• One Page Summary: Flease – Lease Coordination without a Lock Server

    ·

    Placeholder Icon

    This paper talks about a decentralized lease management solution. In the past, many lock/lease services have been centralized, placing a single authority to manage all locks in the system. Google’s Chubby, Apache ZooKeeper, etcd, and others rely on a centralized approach and backed by some flavor of a consensus algorithm for fault-tolerance. According to Flease authors,…

    Read More

  • One Page Summary: “milliScope: a Fine-Grained Monitoring Framework for Performance Debugging of n-Tier Web Services”

    ·

    Placeholder Icon

    Authors of the ICDCS2017 milliScope paper attack an interesting monitoring problem for distributed systems: detecting and determining a cause of short-lived events in the system. In particular, they address the issue of identifying very short bottlenecks (VSBs) in distributed web services. VSBs manifest themselves as performance degradation of a small number of requests, however they…

    Read More

  • Sonification of Distributed Systems with RQL

    ·

    Placeholder Icon

    In the past, I have discussed sonification as a mean of representing monitoring data. Aside from some silly and toy examples, sonifications can be used for serious applications. In many monitoring cases, the presence of some phenomena is more important than the details about it. In such situations, simple sonification is a perfect way to…

    Read More

  • Retroscoping Zookeeper Staleness

    ·

    Placeholder Icon

    ZooKeeper is a popular coordination service used as part of many large scale distributed systems. ZooKeeper provides a file-system inspired abstraction to the users on top of its replicated key-value store. Like other Paxos-inspired protocols, ZooKeeper is typically deployed on at least 3 nodes, and can tolerate F node failure for a cluster of size…

    Read More

  • Why Government IT is Expensive and Archaic

    ·

    Placeholder Icon

    Disclaimer: I do not work for the government, and my rant below is based on my very limited exposure to how IT works at the US government setting. Why Government IT is Expensive and Archaic? I think, this can be a very long discussion, but I do have a quick answer:  standards imposed by government…

    Read More

  • The First Datastore-driven Vehicle

    ·

    Placeholder Icon

    It is not a secret that procrastination is the favorite activity of most PhD students. I have been procrastinating today, even though my advisor probably wants me to keep writing.  In the midst of my procrastination, I thought: “Why are there self-driving vehicles, but no database-driven vehicles?” As absurd as it sounds, I gave it…

    Read More

  • One Page Summary: “Musketeer: all for one, one for all in data processing systems”.

    ·

    Placeholder Icon

    Many distributed computation platforms and programming frameworks exist today, and new ones constantly popping out from the industry and academia.  Some platforms are domain specific, such as TensorFlow for machine learning. Others, like Hadoop and Naiad are more general, and this generality allows for sophisticated and specialized programming abstractions to be built on top. So…

    Read More

  • One Page Summary: “Slicer: Auto-Sharding for Datacenter Applications”

    ·

    Placeholder Icon

    One of the questions engineers of large distributed system must answer is “where to compute”. This is a big and important question, as we do not want to send a request originating in the US to some server in Australia. It simply makes no sense to incur the communication overhead if there are resources available…

    Read More

  • Monitoring with Retroscope: Detecting Invariant Violations

    ·

    Placeholder Icon

    Earlier I briefly mentioned Retroscope, our distributed snapshot library that makes taking non-blocking, unplanned consistent global distributed snapshots possible. However, these snapshots are only good if we know how to use them well. Of course the most obvious use case is just a data backup, and despite it being an important application for snapshots, I…

    Read More

  • One Page Summary: Incremental, Iterative Processing with Timely Dataflow

    ·

    Placeholder Icon

    This paper describes Naiad distributed computation system. Naiad uses dataflow model to represent the computations, but it aims to be a general dataflow framework in contrast to other specialized approaches such as TensorFlow. Similarly to other dataflow systems, the computations are represented as graphs, where vertices represent data and operations and edges carry the data…

    Read More

Aleksey CharapkoI am an assistant professor of computer science at the University of New Hampshire. My research interests lie in distributed systems, distributed consensus, fault tolerance, reliability, and scalability.
X (twitter)@AlekseyCharapko
emailaleksey.charapko@unh.edu

Search