About

I am an Associate Professor at ESPOL University in Guayaquil, Ecuador. In May 2014, I obtained my PhD in Computer Science at the University of Illinois at Urbana-Champaign. Previously, I received my Master of Science degree from UIUC in 2003, funded through a Fulbright Fellowship.

My main research interests lie in the area of distributed systems, in particular clustered storage systems for Big Data and Cloud Computing applications. At UIUC, I was a member of the Systems Research Group, under the guidance of Prof. Roy H. Campbell. During my PhD studies, I collaborated with the Hadoop Core Team at Yahoo, Inc. (UIUC Research Park) and also worked on several projects with Prof. Yi Lu.

In 2016 I received a Google Faculty Research Award to work on storage workload modeling; it makes me proud to note that this was the first time a university in Ecuador received this prestigious award. In addition to this project, I am working on several projects related to using in-memory distributed key-value stores as caches in cloud computing environments. I am mostly interested in studying and improving their performance under varying workloads.

I also like to code; in particular, I like to build distributed systems. While at Yahoo, I contributed to the Apache Hadoop codebase. In my free time, I sometimes answer questions on stackoverflow.

You can follow me on twitter.

(For full list of publications, see my Google Scholar page)

Dynamic memory partitioning for cloud caches with heterogeneous backends

Cristina L. Abad, Andrés G. Abad, Luis E. Lucio

ACM/SPEC International Conference on Performance Engineering (ICPE), 2017

Benchmarking key-value stores via trace replay

Edwin F. Boza, César San-Lucas, Cristina L. Abad, José A. Viteri

IEEE International Conference on Cloud Engineering (IC2E), 2017

Pandas: Robust Locality-Aware Scheduling With Stochastic Delay Optimality

Qiaomin Xie, Mayank Pundir, Yi Lu, Cristina L. Abad, Roy H. Campbell

IEEE/ACM Transactions on Networking, 2016.

A Model-Based Namespace Metadata Benchmark for HDFS

Cristina L. Abad, Yi Lu, Roy H. Campbell, Nathan Roberts

11th International Conference on Autonomic Computing (ICAC), 2014.

CODE: MimesisBench available on github.

Big Data storage workload characterization, modeling and synthetic generation

Cristina L. Abad

PhD Thesis, University of Illinois at Urbana-Champaign, 2014.

Generating request streams on Big Data using clustered renewal processes

Cristina L. Abad, Mindi Yuan, Chris X. Cai, Yi Lu, Nathan Roberts, Roy H. Campbell

Performance Evaluation, Special Issue: IFIP Performance 2013, http://dx.doi.org/10.1016/j.peva.2013.08.006.

Natjam: Design and Evaluation of Eviction Policies For Supporting Priorities and Deadlines in Mapreduce Clusters

Brian Cho, Muntasir Rahman, Tej Chajed, Indranil Gupta, Cristina L. Abad, Nathan Roberts, Philbert Lin

ACM Symposium on Cloud Computing (SOCC), 2013.

A Storage-Centric Analysis of MapReduce Workloads: File Popularity, Temporal Locality and Arrival Patterns

Cristina L. Abad, Nathan Roberts, Yi Lu, Roy H. Campbell

IEEE International Symposium on Workload Characterization (IISWC), 2012.

Metadata Traces and Workload Models for Evaluating Big Storage Systems

Cristina L. Abad, Huong Luu, Nathan Roberts, Kihwal Lee, Yi Lu, Roy H. Campbell

IEEE/ACM International Conference on Utility and Cloud Computing (UCC), 2012.

Technical report with more details on surveyed papers is available in the UIUC repository.

CODE: Namespace Generation Module available on github.

DARE: Adaptive Data Replication for Efficient Cluster Scheduling

Cristina L. Abad, Yi Lu, Roy H. Campbell

IEEE International Conference on Cluster Computing (CLUSTER), 2011.

Preventing ARP cache poisoning attacks: A proof of concept using OpenWrt

Andre Ortega, Xavier Marcos, Luis Chiang, Cristina L. Abad

IEEE Latin American Network Operations and Management Symposium (LANOMS), 2009.

Learning through creating learning objects: Experiences with a class project in a distributed systems course (ACM Authorizer download link)

Cristina L. Abad

ACM SIGCSE Bulletin - ITiCSE '08, Volume 40 Issue 3, 2008.

An analysis of the schemes for detecting and preventing ARP cache poisoning attacks

Cristina L. Abad, Rafael I. Bonilla

IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), 2007.

Adding confidentiality to application-level multicast by leveraging the multicast overlay

Cristina L. Abad, Indranil Gupta, William Yurcik

IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), 2005.

Log correlation for intrusion detection: A proof of concept

Cristina L. Abad, Jed Taylor, Cigdem Sengul, William Yurcik, Yuanyuan Zhou, Ken Rowe

IEEE Computer Security Applications Conference (ACSAC), 2003

Mimesis Namespace Generator

Developed by: Cristina Abad and Shadi Noghabi, Designed by: Cristina Abad

Can create large and realistic hierarchical namespaces. This tool preserves the following distributions (as given by the configuration file used): directories at each depth, subdirectories per directory, files at each depth, files per directory, file sizes, file creation stamps. Details on IEEE/ACM UCC 2012 publication. Repository on Github. 

MimesisBench

Developed and Designed by: Cristina Abad

Metadata-intensive benchmark for the HDFS name node. Access model described on my IFIP Performance 2013 paper. Details of the benchmark on my ICAC 2014 publication. Repository on Github.

KV-Replay

Developed by: Edwin Boza, Designed by: Cristina Abad and Edwin Boza

Tool based on YCSB that can replay real traces under varying models. Details in the IC2E paper (to appear). Repository on Github.

I have an Erdos number of 3: Cristina L. Abad → William Yurcik → Ruth Silverman → Paul Erdős 
E.W. Dijkstra is my academic great-great-grandfather: Dijkstra → A. Habermann → Hugh Lauer → Roy H. Campbell → Cristina L. Abad

Email: cabad [at] fiec [dot] espol [dot] edu [dot] ec