EBM:Traffic-Based Differentiated Enhanced Buffer Management in Data Center Networks

Cloud applications have reshaped the model of services and infrastructure of the Internet. Search engines, social networks, content delivery and retail and e-commerce sites belong to this group of applications. An important element in the architecture of data centers where these applications run is the communication infrastructure, commonly known as data center networks (DCNs). A critical challenge DCNs have to address is the processing of the traffic of cloud applications, which due to its properties is essentially different to the traffic of other Internet applications. In order to improve the responsiveness and throughput of applications, DCNs should be able to prioritize short flows (a few kB) over long flows (several MB). However, given the time and space variations the traffic presents, the information about flow sizes is not available in advance in order to plan the flow scheduling. There has been a wealth of solutions developed in this space, and prior work includes flow scheduling mechanisms optimizing for a specific workload but fall short when workloads are not known in advance, or comprise a collection of applications changing dynamically. In this paper, we present an adaptable mechanism called Adaptable Workload-Agnostic Flow Scheduling (AWAFS). It is an adaptable approach that can adjust in an agnostic way the scheduling configuration of DCN forwarding devices. This agnostic adjustment contributes to reduce the Flow Completion Time (FCT) of those short flows, representing around 85% of the traffic handled by cloud applications. AWAFS operates by observing the traffic and detecting statistical properties that provide a hint to adapt the scheduling parameters. Our evaluation results based on simulation show that AWAFS can reduce the average FCT of short flows between 16.9% and 45.2% when compared to the best existing agnostic non-adaptable solution, without inducing starvation on long flows. Indeed, it can provide improvements as high as 39% for long flows. Additionally, AWAFS can improve the FCT for short flows in scenarios with high heterogeneity in the traffic present in the network, with a reduction up to 5% for the average FCT and 15% for the tail FCT.

In the era of cloud computing, data center network (DCN) can consume a significant amount of power (e.g., 10 to 20 percent) in large-scale data centers. To reduce the power consumption of DCN, traffic consolidation has been recently proposed as an effective approach to reduce the number of DCN devices in use. However, existing consolidation approaches do not sufficiently consider the flow completion time (FCT) requirement. On one hand, missing the FCT deadlines can cause serious violation of service-level agreement, especially for delay-sensitive networking services, such as web search and E-commerce. On the other hand, keeping all the devices on to make FCTs much shorter than the desired requirements is unnecessary because 1) users may not be able to perceive the difference, and 2) such a greedy strategy can lead to unnecessarily high DCN power consumption and thus more electricity costs. In this paper, we propose FCTcon, a dynamic FCT control strategy for DCN power optimization. FCTcon is designed rigorously based on control theory to dynamically control the FCT of delay-sensitive traffic flows exactly to the requirements, such that the desired FCT performance is guaranteed while the maximum amount of DCN power savings can be achieved. Results from both hardware experiments and simulation evaluation demonstrate that, compared to the state-of-the-art DCN power optimization schemes, FCTcon can improve the DCN FCT performance, while achieving nearly the same or even more power savings. Consequently, FCTcon can result in more than 22.0 to 62.2 percent extra net profits for a data center with 50K servers. In addition, we further propose two extended designs of FCTcon to handle the coflow abstraction recently proposed for DCN, which successfully reduce the coflow deadline miss ratio by 12 to 15 percent.

Data center network (DCN) can consume a significant amount of power (e.g., 10% to 20%) in large-scale data centers. To reduce the power consumption of DCN, traffic consolidation has been recently proposed as an effective approach to reduce the number of DCN devices in use. However, existing consolidation approaches do not sufficiently consider the flow completion time (FCT) requirement. On one hand, missing the FCT deadlines can cause serious violation of service-level agreement, especially for delay-sensitive networking services, such as web search and E-commerce. On the other hand, keeping all the devices on to make FCTs much shorter than the desired requirements is unnecessary because 1) users may not be able to perceive the difference, and 2) such a greedy strategy can lead to unnecessarily high DCN power consumption and thus more electricity costs. In this paper, we propose FCTcon, a dynamic FCT control strategy for DCN power optimization. FCTcon is designed rigorously based on control theory to dynamically control the FCT of delay-sensitive traffic flows exactly to requirements, such that the desired FCT performance is guaranteed while the maximum amount of DCN power savings can be achieved. Results from both hardware experiments and simulation evaluations demonstrate that, compared to the state-of-the-art DCN power optimization schemes, FCTcon can improve the DCN FCT performance, while achieving nearly the same or even more power savings. Consequently, FCTcon can result in more than 22.0% to 62.2% extra net profits for a data center with 50K servers.

One of the major issues in Data Center Networks (DCNs) is related to elephant flows. These flows typically are primarily responsible for network congestion, causing impacts on applications that are intolerant to delays. Although there are several works in the literature that analyze this type of traffic, none of them consider the impact of elephant flow size on the throughput and on the Flow Completion Time (FCT). This article presents the EFM (Elephant Flow Manager) as a complete solution for monitoring and re-routing elephant flows in DCNs, by observing the size of these flows in the network. The tests performed show that the size of the elephant flows influences the throughput and the FCT of the applications and, therefore, deserves to be observed. The evaluation of the solution was performed comparing the joint use of EFM with ECMP (EqualCost Multi-path). In all tests, our re-routing solution proved to be better when compared to pure routing solely with ECMP. Then, this paper presents three main contributions: (1) it compares our solution with the ECMP, (2) highlights the importance of the size of the elephant flows in the re-routing of these in DCNs and (3) preliminary tests indicate that due to the decrease in FCT, it is possible to reduce the energy consumption in the data center.

Numerous scheduling approaches have been proposed to improve user experiences in a data center network (DCN) by reducing flow completion time (FCT). Mimicking the shortest job first (SJF) has been proved to be the prominent way to improve FCT. To do so, some approaches require flow size or completion time information in advance, which is not possible in scenarios like HTTP chunk transfer or database query response. Some information-agnostic schemes require involving end-hosts for counting the number of bytes sent. We present Longer Stay Less Priority (LSLP), an information-agnostic flow scheduling scheme, like Multi-Level Feedback Queue (MLFQ) scheduler in operating systems, that aims to mimic SJF using P4 switches in a DCN. LSLP considers all the flows as short flows initially and assigns them to the highest priority queue, and flows get demoted to the lower priority queues over time. LSLP estimates the active time of a flow by leveraging the state-of-the-art P4 switch’s programmable nature. LSLP estimates the active time of a group of new flows that arrive during a time interval and assigns their packets to the highest priority. At the beginning of the next time interval, arriving packets of old flows are placed one priority lower except for those already in the lowest priority queue. Therefore, short flows can be completed in the few higher priority queues while long flows are demoted to lower priority queues. We have evaluated LSLP via a series of tests and shown that its performance is comparable to the existing scheduling schemes.

Reducing the power consumption and maintaining the Flow Completion Time (FCT) for the Quality of Service (QoS) of applications in Data Center Networks (DCNs) are two major concerns for data center operators. However, existing works either fail in guaranteeing the QoS due to the neglect of the FCT constraints or achieve a less satisfying power efficiency. In this paper, we propose SmartFCT, which employs Software-Defined Networking (SDN) coupled with the Deep Reinforcement Learning (DRL) to improve the power efficiency of DCNs and guarantee the FCT. The DRL agent can generate a dynamic policy to consolidate traffic flows into fewer active switches in the DCN for power efficiency, and the policy also leaves different margins in different active links and switches to avoid FCT violation of unexpected short bursts of flows. Simulation results show that with similar FCT guarantee, SmartFCT can save 8% more of the power consumption compared to the state-of-the-art solutions.

Network congestion causes severe transmission performance loss. Congestion control is the key to achieve low latency, high bandwidth and high stability. Due to the high regularity of topologies, datacenter networks contain abundant resources of equal-cost paths inherently and have huge potential for high-bandwidth transmission. Taking in-network telemetry (INT) information as the congestion signal, congestion control algorithms can monitor the network based on precise link load data. Hence the INT-based algorithm is the focus of recent high-precision congestion control research. However, existing INT-based congestion control algorithms handle the single-path transmission between the sender and the receiver, which cannot make full use of the abundant equal-cost paths resources in the network. In this paper, we make the first attempt to propose a multi-path INT-based congestion control algorithm, called MPICC. Compared with the most advanced INT-based congestion control algorithm HPCC, our method realizes multi-path coordinated transmission of data packets in datacenter networks. We conduct extensive experiments under various workloads to evaluate the performance of MPICC. The experimental results show that under the condition of ensuring high throughput of end hosts, MPICC is able to use multi-path to transmit data packets, which greatly reduces the flow completion time (FCT) of the flow in the network. Specifically, under three common datacenter workloads, Cache Follower, Web Search and Web Server, MPICC reduces the average flow completion time of the network by 20.1%, 14.4%, and 39.5%, respectively, and shortens the 97th-percentile flow completion time by 39.9%, 18.9% and 57.9%, respectively.KeywordsCongestion controlIn-network telemetry (INT)Multi-pathDatacenter networksProgrammable switch

In the data center environment, meeting the dissimilar requirements of transmission performance for long and short data flows is crucial for guaranteeing the data center service quality. It is well known that optimizing the network transmission performance is the key. Abundant research studies have reported that designing an effective load-balancing scheme can boost the network performance by enhancing the path utilization of multirooted data center networks. Unfortunately, the existing data center load-balancing schemes fail to provide satisfying flow-level transmission performance since they choose to ignore the constant changing path status and blindly assign paths to data flows regardless of their different performance requirements. In order to solve these issues, we propose a data center load-balancing scheme called TAM to meet the performance requirements of long and short flows simultaneously. In detail, TAM leverages the traffic-aware ECN marking mechanism to force long flows to proactively maintain the switch queue length at a low level and release bandwidth to short flows when they compete for the bottleneck link. On the contrary, TAM carries out the coarse-grained routing or rerouting for short and long flows, respectively, in real time by perceiving the path status. In this way, the short flows achieve low delay transmission while the long flows obtain high throughput. The simulation results based on NS2 tests show that TAM achieves up to 60% lower FCTs for short flows and a 40% improvement in goodput for long flows.

Software-Defined Data Center Networks (SDDCNs) utilizes Software Defined Networking (SDN) as a network architecture to achieve highly flexible, programmable, and automated management of Data Center Networks (DCNs). The high energy consumption of DCNs remains a persistent and significant challenge. Thus, the energy saving is crucial and imperative for DCNs. Current energy-efficient solutions primarily rely on flow consolidation and dynamic device sleeping techniques to reduce energy consumption. However, these approaches often yield long Flow Completion Time (FCT), potentially resulting in violations of service-level agreements, particularly for delay-sensitive applications. In this paper, we formulate the problem of minimizing the power consumption in SDDCNs as key objective while ensuring timely FCT for delay-sensitive applications. To solve this problem, we first introduce the Active Network Generation (ANG) approach, which generates a minimal active subnet with the least number of active devices while meeting the current traffic demand. Subsequently, we propose two algorithms based on the type of applications: the Delay-Tolerant Flow Route (DTFR) algorithm for delay-tolerant applications and the Delay-Sensitive Flow Route (DSFR) algorithm for delay-sensitive applications. Simulation results demonstrate that our propose solution achieves an energy-saving rate of up to 67.77% and significantly reduces FCT compared to benchmark solutions.

Modern datacenters provide a wide variety of application services, which generate a mix of delay-sensitive short flows and throughput-oriented long flows, transmitting in the multi-path datacenter network. Though the existing load balancing designs successfully make full use of available parallel paths and attain high bisection network bandwidth, they reroute flows regardless of their dissimilar performance requirements. The short flows suffer from the problems of large queuing delay and packet reordering, while the long flows fail to obtain high throughput due to low link utilization and packet reordering. To address these inefficiency, we design a fine-grained load balancing scheme, namely TR (Traffic-aware Rerouting), which identifies flow types and executes flexible and traffic-aware rerouting to balance the performances of both short and long flows. Besides, to avoid packet reordering, TR leverages the reverse ACKs to estimate the switch-to-switch delay, thus excluding paths that potentially cause packet reordering. Moreover, TR is only deployed on the switch without any modification on end-hosts. The experimental results of large-scale NS2 simulations show that TR reduces the average and tail flow completion time for short flows by up to 60% and 80%, as well as provides up to 3.02x gain in throughput of long flows compared to the state-of-the-art load balancing schemes.

TCP is widely used in the communications between servers in data centers. However, TCP has scaling limit that its ability to provide fair sharing at bottleneck link is reduced as the number of competing flows increases. Such limit is common in current data center networks and causes unfairness among TCP flows on a small time scale. The unfairness would add unpredictable delay to short flows, which would affect the user experiences of soft real-time applications. In this paper, we propose a simple and cost-effective method — shrinking MTU — to improve the fairness among TCP flows. Through model analysis and extensive simulations, the fairness on a small time scale is improved and the completion time of short flows is reduced by decreasing MTU size.

Nearly 50% of the energy overhead in today's datacenters comes from host-to-host data transfers, which largely depend on the transport layer performance. Multipath TCP (MPTCP) has recently been suggested as a promising transport protocol to improve datacenter network throughput, yet it also increases the host CPU power consumption. It remains unclear whether datacenters can indeed benefit from using MPTCP from the perspective of energy efficiency. By analyzing the performance of MPTCP, we show that (1) despite consuming higher host CPU power than TCP, MPTCP can largely reduce the long flow completion time and thus save the aggregated energy; (2) link-sharing subflows in MPTCP not only has negative impact on both throughput-sensitive long flows and latency-sensitive short flows, but also noticeably increases the host CPU power, especially for short flows. We present MPTCP-D, an energy-efficient variant of multipath TCP for datacenters. MPTCP-D incorporates a novel congestion control algorithm that can provide energy efficiency by minimizing the flow completion time, and an extra subflow elimination mechanism that can preclude link-sharing subflows from increasing the host CPU power. We implement MPTCP-D in the Linux kernel and study its performance by experiments on Amazon EC2. Our results show that, without degrading the performance of the long flow throughput and short flow completion time, MPTCP-D reduces the long flow energy consumption by up to 72% compared to DCTCP for data transfers, and reduces the short flow power consumption by up to 46% compared to MPTCP with linksharing subflows.

Today’s datacenter networks (DCNs) have been built upon multipath topologies where each path contains multiple links. However, flow scheduling schemes proposed to minimize flow completion times (FCT) in DCNs are based on algorithms which are optimum or close-to-optimum only over single link. Moreover, most of these scheduling schemes seek either fully centralized approaches having overhead of communicating to a central entity or fully distributed approaches requiring changes in the fabric.Motivated by these shortcomings, we present HyLine a simple scheduling design for commodity DCNs which is equipped with a joint load-balancing and flow scheduling (path-aware) design exploiting the multipath nature of DCNs. HyLine takes a hybrid approach and uses the global-awareness of centralized and agility of distributed techniques without requiring any changes in the fabric. To that end, it determines a threshold margin identifying flows for which using centralized approach is beneficial.We have shown through extensive ns2 simulations that despite HyLine’s simplicity, it significantly outperforms existing schemes and achieves lower average and 99th percentile FCTs. For instance, compared to Qjump–state-of-the-art practical scheme– and pFabric–one of the best performing flow scheduling schemes– HyLine reduces average FCT up to 68% and 31%, respectively, under a production datacenter workload.

The objective of congestion control is to maximize network bandwidth utilization and minimize the average flow completion time in data center networks. Key performance indicators required to achieve this objective are high throughput and low packet latency. Existing approaches have proposed various methods to control packet delivery based on various network events or parameters such as packet loss, bottleneck bandwidth, RTT, and queue length. However, these methods often result in suboptimal packet transmission states that compromise throughput or latency. We provide a method to overcome this drawback. To this end, we introduce a congestion control method called PRTT (Predicted RTT) that leverages predicted RTT for congestion control. By using accurately predicted RTT values, PRTT dynamically adjusts the packet delivery rate to control the number of in-flight packets. This enables the transmission to approach states where the buffer holds only a few packets while fully utilizing the link bandwidth. Experimental results show that PRTT achieves higher throughput, lower latency, and shorter flow completion times than other state-of-the-art methods, particularly under bursty traffic. These results demonstrate that PRTT offers a promising solution for congestion control.

In data center networks (DCNs), the flow size is a crucial factor to schedule the traffic, as small flows are usually latency-sensitive (e.g., web search from users) while large flows are not (e.g., backup between two sites). Some existing flow scheduling schemes try to schedule flows based on the prior knowledge of flows, such as flow size and deadline. However, it may be unpractical to obtain the prior information in some scenarios. In this paper, we propose START to minimize the flow completion time (FCT) and guarantee the priority of small flows in DCNs. We control the priorities of packets by leveraging the multiple priority queues based on the amount of data a flow has sent. Switches schedule flows according to their priorities. In addition, to schedule the flows more intelligently, we adjust the threshold of each priority dynamically according to the network loads. A prototype of START has been implemented with ns2 simulations. START is compatible with legacy TCP/IP stacks and deployable with existing commodity switches. The results show that START significantly outperforms existing flow scheduling schemes DCTCP and L2DCT up to 40% and 45% for small flows in changing network status. In some scenarios, START can even achieve better performance than pFabric.