October 27, 2014

Characterizing Load Imbalance in Real-World Networked Caches

HotNets 2014: Thirteenth ACM Workshop on Hot Topics in Networks

Modern Web services rely extensively upon a tier of in-memory caches to reduce request latencies and alleviate load on backend servers. Within a given cache, items are typically partitioned across cache servers via consistent hashing, with the goal of balancing the number of items maintained by each cache server. Effects of consistent hashing vary by associated hashing function and partitioning ratio. Most real-world workloads are also skewed, with some items significantly more popular than others. Inefficiency in addressing both issues can create an imbalance in cache-server loads. We analyze the degree of observed load imbalance, focusing on read-only traffic against Facebook’s graph cache tier in Tao. We investigate the principal causes of load imbalance, including data co-location, non-ideal hashing scenarios, and hot-spot temporal effects. We also employ trace-drive analytics to study the benefits and limitations of current load-balancing methods, suggesting areas for future research.

Qi Huang, Helga Gudmundsdottir, Ymir Vigfusson, Daniel A. Freedman, Ken Birman, Robbert van Renesse
October 24, 2014

The HipHop Virtual Machine

ACM International Conference on Object Oriented Programming Systems, Languages, and Applications

The HipHop Virtual Machine (HHVM) is a JIT compiler and runtime for PHP. While PHP values are dynamically typed, real programs often have latent types that are useful for optimization once discovered….

Keith Adams, Jason Evans, Bertrand Maher, Guilherme Ottoni, Drew Paroski, Brett Simmers, Edwin Smith, Owen Yamauchi
October 7, 2014

f4: Facebook’s Warm BLOB Storage System

Operating Systems Design and Implementation

Facebook’s corpus of photos, videos, and other Binary Large OBjects (BLOBs) that need to be reliably stored and quickly accessible is massive and continues to grow.

Subramanian Muralidhar, Wyatt Lloyd, Sabyasachi Roy, Cory Hill, Ernest Lin, Weiwen Liu, Satadru Pan, Shiva Shankar, Viswanath Sivakumar, Linpeng Tang, Sanjeev Kumar
October 6, 2014

The Mystery Machine: End-to-end Performance Analysis of Large-scale Internet Services

Operating Systems Design and Implementation

Current debugging and optimization methods scale poorly to deal with the complexity of modern Internet services, in which a single request triggers parallel execution of numerous heterogeneous softwar…

Mike Chow, David Meisner, Jason Flinn, Daniel Peek, Thomas Wenisch
September 18, 2014

Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation

British Machine Vision Conference

Poselets have been used in a variety of computer vision tasks, such as detection, segmentation, action classification, pose estimation and action recognition, often achieving state-of-the-art performa…

David Bo Chen, Pietro Perona, Lubomir Bourdev
September 18, 2014

Mining Energy Traces to Aid in Software Development: An Empirical Case Study

ACM / IEEE International Symposium on Empirical Software Engineering and Measurement

With the advent of increased computing on mobile devices such as phones and tablets, it has become crucial to pay attention to the energy consumption of mobile applications.

Ashish Gupta, Thomas Zimmermann, Christian Bird, Nachiappan Nagappan, Thirumalesh Bhat, Syed Emran
September 4, 2014

Question Answering with Subgraph Embeddings

Empirical Methods in Natural Language Processing

This paper presents a system which learns to answer questions on a broad range of topics from a knowledge base using few handcrafted features. Our model learns low-dimensional embeddings of words and knowledge base constituents; these representations are used to score natural language questions against candidate answers.

Antoine Bordes, Jason Weston, Sumit Chopra
September 4, 2014

#TagSpace: Semantic Embeddings from Hashtags

Empirical Methods in Natural Language Processing

We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags.

Jason Weston, Sumit Chopra, Keith Adams
September 1, 2014

Optimal Crowd-Powered Rating and Filtering Algorithms

VLDB 2014

We focus on crowd-powered filtering, i.e., filtering a large set of items using humans. Filtering is one of the most commonly used building blocks in crowdsourcing applications and systems. While solu…

Aditya Parameswaran, Stephen Boyd, Hector Garcia-Molina, Ashish Gupta, Neoklis Polyzotis, Jennifer Widom
August 24, 2014

Streamed Approximate Counting of Distinct Elements

ACM Conference on Knowledge Discovery and Data Mining (KDD)

Counting the number of distinct elements in a large dataset is a common task in web applications and databases. This problem is difficult in limited memory settings where storing a large hash table ta…

Daniel Ting
August 24, 2014

Practical Lessons from Predicting Clicks on Ads at Facebook

International Workshop on Data Mining for Online Advertising (ADKDD)

Online advertising allows advertisers to only bid and pay for measurable user responses, such as clicks on ads. As a consequence, click prediction systems are central to most online advertising system…

He Xinran, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yanxin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, Joaquin Quinonero Candela
August 18, 2014

A Hitchhiker’s Guide to Fast and Efficient Data Reconstruction in Erasure-coded Data Centers

ACM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM)

Erasure codes such as Reed-Solomon (RS) codes are being extensively deployed in data centers since they offer significantly higher reliability than data replication methods at much lower storage overheads. These codes however mandate much higher resources with respect to network bandwidth and disk IO during reconstruction of data that is missing or otherwise unavailable.

K.V. Rashmi, Nihar B. Shah, Dikang Gu, Hairong Kuang, Dhruba Borthakur, Kannan Ramchandran
August 18, 2014

Fastpass: A Centralized “Zero-Queue” Datacenter Network

ACM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM)

Current datacenter networks inherit the principles that went into the design of the Internet, where packet transmission and path selection decisions are distributed among the endpoints and routers. In…

Jonathan Perry, Amy Ousterhout, Hari Balakrishnan, Devavrat Shah, Hans Fugal
August 7, 2014

Perceiving, learning, and exploiting object affordances for autonomous pile manipulation

Autonomous Robots

Autonomous manipulation in unstructured environments will enable a large variety of exciting and important applications. Despite its promise, autonomous manipulation remains largely unsolved. Even the…

Dubi Katz, Arun Venkatraman, Moslem Kazemi, J. Andrew Bagnell, Anthony Stentz
June 24, 2014

Collaborative Hashing

Conference on Computer Vision and Pattern Recognition (CVPR)

Hashing technique has become a promising approach for fast similarity search. Most of existing hashing research pursue the binary codes for the same type of entities by preserving their similarities….

Xianglong Liu, Junfeng He, Cheng Deng, Bo Lang
June 24, 2014

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

Conference on Computer Vision and Pattern Recognition (CVPR)

In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing exp…

Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf
June 24, 2014

Fast Database Restarts at Facebook

ACM Special Interest Group on Management of Data (SIGMOD)

Facebook engineers query multiple databases to monitor and analyze Facebook products and services. The fastest of these databases is Scuba, which achieves subsecond query response time by storing all…

Aakash Goel, Bhuwan Chopra, Ciprian Gerea, Dhrúv Mátáni, Josh Metzler, Fahim Ul Haq, Janet Wiener
June 24, 2014

PANDA: Pose Aligned Networks for Deep Attribute Modeling

Conference on Computer Vision and Pattern Recognition (CVPR)

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulat…

Ning Zhang, Manohar Paluri, Marc'Aurelio Ranzato, Trevor Darrell, Lubomir Bourdev
June 23, 2014

Adaptive HTER Estimation for Document-Specific MT Post-Editing

Annual Conference of Association of Computational Linguistics (ACL)

We present an adaptive translation quality estimation (QE) method to predict the human targeted translation error rate (HTER) for a document-specific machine translation model. We first introduce fea…

Fei Huang, Jianming Xu, Abraham Ittycheriah, Salim Roukos
June 20, 2014

vCacheShare: Automated Server Flash Cache Space Management in a Virtualization Environment

USENIX Annual Technical Conference (ATC)

Server Flash Cache (SFC) is being increasingly adopted in virtualization environments for IO acceleration. Deciding the optimal SFC allocation among VMs or VM disks is a major pain-point, dominantly handled manually by administrators.

Fei Meng, Li Zhou, Xiaosong Ma, Sandeep Uttamchandani, Deng Liu