrefHeader>
216ns ± 1% 214ns ± 2% -0.70% (p=0.004 n=18+18)
BM_HpackParserParseHeader<IndexedSingleInternedElem, UnrefHeader>
35.4ns ± 0% 34.4ns ± 0% -2.93% (p=0.000 n=16+16)
BM_HpackParserParseHeader<RepresentativeClientInitialMetadata, UnrefHeader>
140ns ± 0% 130ns ± 0% -7.06% (p=0.000 n=17+18)
BM_HpackParserParseHeader<MoreRepresentativeClientInitialMetadata, UnrefHeader>
644ns ± 1% 636ns ± 2% -1.29% (p=0.003 n=17+20)
BM_HpackParserParseHeader<RepresentativeServerInitialMetadata, UnrefHeader>
49.1ns ± 0% 38.7ns ± 0% -21.13% (p=0.000 n=19+18)
BM_HpackParserParseHeader<RepresentativeServerTrailingMetadata, UnrefHeader>
47.1ns ± 0% 43.2ns ± 0% -8.17% (p=0.000 n=20+19)
BM_HpackParserParseHeader<RepresentativeClientInitialMetadata, OnInitialHeader>
452ns ± 1% 417ns ± 1% -7.86% (p=0.000 n=20+20)
BM_HpackParserParseHeader<MoreRepresentativeClientInitialMetadata,
OnInitialHeader>
1.06µs ± 1% 1.02µs ± 2% -3.42% (p=0.000 n=19+20)
BM_HpackParserParseHeader<RepresentativeServerInitialMetadata, OnInitialHeader>
156ns ± 0% 142ns ± 1% -9.08% (p=0.000 n=17+19)
BM_HpackParserParseHeader<SameDeadline, OnHeaderTimeout>
117ns ± 0% 113ns ± 1% -3.98% (p=0.000 n=20+20)
|
6 years ago |
yunjiaw26
|
c83c28167e
|
Merge pull request #19393 from yunjiaw26/extend_thd_stack_size
Extend thread class to accept setting stack size as a option
|
6 years ago |
|
nanahpang
|
36339f4032
|
fix typo "transfered" to "transferred"
find the typo during import and create this pr to sync up
|
6 years ago |
|
apolcyn
|
dd5f0fcf48
|
Merge pull request #19482 from qixuanl1/add-pick-first-unary
add pick_first_unary interop test
|
6 years ago |
Muxi Yan
|
a3a9480c49
|
Merge pull request #19492 from grpc/oauth2-uninitialized
Resolve uninitialized warning in oauth2_credentials
|
6 years ago |
|
Alexander Polcyn
|
0d2c622f9e
|
Fix DNS resolver cooldown
|
6 years ago |
Soheil Hassas Yeganeh
|
3f574aecc9
|
Merge pull request #19493 from soheilhy/fix-cred-test
Fix build failure in credential_test.cc
|
6 years ago |
Yunjia Wang
|
266c919afc
|
Merge remote-tracking branch 'upstream/master' into extend_thd_stack_size
|
6 years ago |
|
Soheil Hassas Yeganeh
|
dc858eea25
|
Fix build failure in credential_test.cc
|
6 years ago |
|
Muxi Yan
|
424328b8e7
|
Resolve uninitialized warning
|
6 years ago |
Karthik Ravi Shankar
|
0d2d88fce5
|
Merge pull request #19446 from karthikravis/continue-migration-to-impl
Move more of usage to grpc_impl
|
6 years ago |
|
Yunjia Wang
|
b95bb89d13
|
Add TODO comment
|
6 years ago |
Vijay Pai
|
858b9117dd
|
Merge pull request #19478 from grpc/vjpai-patch-1
Explain order of callback execution in executor comments
|
6 years ago |
|
Arjun Roy
|
15e78eb8b5
|
Merge pull request #19485 from arjunroy/hpack_encoder_ensure_space
Slightly better codegen for hpack_encoder.
|
6 years ago |
jboeuf
|
bd8698e8fd
|
Merge pull request #19032 from jboeuf/sts_core_creds_pr
Adding support for STS Token Exchange Creds in core:
|
6 years ago |
Qixuan Li
|
913acf456b
|
fix minor nits
|
6 years ago |
|
Arjun Roy
|
0fc57d0414
|
Slightly better codegen for hpack_encoder.
hpack_encoder::ensure_space checks to see if we need to allocate to start a
frame or not. The common case is that we don't need to, so we mark that code
branch as the more likely one to occur. This causes the common case to jump
around less.
BM_HpackEncoderEncodeDeadline
152ns ± 0% 149ns ± 0% -1.99% (p=0.000 n=19+17)
BM_HpackEncoderEncodeHeader<EmptyBatch>/0/16384
35.0ns ± 2% 34.6ns ± 0% -1.10% (p=0.000 n=20+17)
BM_HpackEncoderEncodeHeader<EmptyBatch>/1/16384
34.9ns ± 1% 34.7ns ± 1% -0.81% (p=0.007 n=20+19)
BM_HpackEncoderEncodeHeader<SingleStaticElem>/0/16384
50.6ns ± 0% 49.1ns ± 1% -3.06% (p=0.000 n=17+19)
BM_HpackEncoderEncodeHeader<SingleInternedKeyElem>/0/16384
84.9ns ± 1% 82.4ns ± 1% -2.90% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleInternedElem>/0/16384
50.5ns ± 0% 49.2ns ± 1% -2.54% (p=0.000 n=15+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<1, false>>/0/16384
50.8ns ± 2% 49.6ns ± 1% -2.46% (p=0.000 n=17+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<3, false>>/0/16384
50.9ns ± 2% 49.5ns ± 1% -2.78% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<10, false>>/0/16384
50.4ns ± 1% 49.2ns ± 1% -2.32% (p=0.000 n=18+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<31, false>>/0/16384
50.3ns ± 0% 49.2ns ± 1% -2.16% (p=0.000 n=18+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<100, false>>/0/16384
50.4ns ± 1% 49.2ns ± 1% -2.35% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<1, true>>/0/16384
50.9ns ± 2% 49.4ns ± 1% -2.81% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<3, true>>/0/16384
50.9ns ± 2% 49.4ns ± 1% -2.91% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<10, true>>/0/16384
50.2ns ± 0% 49.2ns ± 0% -2.04% (p=0.000 n=17+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<31, true>>/0/16384
50.4ns ± 1% 49.2ns ± 1% -2.38% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<100, true>>/0/16384
50.3ns ± 0% 49.2ns ± 0% -2.06% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedElem>/0/16384
91.7ns ± 1% 85.6ns ± 1% -6.64% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<1, false>>/0/16384
116ns ± 1% 112ns ± 1% -3.95% (p=0.000 n=19+18)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<3, false>>/0/16384
122ns ± 0% 117ns ± 1% -3.63% (p=0.000 n=18+17)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<10, false>>/0/16384
145ns ± 1% 140ns ± 0% -2.89% (p=0.000 n=18+18)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<31, false>>/0/16384
233ns ± 1% 231ns ± 1% -1.14% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<100, false>>/0/16384
472ns ± 1% 469ns ± 1% -0.64% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<1, true>>/0/16384
93.2ns ± 1% 87.3ns ± 1% -6.41% (p=0.000 n=20+17)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<3, true>>/0/16384
94.2ns ± 1% 88.0ns ± 1% -6.59% (p=0.000 n=20+17)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<10, true>>/0/16384
94.1ns ± 2% 87.5ns ± 1% -6.98% (p=0.000 n=20+17)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<31, true>>/0/16384
107ns ± 2% 102ns ± 4% -4.30% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<100, true>>/0/16384
106ns ± 1% 100ns ± 1% -5.64% (p=0.000 n=20+17)
BM_HpackEncoderEncodeHeader<SingleNonInternedElem>/0/1
356ns ± 1% 355ns ± 1% -0.47% (p=0.001 n=20+18)
BM_HpackEncoderEncodeHeader<RepresentativeClientInitialMetadata>/0/16384
140ns ± 1% 128ns ± 1% -7.99% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<MoreRepresentativeClientInitialMetadata>/0/16384
237ns ± 1% 218ns ± 1% -7.93% (p=0.000 n=19+19)
BM_HpackEncoderEncodeHeader<RepresentativeServerInitialMetadata>/0/16384
73.7ns ± 1% 69.7ns ± 1% -5.47% (p=0.000 n=20+19)
BM_HpackEncoderEncodeHeader<RepresentativeServerTrailingMetadata>/1/16384
50.7ns ± 0% 49.0ns ± 2% -3.19% (p=0.000 n=18+19)
|
6 years ago |
|
yang-g
|
7a4b6b7e30
|
Update oauth2 token endpoints
|
6 years ago |
Stanley Cheung
|
57d522eda3
|
Merge pull request #19228 from stanley-cheung/php-add-release-to-matrix
PHP: attempt to add v1.21.4 to interop matrix
|
6 years ago |
|
Karthik Ravi Shankar
|
bddcb6c906
|
Don't move ServerContext to impl
|
6 years ago |
|
Soheil Hassas Yeganeh
|
3fc9e00c3f
|
Merge pull request #19480 from grpc/revert-19218-string-view
Revert "Introduce string_view and use it for gpr_split_host_port."
|
6 years ago |
Lidi Zheng
|
25c720f650
|
Merge pull request #19456 from lidizheng/example-auth
[Python] Add authentication extension example
|
6 years ago |
|
Stanley Cheung
|
e92622eb5b
|
Add PHP back to client_matrix.py
|
6 years ago |
|
Qixuan Li
|
0e85762b67
|
add pick_first_unary
|
6 years ago |
|
Soheil Hassas Yeganeh
|
80c177d4c4
|
Revert "Introduce string_view and use it for gpr_split_host_port."
|
6 years ago |
Julien Boeuf
|
189c2c8c30
|
Adding support for STS Token Exchange Creds in core:
- IETF specification is available here:
https://tools.ietf.org/html/draft-ietf-oauth-token-exchange-16
|
6 years ago |
|
Karthik Ravi Shankar
|
748b932d02
|
Fix header guards
|
6 years ago |
hcaseyal
|
e6b29b3693
|
Merge pull request #19463 from hcaseyal/channelz_subchannel
Channelz: SubchannelNode no longer holds a pointer to the Subchannel
|
6 years ago |
|
Vijay Pai
|
ef4388b862
|
Explain order of callback execution in executor comments
|
6 years ago |
|
Jan Tattermusch
|
0454cde111
|
Merge pull request #19242 from jtattermusch/csharp_easier_net45_build
Get rid of workaround to build net45 targets on linux and mac
|
6 years ago |
|
Hope Casey-Allen
|
5a05ea0530
|
Format
|
6 years ago |
|
Soheil Hassas Yeganeh
|
f9516b04d5
|
Merge pull request #19218 from soheilhy/string-view
Introduce string_view and use it for gpr_split_host_port.
|
6 years ago |
|
Lidi Zheng
|
ce41cde908
|
Fix string/bytes problem && lint
|
6 years ago |
|
Karthik Ravi Shankar
|
51626535cd
|
Fix BUILD file
|
6 years ago |
|
Karthik Ravi Shankar
|
d33c02748f
|
Merge branch 'master' into continue-migration-to-impl
|
6 years ago |
|
Hope Casey-Allen
|
7f666a25ff
|
Remove GetC/hildSocketUuid and stop storing uuid inside ConnectedSubchannel
|
6 years ago |
|
Hope Casey-Allen
|
03b063568d
|
Minor fixes
|
6 years ago |
Jan Tattermusch
|
8bfb713c80
|
fix Grpc.Tools build
|
6 years ago |
|
Jan Tattermusch
|
a827504ffb
|
get rid of workaround to build net45 targets on linux and mac
|
6 years ago |
|
apolcyn
|
da3784bf89
|
Merge pull request #19397 from apolcyn/fix_ares_windows_tcp
Simplify and fix c-ares TCP path on Windows
|
6 years ago |
