chore: merge from develop #224
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
release: 20220118
use wyrand, see https://github.com/wangyi-fudan/wyhash. name old time/op new time/op delta SingleCore/math/rand-Uint32()-16 10.8ns ± 0% 10.8ns ± 0% ~ (p=0.913 n=7+10) SingleCore/fast-rand-Uint32()-16 2.26ns ± 0% 2.25ns ± 0% ~ (p=0.015 n=10+10) SingleCore/math/rand-Uint64()-16 11.1ns ± 0% 11.1ns ± 0% ~ (p=0.014 n=10+8) SingleCore/fast-rand-Uint64()-16 5.03ns ± 0% 4.75ns ± 0% -5.50% (p=0.000 n=10+9) SingleCore/math/rand-Read1000-16 682ns ± 0% 682ns ± 0% ~ (p=0.927 n=10+10) SingleCore/fast-rand-Read1000-16 298ns ± 1% 150ns ± 0% -49.69% (p=0.000 n=10+9) MultipleCore/math/rand-Uint32()-16 114ns ± 3% 113ns ± 4% ~ (p=0.306 n=10+10) MultipleCore/fast-rand-Uint32()-16 0.18ns ± 1% 0.18ns ± 2% ~ (p=0.006 n=9+10) MultipleCore/math/rand-Uint64()-16 115ns ± 6% 118ns ± 3% ~ (p=0.018 n=10+9) MultipleCore/fast-rand-Uint64()-16 0.39ns ± 1% 0.38ns ± 0% -1.55% (p=0.000 n=10+8) MultipleCore/math/rand-Read1000-16 1.02µs ± 3% 1.03µs ± 4% ~ (p=0.644 n=10+10) MultipleCore/fast-rand-Read1000-16 112ns ± 0% 102ns ± 1% -9.38% (p=0.000 n=10+10)
* feat: support change min/max gc percent limit * fix: make max/min gc percent private * feat: add get min/max gc percent interface
Change-Id: I63cc5c0e8d7b69b627322220881ded0746001c18 Co-authored-by: gaohui.000 <[email protected]>
Change-Id: I7bff5f64b3b95eab93f8e46132dd264c519c6fd6 Co-authored-by: zhangjie.001 <[email protected]>
* fix(metainfo): fix value override by append * ci(github): increase action timeout for benchdiff
Signed-off-by: cui fliter <[email protected]>
Co-authored-by: huanghongkai <[email protected]>
Co-authored-by: Pure White <[email protected]>
* feat: add RangePersistentValues Change-Id: I60f02e8a0769ea855d775cbfc1980915bb76dfff Change-Id: I1d9a81d81b7fec7ee90396ebdeaa2e8e6e213cfa Co-authored-by: caimufu <[email protected]>
* feat(lscq): add arm64 support Using CASP instruction to implement double-width CAS for arm64. The CASP instruction is available for instruction set Armv8.1+ (inclusive, Apple M1/M2/A12, Snapdragon 845, etc). All tests in lscq_test.go passed on Macbook Air M1 2020, macOS 12.5.1. Change-Id: Ieb89fa9361f1fce8fb52b102dca556867f7e8e8a * use cpu.ARM64.HasATOMICS to determine whether the arm64 cpu has standalone CAS instructions(CASP is only available for ARMv8.1+, use LDAX/STLX instruction on ARMv8.0 instead). Currently, package golang.org/x/sys/cpu do not fully support darwin/arm64(Apple M1/M2), resulting in the cpu.ARM64.HasATOMICS to be false, which is actually true. runtime/internal/cpu has fully supported detecting cpu features on darwin/arm64, maybe extracting code from it is a good walk around. * feat(lscq): use LDAXP/STLXP for armv8.0 instead of CASP use cpu.ARM64.HasATOMICS to determine whether the arm64 cpu has standalone CAS instructions(CASP is only available for ARMv8.1+, use LDAX/STLX instruction on ARMv8.0 instead). Currently, package golang.org/x/sys/cpu do not fully support darwin/arm64(Apple M1/M2), resulting in the cpu.ARM64.HasATOMICS to be false, which is actually true. runtime/internal/cpu has fully supported detecting cpu features on darwin/arm64, maybe extracting code from it is a good walk around. * fix(lscq): fix bad indention fix bad indention problem. * fix(lscq): replace ORR with MOVD Use MOVD instead of ORR to copy between registers. Prettify indentions between operator and operand. * fix(lscq): detect atomics feature correctly on darwin On darwin, golang.org/x/sys/cpu.ARM64.HasATOMICS is set to false, which actually should be true. Therefore, in order to use faster CASPD instruction on darwin_arm64, we can use sysctl/sysctlbyname to detect cpu features on darwin, see https://developer.apple.com/documentation/apple-silicon/addressing-architectural-differences-in-your-macos-code. The sysctlEnabled is exported from internal/cpu.sysctlEnabled, which will call sysctlbyname to detect if specific cpu feature is enabled. And it's ok to use golang.org/x/sys/cpu.ARM64.HasATOMICS on other OS. One more bug fixed: MOVD R2, R6 => MOVD R6, R2. The bug wouldn't be found if arm64HasAtomics is set to false. All test and bench passed. Co-authored-by: yuchengye <[email protected]>
* chore: fix gctuner tests * chore: fix finalizer test * chore: use manual gc for finalizer test Co-authored-by: Pure White <[email protected]>
The key problem is that the LoadOrStore uses an outdated highest level to search the skip list, if the new generated level(say newLevel) is bigger than the outdated highest level(say oldLevel), all slots in the slices preds[newLevel-oldLevel:newLevel] are nil, the function will panic. The solution is that if the newLevel has updated the highest level, we can just continue the loop, and find a new path. At this time, the latest highest level used by the findNode is always bigger than or equal to the newLevel, the function won't panic. name old time/op new time/op delta LoadOrStoreExist-16 4.43ns ±11% 1.06ns ±21% -76.05% (p=0.000 n=10+10) LoadOrStoreLazyExist-16 4.61ns ± 6% 1.16ns ± 0% -74.90% (p=0.000 n=9+7) LoadOrStoreExistSingle-16 37.5ns ± 6% 10.3ns ± 0% -72.61% (p=0.000 n=9+9) LoadOrStoreLazyExistSingle-16 38.3ns ±11% 10.6ns ± 0% -72.43% (p=0.000 n=10+10) LoadOrStoreRandom-16 209ns ±14% 206ns ±14% ~ (p=0.684 n=10+10) LoadOrStoreLazyRandom-16 215ns ± 8% 207ns ± 9% ~ (p=0.139 n=10+10) LoadOrStoreRandomSingle-16 1.05µs ± 1% 1.04µs ± 4% ~ (p=0.535 n=9+10) LoadOrStoreLazyRandomSingle-16 1.07µs ± 1% 1.06µs ± 3% -1.09% (p=0.029 n=8+9)
…from context to HTTP header (#169)
* fix(metainfo): old kvs missed after `WithValues()` * opt: add Len() API for better performance when dumping KVS
…o send from the given context (#164)
Co-authored-by: ZhangYunHao <[email protected]>
* chore: fix license check ci * chore: rm feishu notify since it not work now * chore: rm bench diff since it not work now * chore: change license ci * chore: speed up ci * chore: fix TestBreakerConcurrent ci * chore: skip un-stable unit test since its time sensetive * chore: fix test race * fix: FromHTTPHeader add stale * fix: TestChannelNoConsumer race * chore: grant owner to joway
* chore: rm linked fast rand for test * chore: rm unstable ci assert * chore: spped up TestDigest
joway
requested review from
lyeeeeee,
PureWhiteWu,
zhangyunhao116,
kaka19ace,
SilverRainZ and
lsjbd
as code owners
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.