当前位置:网站首页>Bare metal cloud FASS high performance elastic block storage solution
Bare metal cloud FASS high performance elastic block storage solution
2022-07-29 05:48:00 【Taocloud Avenue】
Distributed storage | Beijing Avenue yunhang Technology Co., Ltd
01 Background Overview
Compared with the public cloud model , Bare metal servers provide users with physical server rental services , It continues the unique advantage of non-destructive performance of physical machine , It can meet the strict requirements of core application scenarios for high performance and stability at the same time . Use bare metal server to monopolize client resources , Don't share with other customers CPU、 Memory, etc. , Performance can be fully exploited . Because of the complete isolation at the physical machine level , Can provide more security 、 Reliable computing resources . Bare metal servers can achieve performance that is no worse than physical servers , At the same time, it can realize the elastic expansion and use of resources , Fully automated operation and maintenance management , More and more attention is paid to financial securities 、HPC And so on 、 High data security requirements are welcomed by users .
02 Demand pain point
Bare metal cloud can realize elastic and automatic computing resource management , However, there is no powerful data storage matching scheme :
1、 Not flexible enough 、 Complex operation and maintenance : It is inconvenient to expand the capacity of bare metal server with local hard disk , Lack of unified management , Unable to allocate resources dynamically and reasonably , Capacity expansion requires a lot of manual intervention , Bring great cost growth .
2、 Resource solidification 、 The high cost of : The business application of bare metal cloud requires high storage performance , Each host will be configured independently NVME disc , But each host SSD Resources cannot be pooled and dynamically allocated , Low resource utilization , The high cost of .
3、 A single point of failure 、 Low security : The local hard disk mode lacks unified management and data protection , Become an obvious single point of failure of the system , Once the server or hard disk is damaged , It will cause serious consequences such as data loss and business interruption .
03 FASS High performance elastic block storage solution

△ Scheme topology
Storage pool mainly adopts Fully equipped NVMe Discoid FASS Construction of distributed full flash storage system ,FASS Use cross node SSD Resource to create a storage pool , And divide into multiple LUN volume , be based on 100Gb Ethernet or Infiniband The Internet , With iSCSI/iSER/NVMeoF The protocol maps to each bare metal host that needs to be stored .
FASS Every LUN Thin provisioned volumes , Space that can be allocated far more than actual physical resources , Meet the changing business needs of each host . The background can be used according to the essence of each host , Dynamically allocate physical resources .
As a standard distributed storage system ,FASS Support 512 Node Scale-out Expand , It can change with business needs , Easily increase capacity and performance by scaling horizontally , Meet the huge needs of cloud business .
04 Program advantages
Standard agreement 、 Excellent performance ——FASS The distributed full flash block storage solution adopts NVMe medium , Based on standards iSCSI、iSER、NVMeoF Can provide the ultimate I/O performance , Combined with the software layer XPE Engine design 、 Microcontroller technology 、 Lightweight metadata indexing and other mechanisms , The block storage end can reach 30 million nodes IOPS、 Microsecond delay , It can easily meet the stringent performance requirements of bare metal virtual machines .
High availability 、 Elastic expansion ——FASS The distributed full flash storage system adopts full live high availability architecture , Any node can be allowed to fail without interrupting the block storage service , High business availability .FASS Single node can achieve 100 All level IOPS, With the growth of cluster size, the linear growth of capacity and performance can be realized at the same time , Up to tens of millions of IOPS performance .
According to the need to use 、 Planning minimalism ——FASS Thin provisioned volumes are provided by default , You can ignore the actual physical space , Create a large capacity logical volume . Without any human intervention , It can meet the different and dynamic capacity requirements of different virtual machines , Dramatically simplify capacity management .
05 Business scenario
In new information technology 、 In the context of mobile Internet , The bare metal server based on distributed full flash block storage can meet the needs of Internet 、 Artificial intelligence 、 big data 、 Genetic engineering and other technology companies , With its ultra-high cost performance 、 High performance 、 Customizable 、 Send property rights and other advantages , Solve the problem of resource shortage of customers in the expansion period .
1、 Finance 、 Securities industry scene with high requirements for safety and supervision , Enterprises that have strict requirements for data security .
2、 High performance computing scenarios : Supercomputing Center 、 High performance computing scenarios such as gene sequencing have a large amount of data processing , The computing performance of the server 、 stability 、 High real-time requirements .
3、 Core database scenario : Some key database services cannot be deployed on virtual machines , It has to be exclusive through resources 、 Network isolation 、 Physical servers with guaranteed performance .
4、 Mobile application scenarios : Around mobile apps , Especially the development of mobile games 、 test 、 go online 、 operating .
边栏推荐
- The difference between link and @import importing external styles
- 如何 Pr 一个开源composer项目
- Set the background color of a cell in the table
- Hcia-r & s self use notes (27) comprehensive experiment
- JDBC连接数据库详细步骤
- What is nmap and how to use it
- [untitled]
- dcat 批量操作弹窗及参数传递
- Extreme deflation and perpetual motion machine model will promote the outbreak of platofarm
- 完全去中心化的编程模式,不需要服务器,也不需要ip,就像一张漫无目的的网络、四处延伸
猜你喜欢

北京宝德&TaoCloud共建信创之路

Starfish OS:以现实为纽带,打造元宇宙新范式

DAY15:文件包含漏洞靶场手册(自用 file-include 靶场)

OpenAtom OpenHarmony分论坛圆满举办,生态与产业发展迈向新征程

Move protocol global health declaration, carry out the health campaign to the end

完全去中心化的编程模式,不需要服务器,也不需要ip,就像一张漫无目的的网络、四处延伸

Win10 compiles ffmpeg (including ffplay)

The completely decentralized programming mode does not need servers or IP, just like a aimless network extending everywhere

Plato farm is expected to further expand its ecosystem through elephant swap

QFrame类学习笔记
随机推荐
IDEA使用JDBC连接MySQL数据库个人详细教程
浅谈分布式全闪存储自动化测试平台设计
Laravel service container (inheritance and events)
深度学习的趣味app简单优化(适合新手)
Sports health is deeply rooted in the hearts of the people, and move protocol leads quality life
Sliding switch of tab of uniapp component
DAY5:PHP 简单语法与使用
What is wapiti and how to use it
Fvuln-自动化web漏洞检测工具
全闪分布式,如何深度性能POC?
量化开发必掌握的30个知识点【什么是分笔逐笔数据】?
Windows下cmd窗口连接mysql并操作表
DAY13:文件上传漏洞
QT layout management -- Part stretch principle and sizepolicy
“山东大学移动互联网开发技术教学网站建设”项目实训日志一
如何在加密市场熊市中生存?
DAY4:MySQL 数据库的建立及简单实用
“山东大学移动互联网开发技术教学网站建设”项目实训日志六
超简单集成HMS ML Kit 实现parental control
Use QSS to style the form