Proactive Incast Congestion Control in a Datacenter Serving Web Applications

Wang, Haoyu; Shen, Haiying

doi:10.1109/infocom.2018.8485989

Cited by 16 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For multiple co-existing aggregators, CCMA schedules them sequentially to avoid traffic collisions. DSRAL [16], ARS [10], and PICC [17] avoid TCP incast by controlling the number of concurrent TCP connections. However, these methods all assume that the receiver is aware of the remaining available bandwidth, which is usually not valid in real data centers.…”

Section: Related Workmentioning

confidence: 99%

PFDCT: An Enhanced Transport Layer Protocol for Precise Flow Control in Data Centers

Wang

et al. 2023

Electronics

View full text Add to dashboard Cite

This paper proposes an enhanced transport layer protocol for precise flow control in data centers, referred to as PFDCT, combining explicit rate control (priority scheduling) and implicit rate control (marking algorithm with dynamic threshold) innovatively, while satisfying the transmission requirements of each data flow. It enables multiple data flows to share the bandwidth fairly, which is rarely achieved by previous data transmission protocols. Our design stems from the observation that different packets in a data center network need to be processed differentially and that the accuracy of the feedback of the indication information to the link state will directly affect the effectiveness of the congestion control mechanism. Our tests show that PFDCT has lower network jitter, better fairness, and significant performance gains over existing proposals (DCTCP, ICTCP, and L2DCT) in terms of Flow Completion Time (FCT) and throughput on average. Furthermore, we discussed the impact of the marking algorithm with dynamic thresholds on the performance of PFDCT, and the results of the experiments show that the addition of the marking algorithm will further improve the performance of PFDCT in terms of packet loss rate, latency, and FCT.

show abstract

Section: Related Workmentioning

confidence: 99%

PFDCT: An Enhanced Transport Layer Protocol for Precise Flow Control in Data Centers

Wang

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Wu et al [227] designed an Incast congestion Control for the TCP (ICTCP) scheme at the receiver side to adjust TCP receive window proactively. Wang et al [228] also proposed proactive Incast congestion control in a DC network serving web applications. Packet pacing is also proposed as another Incast solution.…”

Section: ) Related Workmentioning

confidence: 99%

Latency and Throughput Optimization in Modern Networks: A Comprehensive Survey

Mirzaeinnia¹,

Mirzaeinia²,

Rezgui³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…According to the experiment [22], the k is set to 0.6. The SLA violation is represented by the percentage of time, during which active PMs have experienced the CPU utilization of 100% [31]. The results of power consumption and SLA violation are given in Figure 12 and Figure 13.…”

Section: ) Power Consumption and Sla Violationmentioning

confidence: 99%

A Weighted PageRank-Based Algorithm for Virtual Machine Placement in Cloud Computing

2019

View full text Add to dashboard Cite

Virtualization makes virtual machine placement (VMP) one of the most important technology in cloud computing. An effective VMP algorithm can significantly improve resource utilization of physical machines (PMs) in cloud datacenters. In this paper, we propose a VMP algorithm based on weighted PageRank (WPRVMP), which pursued to minimize the number of active PMs and improve the total resource utilization of all PMs in cloud datacenters. The impact of unplaced virtual machines (VMs) in the VMP process on the placement results, and the impact of VMP on the total resource utilization of all PMs are considered in this algorithm, to avoid the algorithm to fall into local optimal solution. In the process of selecting PM for each VM, the number of unplaced VMs of different types in the VMP process is considered in WPRVMP by weighted. The weighted PageRank algorithm is used to measure the possibility of a PM making full use of resources under different VMP conditions. The algorithm then ranks PMs according to the impact of the given VM is placed on each PM on the maximum resource utilization of all PMs, and places the VM based on the ranking results. Experimental results show that our algorithm is superior to other algorithms in reducing the number of active PMs and improving the resource utilization of PMs.

show abstract

Proactive Incast Congestion Control in a Datacenter Serving Web Applications

Cited by 16 publications

References 24 publications

PFDCT: An Enhanced Transport Layer Protocol for Precise Flow Control in Data Centers

PFDCT: An Enhanced Transport Layer Protocol for Precise Flow Control in Data Centers

Latency and Throughput Optimization in Modern Networks: A Comprehensive Survey

A Weighted PageRank-Based Algorithm for Virtual Machine Placement in Cloud Computing

Contact Info

Product

Resources

About