An Overview of Packet Reordering in Transmission Control Protocol (TCP): Problems, Solutions, and Challenges

Leung, Ka-Cheong; Li, V.O.K.; Yang, Daiqin

doi:10.1109/tpds.2007.1011

Cited by 150 publications

(99 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the assumption of congestion loss does not hold because the missing packet was caused by e.g. packet reordering, severe performance degradation can occur [8], [3], [9].…”

Section: Impact Of Packet Reorderingmentioning

confidence: 99%

I'll be a bit late — packet reordering in mobile networks

et al. 2017

View full text Add to dashboard Cite

Data transfer in mobile networks has increased significantly over the past years, and the capacity of these networks has grown accordingly. Due to their different set of characteristics compared to wired networks, they have also received attention from end-to-end developers on transport and application level. However, there exists no research on packet reordering in modern mobile networks, and how a transport layer should be designed to cope with it. In this paper we discuss how to measure packet reordering in mobile networks with the help of TCP. Our analysis in Finnish mobile networks shows that reordering characteristics depend heavily on the operator, but is present in all tested networks, and negatively impacts TCP when not handled. We find that both number of reorderings in a connection and the extent of the reordering is influenced by the sending rate. Additionally, we present the framework for a reordering prevention algorithm which takes into account the findings by automatically adapting to the current sending rate.

show abstract

“…When the assumption of congestion loss does not hold because the missing packet was caused by e.g. packet reordering, severe performance degradation can occur [8], [3], [9].…”

Section: Impact Of Packet Reorderingmentioning

confidence: 99%

I'll be a bit late — packet reordering in mobile networks

et al. 2017

View full text Add to dashboard Cite

show abstract

“…How to rebalance flows across processing cores without impacting network performance, given that dataplane operating systems implement their own TCP/IP networking stack and that TCP/IP performance is negatively impacted whenever packets are either lost or processed out of order [24]. This is particularly challenging whenever the rebalancing operation also involves the reconfiguration of the NIC, which generates inherent race conditions.…”

Section: Dynamic Resource Controls Of Dataplanesmentioning

confidence: 99%

“…Such anomalies have severe consequences in general on the performance of the TCP/IP networking stack [24]. IX's coherence-free design exposes a further constraint: because there are no locks within the TCP/IP stack, two elastic threads cannot process packets from the same flow simultaneously.…”

Section: Dynamic Nic Configurationmentioning

confidence: 99%

Energy proportionality and workload consolidation for latency-critical applications

Prekas

Primorac

Belay

et al. 2015

Proceedings of the Sixth ACM Symposium on Cloud Computing

View full text Add to dashboard Cite

Energy proportionality and workload consolidation are important objectives towards increasing efficiency in largescale datacenters. Our work focuses on achieving these goals in the presence of applications with µs-scale tail latency requirements. Such applications represent a growing subset of datacenter workloads and are typically deployed on dedicated servers, which is the simplest way to ensure low tail latency across all loads. Unfortunately, it also leads to low energy efficiency and low resource utilization during the frequent periods of medium or low load.We present the OS mechanisms and dynamic control needed to adjust core allocation and voltage/frequency settings based on the measured delays for latency-critical workloads. This allows for energy proportionality and frees the maximum amount of resources per server for other background applications, while respecting service-level objectives. Monitoring hardware queue depths allows us to detect increases in queuing latencies. Carefully coordinated adjustments to the NIC's packet redirection table enable us to reassign flow groups between the threads of a latency-critical application in milliseconds without dropping or reordering packets. We compare the efficiency of our solution to the Pareto-optimal frontier of 224 distinct static configurations. Dynamic resource control saves 44%-54% of processor energy, which corresponds to 85%-93% of the Pareto-optimal upper bound. Dynamic resource control also allows background jobs to run at 32%-46% of their standalone throughput, which corresponds to 82%-92% of the Pareto bound.

show abstract

“…Packet reordering (Mogul, 1992;Leung et al, 2007) is a phenomenon in which packets with higher sequence numbers are received earlier than those with smaller sequence numbers. It can be caused by a myriad of reasons.…”

Section: Related Workmentioning

confidence: 99%

“…It can be caused by a myriad of reasons. In Leung et al (2007), five major causes are listed: packet-level multi-path routing, route fluttering, inherent parallelism in modern high-speed routers, link-layer retransmission, and router forwarding lulls. This paper focuses on alleviating the packet reordering caused by another new reason of the multi-path heterogeneity when performing CMT.…”

Section: Related Workmentioning

confidence: 99%

OSIA: Out-of-order Scheduling for In-order Arriving in concurrent multi-path transfer

Wang

Liao

2012

Journal of Network and Computer Applications

View full text Add to dashboard Cite

One major problem of concurrent multi-path transfer (CMT) scheme in multi-homed mobile networks is that the utilization of different paths with diverse delays may cause packet reordering among packets of the same flow. In the case of TCP-like, the reordering exacerbates the problem by bringing more timeouts and unnecessary retransmissions, which eventually degrades the throughput of connections considerably. To address this issue, we first propose an Out-of-order Scheduling for In-order Arriving (OSIA), which exploits the sending time discrepancy to preserve the in-order packet arrival. Then, we formulate the optimal traffic scheduling as a constrained optimization problem and derive its closedform solution by our proposed progressive water-filling solution. We also present an implementation to enforce the optimal scheduling scheme using cascaded leaky buckets with multiple faucets, which provides simple guidelines on maximizing the utilization of aggregate bandwidth while decreasing the probability of triggering 3 dupACKs. Compared with previous work, the proposed scheme has lower computation complexity and can also provide the possibility for dynamic network adaptability and finer-grain load balancing. Simulation results show that our scheme significantly alleviates reordering and enhances transmission performance.

show abstract

An Overview of Packet Reordering in Transmission Control Protocol (TCP): Problems, Solutions, and Challenges

Cited by 150 publications

References 42 publications

I'll be a bit late — packet reordering in mobile networks

I'll be a bit late — packet reordering in mobile networks

Energy proportionality and workload consolidation for latency-critical applications

OSIA: Out-of-order Scheduling for In-order Arriving in concurrent multi-path transfer

Contact Info

Product

Resources

About