Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in / Register
Toggle navigation
B
brpc
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Packages
Packages
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
submodule
brpc
Commits
b2259139
Commit
b2259139
authored
Sep 14, 2017
by
gejun
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
adapt github markdown rules
parent
9afbd71b
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
2 additions
and
2 deletions
+2
-2
case_elf.md
docs/cn/case_elf.md
+1
-1
case_ubrpc.md
docs/cn/case_ubrpc.md
+1
-1
No files found.
docs/cn/case_elf.md
View file @
b2259139
...
...
@@ -36,7 +36,7 @@ fm-sync算法: 替换前总耗时6:16:37, 替换后总耗时5:21:00, 提升14.6%
| 替换后 | 304.878 | 2571.34 | 0 |
| 缩短 | 53.7% | 63.9% | |
##结论
##
结论
单个rpc-call以及单次请求所有rpc-call的提升非常显著,提升都在50%以上,总任务的耗时除了ftrl-sync-no-shuffle提升不明显外,其余三个算法都有15%左右的提升,现在算法的瓶颈在于对计算逻辑,所以相对单个的rpc的提升没有那么多。
...
...
docs/cn/case_ubrpc.md
View file @
b2259139
...
...
@@ -21,6 +21,7 @@ brpc改造后的connecter收益明显,可以用较少的机器提供更优质
# 不同配置机器qps和延时的比较
qps固定为6500,观察延时。
| 机器名称 | 略 | 略 |
| ----- | ---------------------------------------- | ---------------------------------------- |
| cpu | 24 Intel(R) Xeon(R) CPU E5645 @ 2.40GHz | 24 Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz |
...
...
@@ -30,7 +31,6 @@ qps固定为6500,观察延时。
有此可见:
*
ubrpc在不同配置下性能表现差异大,在配置较低的机器下表现较差。
*
brpc表现的比ubrpc好,在较低配置的机器上也能有好的表现,因机器不同带来的差异不大。
# 相同配置机器idle分布的比较
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment