Chiebot-Mirror/grpc - grpc - Gitea: Git with a cup of tea

Commit Graph

Author	SHA1	Message	Date
Yash Tibrewal	64e7131a61	Add some TODOs	5 years ago
Yash Tibrewal	682c807f05	Remove chttp2 combiner and replace it with a simple mutex.	5 years ago
yang-g	4ba19b29f8	Clear thread local after use	6 years ago
Soheil Hassas Yeganeh	5f2bcfca73	Clarify what callback means.	6 years ago
Alexander Polcyn	1c56cda526	Add comment	6 years ago
Alex Polcyn	fd37378a52	Fix use after free	6 years ago
Yash Tibrewal	f1914fba00	Renaming remaining filter functions	6 years ago
Soheil Hassas Yeganeh	dd6e6e3ef7	Introduce GRPC_ARG_TSI_MAX_FRAME_SIZE channel arg. Introduce GRPC_ARG_TSI_MAX_FRAME_SIZE so that users can use larger than 14KiB frame size if they need to.	6 years ago
Soheil Hassas Yeganeh	35e2760ffa	Add a fast path to allocate slices in the resource quota. Currently, we are always scheduling a callback to run the allocation. Instead, this patch adds a fastpath so that TCP can read the socket inline, instead of waiting for the exec context to flush. BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/64/2 [polls/iter:12 ] 65.3µs ± 0% 64.7µs ± 1% -0.92% (p=0.032 n=4+5) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/2 [polls/iter:12.0002 ] 61.4µs ± 4% 57.3µs ±13% -6.66% (p=0.030 n=5+7) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/1/2 [polls/iter:12.0002 ] 61.7µs ± 1% 60.8µs ± 1% -1.49% (p=0.003 n=9+4) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/32768/2 [polls/iter:12.0002 ] 114µs ± 2% 112µs ± 0% -2.09% (p=0.030 n=10+2) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/1/2 [polls/iter:12.0002 ] 62.9µs ± 0% 62.0µs ± 1% -1.32% (p=0.001 n=7+6) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/64/2 [polls/iter:12.0002 ] 66.5µs ± 3% 64.4µs ± 1% -3.20% (p=0.016 n=5+4) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/512/2 [polls/iter:12 ] 66.1µs ± 1% 65.2µs ± 1% -1.30% (p=0.003 n=8+5) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/4096/2 [polls/iter:12 ] 72.1µs ± 4% 70.8µs ± 1% -1.92% (p=0.004 n=9+5) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/2 [polls/iter:12.0001 ] 60.4µs ± 1% 59.4µs ± 0% -1.55% (p=0.004 n=6+5) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/8/2 [polls/iter:12 ] 63.6µs ± 1% 62.2µs ± 1% -2.13% (p=0.001 n=7+6) BM_StreamingPingPongMsgs<TCP, NoOpMutator, NoOpMutator>/4096 [polls/iter:4.00008 ] 20.9µs ± 1% 19.8µs ±13% -5.30% (p=0.029 n=4+4) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/1 [polls/iter:8.00014 ] 44.4µs ± 1% 41.9µs ±13% -5.51% (p=0.010 n=6+4) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/8/2 [polls/iter:12.0001 ] 62.1µs ± 0% 61.1µs ± 1% -1.56% (p=0.036 n=3+5) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/64/2 [polls/iter:12.0002 ] 64.0µs ± 0% 63.3µs ± 0% -1.14% (p=0.004 n=5+6) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/1/2 [polls/iter:12 ] 62.0µs ± 1% 61.0µs ± 1% -1.61% (p=0.032 n=4+5) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/0/2 [polls/iter:12.0002 ] 62.4µs ± 4% 60.6µs ± 1% -2.82% (p=0.003 n=7+5) BM_StreamingPingPongMsgs<TCP, NoOpMutator, NoOpMutator>/512 [polls/iter:4.00009 ] 17.9µs ± 1% 16.5µs ±11% -7.40% (p=0.032 n=4+5) BM_StreamingPingPong<TCP, NoOpMutator, NoOpMutator>/4096/1 [polls/iter:8.00016 ] 50.2µs ± 0% 49.5µs ± 1% -1.46% (p=0.024 n=3+6) BM_StreamingPingPong<MinTCP, NoOpMutator, NoOpMutator>/512/2 [polls/iter:12.0002 ] 65.5µs ± 3% 61.9µs ±13% -5.59% (p=0.048 n=5+7) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/0 [polls/iter:3.00009 ] 23.4µs ± 2% 23.0µs ± 0% -1.88% (p=0.036 n=3+5) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/512/0 [polls/iter:3.0001 ] 25.6µs ± 2% 25.0µs ± 0% -2.44% (p=0.017 n=7+3) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/262144/0 [polls/iter:3.00022 ] 164µs ± 2% 161µs ± 1% -1.83% (p=0.048 n=3+6)	6 years ago
Mark D. Roth	01eeec72c6	Change RR to consider a subchannel in TF if it has failed since it was READY.	6 years ago
Yash Tibrewal	1b1364eb6b	Reviewer comments	6 years ago
Yash Tibrewal	6f5e358da7	Rename filter functions to be able to uniquely identify them	6 years ago
Esun Kim	cf444b9cab	Regenerate projects	6 years ago
Esun Kim	c965ca1494	Pull out configuration from ssl_utils	6 years ago
Soheil Hassas Yeganeh	4b2b00b35b	Optimize cycle to millis conversion by bypassing sub+add.	6 years ago
Soheil Hassas Yeganeh	7b84f81a8c	Add grpc_cycle_counter_to_millis().	6 years ago
Soheil Hassas Yeganeh	81a29ae1a6	Mark double-second local variables as const.	6 years ago
Soheil Hassas Yeganeh	c9376b4e0b	Use cycle clock instead of clock monotonic to measure call latency. This removes two more getttime syscalls from the hot path, when cycle clock is enabled.	6 years ago
Arjun Roy	c63f419c49	Mark CH2 on_initial_header error path unlikely. Yields slightly better unary and streaming performance for TCP: BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/4096/4096 [polls/iter:3.00006 ] 27.1µs ± 2% 26.3µs ± 1% -2.77% (p=0.036 n=5+3) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/1/0 [polls/iter:3.00009 ] 21.7µs ± 2% 21.1µs ± 1% -2.88% (p=0.029 n=4+4) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/1 [polls/iter:3.00009 ] 21.8µs ± 2% 20.9µs ± 1% -4.32% (p=0.003 n=7+5) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/1/1 [polls/iter:3.00008 ] 22.0µs ± 1% 21.3µs ± 1% -3.15% (p=0.036 n=3+5) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/64/0 [polls/iter:3.00006 ] 22.0µs ± 1% 21.5µs ± 1% -2.19% (p=0.032 n=4+5) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/32768/0 [polls/iter:3.00007 ] 34.7µs ± 1% 34.1µs ± 0% -1.72% (p=0.017 n=7+3) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/262144 [polls/iter:3.00023 ] 160µs ± 1% 158µs ± 1% -1.29% (p=0.016 n=8+4) BM_UnaryPingPong<UDS, NoOpMutator, NoOpMutator>/0/0 [polls/iter:3.00012 ] 20.8µs ± 1% 20.4µs ± 0% -1.89% (p=0.029 n=4+4) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/0/0 [polls/iter:3.00008 ] 22.1µs ± 4% 21.3µs ± 0% -3.88% (p=0.004 n=6+5) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/64/0 [polls/iter:3.00008 ] 23.2µs ± 2% 22.5µs ± 3% -3.07% (p=0.014 n=7+6) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/512/512 [polls/iter:3.0001 ] 23.5µs ± 2% 22.9µs ± 0% -2.85% (p=0.010 n=6+4) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/1/0 [polls/iter:3.00008 ] 22.5µs ± 1% 21.7µs ± 1% -3.35% (p=0.036 n=3+5) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/32768/32768 [polls/iter:3.0001 ] 48.6µs ± 1% 48.3µs ± 1% -0.58% (p=0.045 n=5+8) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/8/8 [polls/iter:3.00008 ] 22.0µs ± 1% 21.5µs ± 1% -2.35% (p=0.016 n=4+5) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/8/8 [polls/iter:3.00006 ] 22.4µs ± 3% 21.4µs ± 1% -4.05% (p=0.017 n=7+3) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/4096/0 [polls/iter:3.00007 ] 24.5µs ± 1% 23.9µs ± 1% -2.30% BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/1/1 [polls/iter:3.0001 ] 22.9µs ± 2% 22.4µs ± 3% -2.04% (p=0.048 n=7+5) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/8/8 [polls/iter:3.0001 ] 23.0µs ± 2% 22.4µs ± 1% -2.75% (p=0.012 n=7+4) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/64/64 [polls/iter:3.00008 ] 23.5µs ± 2% 23.1µs ± 0% -2.10% (p=0.002 n=8+5) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/64/0 [polls/iter:3.00008 ] 22.1µs ± 2% 21.5µs ± 1% -2.93% (p=0.009 n=9+3) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/0/64 [polls/iter:3.00008 ] 22.2µs ± 1% 21.4µs ± 1% -3.51% (p=0.003 n=4+9) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/512/0 [polls/iter:3.00008 ] 22.4µs ± 2% 21.8µs ± 1% -2.75% (p=0.009 n=5+6) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/32768/0 [polls/iter:3.0001 ] 34.5µs ± 1% 34.0µs ± 1% -1.58% But, slightly worse performance for in-proc (about 2-3%).	6 years ago
Arjun Roy	0b06676c9e	hpack encoder optimizations. Removed some cycles and branches from hpack_enc for CH2. Specifically: 1. Pushed certain metadata key/value length checks to prepare_application_metadata() in src/core/lib/surface/call.cc. This means that rather than check all key/val lengths for all metadata, we only do so for custom added user metadata. Inside CH2, we change the length checks to debug checks so we can catch if core/filter metadata fails to pass the check. 2. Changed various asserts to debug asserts when able. 3. Refactored some of the header emission code to remove duplicated code. 4. Un-inlined some logging methods. This results in somewhat faster hpack_encoder performance: BM_HpackEncoderInitDestroy 222ns ± 0% 221ns ± 0% -0.29% (p=0.000 n=34+34) BM_HpackEncoderEncodeDeadline [framing_bytes/iter:9 header_bytes/iter:6 ] 135ns ± 1% 124ns ± 0% -8.05% (p=0.000 n=39+38) BM_HpackEncoderEncodeHeader<EmptyBatch>/0/16384 [framing_bytes/iter:9 header_bytes/iter:0 ] 34.2ns ± 0% 34.2ns ± 0% -0.01% (p=0.014 n=34+38) BM_HpackEncoderEncodeHeader<EmptyBatch>/1/16384 [framing_bytes/iter:9 header_bytes/iter:0 ] 34.2ns ± 0% 34.2ns ± 0% -0.04% (p=0.004 n=34+37) BM_HpackEncoderEncodeHeader<SingleStaticElem>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.5ns ± 0% 45.9ns ± 0% -3.28% (p=0.000 n=28+38) BM_HpackEncoderEncodeHeader<SingleInternedKeyElem>/0/16384 [framing_bytes/iter:9 header_bytes/iter:6 ] 77.0ns ± 1% 68.3ns ± 1% -11.33% (p=0.000 n=39+40) BM_HpackEncoderEncodeHeader<SingleInternedElem>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.7ns ± 1% 45.5ns ± 0% -4.63% (p=0.000 n=39+33) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<1, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.2ns ± 0% 45.3ns ± 0% -3.96% (p=0.000 n=33+34) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<3, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.7ns ± 0% 45.6ns ± 0% -4.54% (p=0.000 n=38+40) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<10, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.7ns ± 0% 45.5ns ± 0% -4.63% (p=0.000 n=39+32) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<31, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.8ns ± 0% 45.6ns ± 1% -4.59% (p=0.000 n=38+39) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<100, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.8ns ± 0% 45.5ns ± 0% -4.64% (p=0.000 n=39+36) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<1, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.3ns ± 0% 45.3ns ± 0% -4.09% (p=0.000 n=38+36) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<3, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.8ns ± 1% 45.6ns ± 0% -4.71% (p=0.000 n=37+40) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<10, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.7ns ± 0% 45.5ns ± 0% -4.66% (p=0.000 n=39+32) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<31, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.8ns ± 1% 45.6ns ± 1% -4.62% (p=0.000 n=37+39) BM_HpackEncoderEncodeHeader<SingleInternedBinaryElem<100, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.7ns ± 0% 45.5ns ± 0% -4.67% (p=0.000 n=38+32) BM_HpackEncoderEncodeHeader<SingleNonInternedElem>/0/16384 [framing_bytes/iter:9 header_bytes/iter:9 ] 80.5ns ± 1% 74.7ns ± 0% -7.16% (p=0.000 n=38+35) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<1, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:12 ] 105ns ± 1% 99ns ± 0% -5.91% (p=0.000 n=38+34) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<3, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:14 ] 111ns ± 1% 106ns ± 1% -4.86% (p=0.020 n=39+2) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<10, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:23 ] 135ns ± 0% 130ns ± 0% -3.45% (p=0.020 n=35+2) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<31, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:46 ] 225ns ± 1% 223ns ± 0% -0.91% (p=0.003 n=37+2) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<100, false>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:120 ] 467ns ± 0% 472ns ± 0% +1.09% (p=0.003 n=38+2) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<1, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:12 ] 81.6ns ± 1% 74.8ns ± 0% -8.40% (p=0.000 n=37+33) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<3, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:14 ] 82.0ns ± 1% 74.8ns ± 0% -8.80% (p=0.000 n=37+32) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<10, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:21 ] 82.1ns ± 1% 74.9ns ± 0% -8.86% (p=0.000 n=35+34) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<31, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:42 ] 97.6ns ± 2% 91.8ns ± 0% -5.95% (p=0.000 n=35+27) BM_HpackEncoderEncodeHeader<SingleNonInternedBinaryElem<100, true>>/0/16384 [framing_bytes/iter:9 header_bytes/iter:111 ] 97.2ns ± 1% 91.2ns ± 2% -6.19% (p=0.000 n=37+38) BM_HpackEncoderEncodeHeader<SingleNonInternedElem>/0/1 [framing_bytes/iter:54 header_bytes/iter:9 ] 230ns ± 0% 221ns ± 0% -3.91% (p=0.000 n=38+37) BM_HpackEncoderEncodeHeader<MoreRepresentativeClientInitialMetadata>/0/16384 [framing_bytes/iter:9 header_bytes/iter:16 ] 206ns ± 2% 170ns ± 1% -17.51% (p=0.000 n=39+39) BM_HpackEncoderEncodeHeader<RepresentativeServerInitialMetadata>/0/16384 [framing_bytes/iter:9 header_bytes/iter:3 ] 66.4ns ± 2% 62.5ns ± 1% -5.85% (p=0.000 n=34+39) BM_HpackEncoderEncodeHeader<RepresentativeServerTrailingMetadata>/1/16384 [framing_bytes/iter:9 header_bytes/iter:1 ] 47.5ns ± 0% 45.9ns ± 1% -3.29% (p=0.000 n=26+38)	6 years ago
Mark D. Roth	e592414fae	Add check for input parameter being null.	6 years ago
Mark D. Roth	51d18ecc63	Convert mpscq API from C to C++.	6 years ago
Arjun Roy	ee603bf172	Better codegenfor validate_filtered_metadata. validate_filtered_metadata() performs several checks to see if a call must be failed. Failure is the unlikely case; to that end, failing branches are marked unlikely, and the specific code handling failure cases is refactored into explicitly un-inlined helper methods. This will prevent us from unnecessarily clobbering registers and give us a straight-line codepath for the success case. Results: BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/8/0 [polls/iter:3.00008 ] 22.5µs ± 0% 21.6µs ± 0% -4.02% (p=0.036 n=5+3) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/64/64 [polls/iter:3.00008 ] 23.4µs ± 1% 23.0µs ± 1% -1.63% (p=0.010 n=6+4) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/32768/0 [polls/iter:3.00007 ] 34.4µs ± 1% 34.1µs ± 0% -0.99% (p=0.024 n=6+3) BM_UnaryPingPong<InProcess, NoOpMutator, NoOpMutator>/0/0 [polls/iter:0 ] 6.36µs ± 5% 6.16µs ± 2% -3.26% (p=0.013 n=20+19) BM_UnaryPingPong<InProcess, NoOpMutator, NoOpMutator>/1/1 [polls/iter:0 ] 6.62µs ± 6% 6.50µs ± 4% -1.72% (p=0.049 n=20+20) BM_UnaryPingPong<InProcess, NoOpMutator, NoOpMutator>/512/0 [polls/iter:0 ] 6.67µs ± 6% 6.59µs ± 2% -1.29% (p=0.047 n=20+19) BM_UnaryPingPong<InProcess, NoOpMutator, NoOpMutator>/4096/0 [polls/iter:0 ] 7.68µs ± 1% 7.65µs ± 2% -0.46% (p=0.031 n=18+18) BM_UnaryPingPong<InProcess, NoOpMutator, NoOpMutator>/0/262144 [polls/iter:0 ] 86.0µs ± 2% 85.3µs ± 2% -0.77% (p=0.046 n=19+19) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/0/0 [polls/iter:0 ] 6.28µs ± 5% 6.00µs ± 2% -4.37% (p=0.000 n=20+20) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/1/0 [polls/iter:0 ] 6.39µs ± 6% 6.20µs ± 2% -3.03% (p=0.001 n=20+19) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/0/1 [polls/iter:0 ] 6.36µs ± 6% 6.17µs ± 1% -3.00% (p=0.006 n=20+17) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/1/1 [polls/iter:0 ] 6.59µs ± 5% 6.30µs ± 2% -4.37% (p=0.000 n=20+19) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/8/0 [polls/iter:0 ] 6.37µs ± 5% 6.20µs ± 2% -2.76% (p=0.001 n=20+20) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/0/8 [polls/iter:0 ] 6.36µs ± 5% 6.17µs ± 2% -2.95% (p=0.001 n=20+19) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/8/8 [polls/iter:0 ] 6.45µs ± 7% 6.27µs ± 1% -2.72% (p=0.002 n=20+18) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/64/0 [polls/iter:0 ] 6.46µs ± 6% 6.31µs ± 1% -2.39% (p=0.001 n=20+20) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/512/0 [polls/iter:0 ] 6.62µs ± 6% 6.43µs ± 2% -2.92% (p=0.000 n=20+18) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/0/512 [polls/iter:0 ] 6.58µs ± 7% 6.41µs ± 1% -2.57% (p=0.002 n=20+17) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/512/512 [polls/iter:0 ] 6.88µs ± 7% 6.76µs ± 2% -1.81% (p=0.047 n=20+19) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/4096/0 [polls/iter:0 ] 7.57µs ± 3% 7.49µs ± 2% -0.99% (p=0.007 n=20+20) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/0/4096 [polls/iter:0 ] 7.66µs ± 5% 7.50µs ± 2% -2.15% (p=0.003 n=20+20) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/32768/0 [polls/iter:0 ] 15.8µs ± 2% 15.7µs ± 1% -0.75% (p=0.001 n=20+19) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/0/32768 [polls/iter:0 ] 16.1µs ± 2% 16.0µs ± 2% -0.84% (p=0.002 n=20+20) BM_UnaryPingPong<MinInProcess, NoOpMutator, NoOpMutator>/32768/32768 [polls/iter:0 ] 25.5µs ± 1% 25.4µs ± 1% -0.42% (p=0.011 n=20+19) BM_UnaryPingPong<InProcess, Client_AddMetadata<RandomBinaryMetadata<100>, 2>, NoOpMutator>/0/0 [polls/iter:0 ] 7.99µs ± 5% 7.85µs ± 2% -1.81% (p=0.028 n=20+20) BM_UnaryPingPong<InProcess, NoOpMutator, Server_AddInitialMetadata<RandomBinaryMetadata<100>, 1>>/0/0 [polls/iter:0 ] 7.07µs ± 6% 7.14µs ± 5% +0.95% (p=0.007 n=19+18) BM_UnaryPingPong<InProcess, Client_AddMetadata<RandomAsciiMetadata<31>, 1>, NoOpMutator>/0/0 [polls/iter:0 ] 6.95µs ± 5% 7.02µs ± 3% +0.94% (p=0.017 n=18+19) BM_UnaryPingPong<InProcess, Client_AddMetadata<RandomAsciiMetadata<100>, 1>, NoOpMutator>/0/0 [polls/iter:0 ] 7.10µs ± 2% 7.19µs ± 2% +1.31% (p=0.000 n=16+20) BM_UnaryPingPong<InProcess, NoOpMutator, Server_AddInitialMetadata<RandomAsciiMetadata<31>, 1>>/0/0 [polls/iter:0 ] 6.89µs ± 2% 7.00µs ± 3% +1.61% (p=0.000 n=17+19) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/512/512 [polls/iter:3.00007 ] 24.1µs ± 1% 23.7µs ± 1% -1.77% (p=0.024 n=6+3) BM_UnaryPingPong<MinTCP, NoOpMutator, NoOpMutator>/1/0 [polls/iter:3.00009 ] 21.5µs ± 1% 20.9µs ± 0% -2.78% (p=0.024 n=6+3) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/4096/0 [polls/iter:3.00005 ] 24.4µs ± 2% 23.9µs ± 2% -2.16% (p=0.020 n=9+4) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/32768/0 [polls/iter:3.0001 ] 35.3µs ± 1% 34.8µs ± 1% -1.45% (p=0.008 n=5+5) BM_UnaryPingPong<MinSockPair, NoOpMutator, NoOpMutator>/0/0 [polls/iter:3.00008 ] 19.5µs ± 1% 19.1µs ± 1% -2.30% (p=0.016 n=4+5) BM_UnaryPingPong<TCP, NoOpMutator, NoOpMutator>/0/32768 [polls/iter:3.0001 ] 35.4µs ± 1% 34.7µs ± 1% -1.77% (p=0.016 n=4+5)	6 years ago
Mark D. Roth	d3f50ace39	Use mutex instead of combiner in client channel data plane.	6 years ago
Yash Tibrewal	7315e75ce6	Add comments	6 years ago
Yash Tibrewal	3476df0b50	Add in ref to error	6 years ago
Yash Tibrewal	e6ffb2c3bb	Replace direct closure callback calls with GRPC_CLOSURE_SCHED	6 years ago
Esun Kim	a96cbbd592	Fix ubsan on InternNewStringLocked	6 years ago
Esun Kim	fa7bdff69f	Fix buffer-overflow in grpc_static_mdelem_for_static_strings	6 years ago
Alexander Polcyn	d1dae7d9d8	Log errors in ALTS handshaker message op completion cb	6 years ago
Alexander Polcyn	aa2a65faed	Remove call from queued picks when failing it due to channel destruction	6 years ago
Yash Tibrewal	156a4cccdf	Remove unusued arg	6 years ago
Arjun Roy	b46e3668d3	s/branch/tail_call/ for CH2 on_hdr(). on_hdr() checks if a void-return function pointer is null before jumping to it. If it is null, it returns an error; else it executes that function and returns success. This change converts the void-returning function to one that returns a grpc_error* and thus saves a branch in on_hdr() (since we're branching once by following the function pointer anyways, we're effectively coalescing these two branches).	6 years ago
Mark D. Roth	21c5424477	Add API for accessing per-call backend metric data in LB policies.	6 years ago
Mark D. Roth	c8430023a5	Apply health check service name changes to existing subchannels.	6 years ago
Arjun Roy	2767accc1b	Fixed init-order-fiasco for static slice table. Fixes init-order bug affecting https://github.com/grpc/grpc/issues/19819 which was first exposed by this commit: `857375a142`	6 years ago
Mark D. Roth	18be57b4df	LB policy API changes suggested by Sanjay.	6 years ago
Esun Kim	2707fd0bd4	Added GRPC_USE_CPP_STD_LIB flag	6 years ago
Benjamin Peterson	57586a1ca7	Rename gettid() functions. glibc 2.30 will declare its own gettid; see https://sourceware.org/git/?p=glibc.git;a=commit;h=1d0fc213824eaa2a8f8c4385daaa698ee8fb7c92. Rename the grpc versions to avoid naming conflicts.	6 years ago
Arjun Roy	6e159d3ee3	Fix hpack parser fuzzer failure. Fix crash when nullptr is passed to ManagedMemorySlice::Equals().	6 years ago
yang-g	3728329033	return unavailable on transport closed	6 years ago
Esun Kim	32f1119d2b	Strict C++	6 years ago
Juanli Shen	de6255941a	Fix gettid() naming conflict	6 years ago
Mark D. Roth	5d646ff9ff	Make Map<> copyable.	6 years ago
Prashant Jaikumar	41986e8ed8	Added test for timer wakeups	6 years ago
Hope Casey-Allen	257737f2c6	Fix warning in client_idle_filter.cc to support gcc8	6 years ago
Qiancheng Zhao	e45bea777e	use acquire instead of relaxed in IdleTimerCallback()	6 years ago
Juanli Shen	a802b14be6	Add xds resolver	6 years ago
Qiancheng Zhao	1391c93a95	atomic client idle filter	6 years ago
Juanli Shen	c1713800e0	Handle EDS response update in locality map	6 years ago

1 2 3 4 5 ...

12263 Commits (64e7131a614fabc57fa54326833f7a7a49513926)