Runtime application observability is crucial not only for system provenance but also for the orchestration of deployed microservices in dynamic sandboxed distributed computing environments. Also, log extraction and aggregation in highly distributed and sandboxed environments pose significant challenges, especially when preserving the causal order of the events triggered by different asynchronous microservices running over multiple hosts. However, ensuring causally consistent logging of application events is challenging, although it is vital for continuously tracing and profiling the underlying platform. This paper proposesXPLOG, a scalable, pluggable, easily deployable, and dynamic runtime observability framework for distributed sandboxed computing platforms that leverages the capability of extended Berkeley Packet Filters (eBPF) to intercept system-level events within the host while capturing and amalgamating relevant application and system logs to produce globally causally-consistent log streams. Through qualitative and quantitative analysis, we observe thatXPLOGsignificantly improves log richness with minimum system overhead while preserving the causality of log-generating events across multiple microservices.

Provenance tracking has been widely used in the recent literature to debug system vulnerabilities and find the root causes behind faults, errors, or crashes over a running system. However, the existing approaches primarily developed graph-based models for provenance tracking over monolithic applications running directly over the operating system kernel. In contrast, the modern DevOps-based service-oriented architecture relies on distributed platforms, like serverless computing that uses container-based sandboxing over the kernel. Provenance tracking over such a distributed micro-service architecture is challenging, as the application and system logs are generated asynchronously and follow heterogeneous nomenclature and logging formats. This paper develops a novel approach to combining system and micro-services logs together to generate a Universal Provenance Graph (UPG) that can be used for provenance tracking over serverless architecture. We develop a Loadable Kernel Module (LKM) for runtime unit identification over the logs by intercepting the system calls with the help from the control flow graphs over the static application binaries. Finally, we design a regular expression-based log optimization method for reverse query parsing over the generated UPG. A thorough evaluation of the proposed UPG model with different benchmarked serverless applications shows the system’s effectiveness.

Internet of Things (IoT) platforms use a large number of low-cost resource constrained devices and generates millions of short-flows. In-network processing is gaining popularity day by day to handle IoT applications and services. However, traditional software-defined networking (SDN) based management systems are not suitable to handle the plug and play nature of such systems. In this paper, we propose Aloe, an auto-scalable SDN orchestration framework. Aloe exploits in-network processing framework by using multiple lightweight controller instances in place of service grade SDN controller applications. The proposed framework ensures the availability and significant reduction in flow-setup delay by deploying instances in the vicinity the resource constraint IoT devices dynamically. Aloe supports fault-tolerance with recovery from network partitioning by employing self-stabilizing placement of migration capable controller instances. Aloe also provides resource reservation for micro-controllers so that they can ensure the quality of services (QoS). The performance of the proposed system is measured by using an in-house testbed along with a large scale deployment in Amazon Web services (AWS) cloud platform. The experimental results from these two testbeds show significant improvement in response time for standard IoT based services. This improvement of performance is due to the reduction in flow-setup time. We found that Aloe can improve flow-setup time by around 10%-30% in comparison to one of the states of the art orchestration framework.

In the presence of the Internet of Things (IoT) devices, the end-users require a response within a short amount of time which the cloud computing alone cannot provide. Fog computing plays an important role in the presence of IoT devices in order to meet such delay requirements. Though beneficial in these latency-sensitive scenarios, the fog has several implementation challenges. In order to solve the problem of micro-service placement in the fog devices, we propose a framework with the objective of achieving low response time. This problem has been formulated as an optimization problem to improve the response time by considering the time-varying resource availability of the fog devices as constraints. We propose an orchestration framework named Pick-Test-Choose (PTC) to solve the problem. PTC uses Bayesian Optimization based iterative reinforcement learning algorithm to find out a micro-service allocation based on the current workload of the fog devices. PTC employs containers for service isolation and migration of the micro-services. The proposed architecture is implemented over an in-house testbed as well as in iFogSim simulator. The experimental results show that the proposed framework performs better in terms of response time compared to various other baselines.

Management of networked Internet of Things (IoT) infrastructure with in-network processing capabilities is becoming increasingly difficult due to the volatility of the system with low-cost resource-constraint devices. Traditional software-defined networking (SDN) based management systems are not suitable to handle the plug and play nature of such systems. Therefore, in this paper, we propose Aloe, an elastically auto-scalable SDN orchestration framework. Instead of using service grade SDN controller applications, Aloe uses multiple lightweight controller instances to exploit the capabilities of in-network processing infrastructure. The proposed framework ensures the availability and significant reduction in flow-setup delay by deploying instances near the resource constraint IoT devices dynamically. Aloe supports fault-tolerance and can recover from network partitioning by employing self-stabilizing placement of migration capable controller instances. The performance of the proposed system is measured by using an in-house testbed along with a large scale deployment in Amazon web services (AWS) cloud platform. The experimental results from these two testbed show significant improvement in response time for standard IoT based services. This improvement of performance is due to the reduction in flow-setup time. We found that Aloe can improve flow-setup time by around 10%-30% in comparison to one of the state of the art orchestration framework.

The primary objective behind the development of Multipath TCP (MPTCP) is to aggregate throughput by creating multiple sub-flows via different network interfaces. A difference in end-to-end path characteristics for the sub-flows may generate out of order segments, causing head of line (HOL) blocking at the receiver. An intelligent selection of a subset of the available sub-flows can reduce the number of out of order segments; thus sub-flow selection can enhance the performance of MPTCP. In this paper, we first propose a Markov model for the performance of MPTCP in terms of end-to-end sub-flow characteristics. Based on the theoretical model, we present an optimization framework for active sub-flow selection by exploiting the controller functionalities over a software defined network (SDN) architecture. Finally, experimental results are obtained to demonstrate performance improvements of MPTCP in terms of aggregated throughput.

The current developments of software defined networking (SDN) paradigm provide a flexible architecture for network control and management, in the cost of deploying new hardwares by replacing the existing routing infrastructure. Further, the centralized controller architecture of SDN makes the network prone to single point failure and creates performance bottleneck. To avoid these issues and to support network manageability over the existing network infrastructure, we develop Flipper in this paper, that uses only software augmentation to convert existing off-the-shelf routers to network policy design and enforcement points (PDEP). We develop a distributed self-stabilized architecture for dynamic role change of network devices from routers to PDEPs, and make the architecture fault-tolerant. The performance of Flipper has been analyzed from both simulation over synthetic networks, and emulation over real network protocol stacks, and we observe that Flipper is scalable, flexible and fail-safe that can significantly boost up the manageability of existing network infrastructure.

This poster provides an in-depth analysis of the primary path effect in Multi-path TCP using thorough experimentation over a realistic network setup. We observe the impact of various primary path parameters, like bandwidth, delay and loss, over the end-to-end performance. It is shown that under certain circumstances overall network performance can be improved by more than 50% with proper primary path selection. This study may drive the research community towards the design of new segment scheduling algorithms considering the effect of primary path selection over Multi-path TCP.

Existing studies on evolution of social network largely focus on addition of new nodes and links in the network. However, as network evolves, existing relationships degrade and break down, and some nodes go to hibernation or decide not to participate in any kind of activities in the network where it belongs. Such nodes and links, which we refer as "dull", may affect analysis and prediction tasks in networks. This paper formally defines the problem of predicting dull nodes and links at an early stage, and proposes a novel time aware method to solve it. Pruning of such nodes and links is framed as "network data cleaning" task. As the definitions of dull node and link are non-trivial and subjective, a novel scheme to label such nodes and links is also proposed here. Experimental results on two real network datasets demonstrate that the proposed method accurately predicts potential dull nodes and links. This paper further experimentally validates the need for data cleaning by investigating its effect on the well-known "link prediction" problem.

This paper proposes an opportunistic approach to mitigating the hidden and exposed node problem in a high-throughput mesh network, by exploiting the frame aggregation and block acknowledgment (BACK) capabilities of IEEE 802.11n/ac wireless networking standard. Hidden nodes significantly drop down the throughput of a wireless mesh network by increasing data loss due to collision, whereas exposed nodes cause under-utilization of the achievable network capacity. The problem becomes worse in IEEE 802.11n/ac supported high-throughput mesh networks, due to the large physical layer frame size and prolonged channel reservation from frame aggregation. The proposed approach uses the standard carrier sense multiple access (CSMA) technology along with an opportunistic collision avoidance (OCA) method that blocks the communication for hidden nodes and opportunistically allows exposed nodes to communicate with the peers. The performance of the proposed CSMA/OCA mechanism for high throughput mesh networks is studied using the results from an IEEE 802.11n+s wireless mesh networking testbed, and the scalability of the scheme has been analyzed using simulation results.