Start Me Up

Islam, Safiqul; Welzl, Michael

doi:10.1145/2959424.2959440

Cited by 11 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also proposed a lightweight, dynamically configured TCPin-UDP (TiU) encapsulation scheme to enforce a common bottleneck by ensuring the same 5-tuple is used by multiple connections. We demonstrated the efficacy of our mechanism using ns2 and an implementation in FreeBSD [15], [16].…”

Section: Single-path Tcp Congestion Control Couplingmentioning

confidence: 99%

How not to IETF: Lessons Learned From Failed Standardization Attempts

Welzl

Ott²,

Perkins

et al. 2023

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and Other Affiliated Events (PerCom Work

Self Cite

View full text Add to dashboard Cite

Protocol standards work is an interesting mixture of technical, political, financial, and human factors. Standardization processes require stamina as they may be lengthy, and they demand frustration resistance as they may hold surprises at all stages. While this certainly bears some similarity to academic endeavors, the need to build broader consensus and the potential of far reaching industry impact, among other factors, lead to different incentives and value systems. Peer review perspectives may also differ notably. In this paper, we discuss issues we came across in the past when trying to develop and advance technologies in the IETF or push presumed solid technology solutions towards standardization. We summarize our personal perspectives on the lessons learned.

show abstract

Section: Single-path Tcp Congestion Control Couplingmentioning

confidence: 99%

How not to IETF: Lessons Learned From Failed Standardization Attempts

Welzl

Ott²,

Perkins

et al. 2023

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and Other Affiliated Events (PerCom Work

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are several research proposals on changing the semantics or implementation of TCP, according to application needs, such as sharing the congestion window [20] for faster convergence, advertising the send buffer occupancy for better load balancing and network utilization [1], or adaptively changing the send buffer size for streaming [18].…”

Section: Related Workmentioning

confidence: 99%

Flow control for Latency-Critical RPCs

Kogias

Bugnion

2018

Proceedings of the 2018 Afternoon Workshop on Kernel Bypassing Networks

View full text Add to dashboard Cite

In today's modern datacenters, the waiting time spent within a server's queue is a major contributor of the end-to-end tail latency of µs-scale remote procedure calls. In traditional TCP, congestion control handles in-network congestion, while flow control was designed to avoid memory overruns in streaming scenarios. The latter is unfortunately oblivious to the load on the server when processing short requests from multiple clients at very high rates. Acknowledging flow control as the mechanism that controls queuing on the end-host, we propose a different flow control mechanism that depends on the application-specific service-level objectives and controls the waiting time in the receivers queue by adjusting the incoming load accordingly. We design this latency-aware flow control mechanism as part of TCP by maintaining a wire-compatible header format without introducing extra messages. We implement a proof-of-concept userspace TCP stack on top of DPDK and we show that the new flow control mechanism prevents applications from violating service-level objectives in a single-server environment by throttling the incoming requests. We demonstrate the true benefit of the approach in a replicated, multi-server scenario, where independent clients leverage the flow-control signal to avoid directing requests to the overloaded servers.

show abstract

“…In [14] an adaptive auto-tuning of TCP pacing that adjusts the pacing speed dynamically is suggested. It is based on the network situation that is complicated by static and manual techniques.…”

Section: Related Workmentioning

confidence: 99%

Congestion Aware Packet Routing for Delay Sensitive Cloud Communications

Nyangaresi¹,

Abeka²,

Ogara³

2017

ijcna

View full text Add to dashboard Cite

-In the recent years, many organizations have turned to cloud technology to support their information technology services.The cloud servers are therefore increasingly holding huge and sensitive information belonging to diverse groups of individuals and companies. Additionally, some organizations employ the cloud to provide them with online backup services. One of the most outstanding requirements for cloud customers is availability -the customers must be able to access their information and other resources stored in the cloud any time and from anywhere on the globe. This means that there should be efficient network design such that any delays are averted. The connection between the customer and the cloud can therefore be regarded as delay senstive. Network congestions often lead to delays and packet losses. Transmission control protocol employs four congestion control algorithms -slow start, congestion avoidance, fast retransmit and fast recovery, all of which fail to meet the requirements of delay intolerance. Transmission control protocol pacing has been suggested as a possible solution to delays and packet dropping in computer networks. However, the conventional pacing is static in nature, meaning that constant pauses are introduced between packet transmissions to prevent bursty transmissions which can lead to delays at the receiver buffers. This paper therefore presents a congestion aware packet routing where the delay period is hinged on the prevailing network conditions. This dynamic pacing algorithm was designed and implemented in Spyder using Python programming language. It employed probe signals to gather network intelligence such as the applicable round trip times of the network. Thereafter, this network intelligence was employed to tailor the paces to these network conditions. The results obtained showed that this algorithm introduced longer paces when more packets are transmitted and shorter paces when few packets are transmitted. In so doing, this new algorithm gives enough time for large packets to be delivered and smaller paces when few packets are sent. The analysis was done in terms of bandwidth utilization efficiency, round trip times and congestion window size adjustments. The congestion window -time graphs and throughput -time graphs showed that the developed dynamic pacing algorithm adjusted quickly to network congestions hence ensuring that the network is efficiently utilized by averting delays.

show abstract

Start Me Up

Cited by 11 publications

References 10 publications

How not to IETF: Lessons Learned From Failed Standardization Attempts

How not to IETF: Lessons Learned From Failed Standardization Attempts

Flow control for Latency-Critical RPCs

Congestion Aware Packet Routing for Delay Sensitive Cloud Communications

Contact Info

Product

Resources

About