Adjusting Switching Granularity of Load Balancing for Heterogeneous Datacenter Traffic

Hu, Jinbin; Huang, Jiawei; Lyu, Wenjun; Li, Weihe; Li, Zhaoyi; Jiang, Wenchao; Wang, Jianxin; He, Tian

doi:10.1109/tnet.2021.3088276

Cited by 22 publications

(7 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we all know, DCN consists of two crucial components: Intra-DCN and Inter-DCN, and tens of millions of bytes of data are transmitted via it daily. It happens all the time, whether during requests and responses between different users, backup procedures to prevent data loss, or information transmission between data centers [30,31]. Additionally, the transmission requirements of traffic within and between data centers also differ significantly.…”

Section: Further Discussionmentioning

confidence: 99%

Enhancing Security by Using GIFT and ECC Encryption Method in Multi-Tenant Datacenters

Wang¹,

Liu²,

Rao³

et al. 2023

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

Data security and user privacy have become crucial elements in multi-tenant data centers. Various traffic types in the multi-tenant data center in the cloud environment have their characteristics and requirements. In the data center network (DCN), short and long flows are sensitive to low latency and high throughput, respectively. The traditional security processing approaches, however, neglect these characteristics and requirements. This paper proposes a fine-grained security enhancement mechanism (SEM) to solve the problem of heterogeneous traffic and reduce the traffic completion time (FCT) of short flows while ensuring the security of multi-tenant traffic transmission. Specifically, for short flows in DCN, the lightweight GIFT encryption method is utilized. For Intra-DCN long flows and Inter-DCN traffic, the asymmetric elliptic curve encryption algorithm (ECC) is utilized. The NS-3 simulation results demonstrate that SEM dramatically reduces the FCT of short flows by 70% compared to several conventional encryption techniques, effectively enhancing the security and anti-attack of traffic transmission between DCNs in cloud computing environments. Additionally, SEM performs better than other encryption methods under high load and in largescale cloud environments.

show abstract

Section: Further Discussionmentioning

confidence: 99%

Enhancing Security by Using GIFT and ECC Encryption Method in Multi-Tenant Datacenters

Wang¹,

Liu²,

Rao³

et al. 2023

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each has its advantages and drawbacks. Information about flow throughput [121] is insufficient to determine the type of congestion unless we also know the actual service plan of the client. TCP state analysis can help us analyze TCP state transitions and flow behavior; however, it does not help us differentiate between different kinds of congestion.…”

Section: Challenges In Identifying the Type Of Congestionmentioning

confidence: 99%

TCP/IP stack transport layer performance, privacy, and security issues

Oroo Oyondi Felix

2024

World J. Adv. Eng. Technol. Sci.

View full text Add to dashboard Cite

Transmission Control Protocol/ Internet Protocol (TCP/IP) is the backbone of Internet transmission. The Transport Layer of the TCP/IP stack, which includes TCP (Transmission Control Protocol) and UDP (User Datagram Protocol) protocols, plays a crucial role in ensuring reliable communication between devices over a network. To come up with measures that make networks more secure, it is important to learn about the vulnerabilities that exist in the transport TCP/IP stack and then have an understanding of the typical attacks carried out in such layer. This paper explores how the TCP Protocol works, the TCP/IP 3 Way Handshake, TCP Header Structure, the typical vulnerabilities and the classical attacks of transport layer TCP/IP, tools, and solutions adopted to prevent and reduce the chances of some of these attacks. The findings indicated that the major TCP/ IP stack transport layer threats include Finger printing, SYN Flood, TCP reassembly and sequencing, IP Spoofing, TCP session hijacking, RST and FIN denial of service attack, Ping of Death, Low Rate/ Shrew Attacks. Their preventive measures and mechanisms are discussed.

show abstract

“…ECMP and LetFlow easily degrade the link utilization due to their inflexibility. QDAPS flexibly selects the port with the shortest buffer queue for forwarding packets to avoid congestion, so its FCT is close to PDLB [37][38][39].…”

Section: Large-scale Simulation Testmentioning

confidence: 99%

PDLB: Path Diversity-aware Load Balancing with adaptive granularity in data center networks

Gao,

Huang,

et al. 2023

J Cloud Comp

Self Cite

View full text Add to dashboard Cite

Modern data center topologies often take the form of a multi-rooted tree with rich parallel paths to provide high bandwidth. However, various path diversities caused by traffic dynamics, link failures and heterogeneous switching equipment widely exist in the production datacenter network. Therefore, the multi-path load balancer in data center should be robust to these diversities. Although prior fine-grained schemes such as RPS and Presto make the best use of available paths, However, they are prone to experiencing packet reordering problem under the asymmetric topology. The coarse-grained solutions such as ECMP and LetFlow effectively avoid packet reordering, but easily lead to under-utilization of multiple paths. To cope with these inefficiencies, we propose a load balancing mechanism called PDLB, which adaptively adjusts flowcell granularity according to path diversity. PDLB increases flowcell granularity to alleviate packet reordering under large degrees of topology asymmetry, while reducing flowcell granularity to obtain high link utilization under small degrees of topology asymmetry. PDLB is only deployed on the sender without any modification on switch. We evaluate PDLB through large-scale NS2 simulations. The experimental results show that PDLB reduces the average flow completion time by up to $$\sim$$ ∼ 8-53% over the state-of-the-art load balancing schemes.

show abstract

Adjusting Switching Granularity of Load Balancing for Heterogeneous Datacenter Traffic

Cited by 22 publications

References 52 publications

Enhancing Security by Using GIFT and ECC Encryption Method in Multi-Tenant Datacenters

Enhancing Security by Using GIFT and ECC Encryption Method in Multi-Tenant Datacenters

TCP/IP stack transport layer performance, privacy, and security issues

PDLB: Path Diversity-aware Load Balancing with adaptive granularity in data center networks

Contact Info

Product

Resources

About