Ramnatthan Alagappan

Postdoctoral Researcher
VMware Research Group

I am a postdoctoral researcher at VMware Research Group. I was previously a graduate student with Prof. Andrea Arpaci-Dusseau and Prof. Remzi Arpaci-Dusseau at the UW Computer Sciences department. I earned my PhD in the summer of 2019, working on reliability and performance problems in distributed storage. My research interests include file and storage systems, distributed systems, and operating systems. Aishwarya Ganesan and I co-taught CS739 Distributed Systems in Spring 2020. You can find my CV here.

Latest:
[Oct 20] I will serve on the SYSTOR 21 program committee
[Oct 20] Presented our work on distributed storage reliability at the Facebook Faculty Summit!
[Oct 20] Invited to serve on EuroDW 21 program committee
[Aug 20] Our work on Learned Indexes for LSMs (pre-print) has been accepted to OSDI 2020!
[Aug 20] Started as a postdoctoral researcher at VMware Research!
[May 20] Our work on fsync failues has been accepted to Usenix ATC 2020!
[May 20] Our work on storage-system tuning has been accepted to HotStorage 2020!
[Feb 20] Our proposal to examine and improve blockchain reliability will be funded by Facebook Research.
[Feb 20] Our work on consistency-aware durability won the best paper award at FAST 2020!

Awards

Best Paper FAST '20 - CAD
UW CS Graduate Student Research (Best Dissertation Research) Award - Honorable Mention - 2019.
Best Shadow PC Reviewer Eurosys '19
Best Paper FAST '18 - PAR/CTRL
Best Paper FAST '17 - CCFS
Best Paper Nominee FAST '17- Redundancy Does Not Imply Fault Tolerance
Alumni Scholarship @ cs wisc 2013

Publications

Conference Publications


From Wisckey to Bourbon: A Learned Index for Log-structured Merge Trees
Yifan Dai, Yien Xu, Aishwarya Ganesan, Ramnatthan Alagappan, Brian Kroth, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 14th Symposium on Operating System and Design Implementation
OSDI '20
Can Applications Recover from fsync Failures?
Anthony Rebello, Yuvraj Patel, Ramnatthan Alagappan, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
The 2020 USENIX Annual Technical Conference
Available as: PDF, BibTex
ATC '20
Strong and Efficient Consistency with Consistency-aware Durability
Aishwarya Ganesan, Ramnatthan Alagappan, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
18th USENIX Conference on File and Storage Technologies
Available as: PDF, BibTex, Talk Slides
Best Paper Award
FAST '20
Fault-Tolerance, Fast and Slow: Exploiting Failure Asynchrony in Distributed Systems
Ramnatthan Alagappan, Aishwarya Ganesan, Jing Liu, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 13th Symposium on Operating System and Design Implementation
Available as: PDF, BibTex, Talk Slides
OSDI '18
Protocol-Aware Recovery for Consensus-Based Storage
Ramnatthan Alagappan, Aishwarya Ganesan, Eric Lee, Aws Albarghouthi, Vijay Chidambaram, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 16th USENIX Conference on File and Storage Technologies
Available as: PDF, BibTex, Talk Slides
Best Paper Award
Coverage: Morning Paper, zdnet
FAST '18
Atomic In-Place Updates for Non-Volatile Main Memories with KaminoTx
Amir Saman Memaripour, Anirudh Badam, Amar Phanishayee, Yanqi Zhou, Ramnatthan Alagappan, Karin Strauss, Steven Swanson
Proceedings of the Twelfth European Conference on Computer Systems
Available as: PDF, BibTex
EuroSys '17
Redundancy Does Not Imply Fault Tolerance: Analysis of Distributed Storage Reactions to Single Errors and Corruptions
Aishwarya Ganesan, Ramnatthan Alagappan, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 15th USENIX Conference on File and Storage Technologies
Available as: PDF, BibTex, Talk Slides, Project, Code
Best Paper Award Nominee
Coverage: StorageMojo, Morning Paper, DHSR's blog
FAST '17
Application Crash Consistency and Performance with C2FS
Thanumalayan Sankaranarayana Pillai, Ramnatthan Alagappan, Lanyue Lu, Vijay Chidambaram, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 15th USENIX Conference on File and Storage Technologies
Available as: PDF, BibTex, Talk Slides
Best Paper Award
Coverage: Morning Paper
FAST '17
Correlated Crash Vulnerabilities
Ramnatthan Alagappan, Aishwarya Ganesan, Yuvraj Patel, Thanumalayan Sankaranarayana Pillai, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 12th Symposium on Operating System and Design Implementation
Available as: PDF, BibTex, Project, Talk Slides, Code
OSDI '16
All File Systems Are Not Created Equal: On the Complexity of Crafting Crash-Consistent Applications
Thanumalayan Sankaranarayana Pillai, Vijay Chidambaram, Ramnatthan Alagappan, Samer Al Kiswany, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Proceedings of the 11th Symposium on Operating System and Design Implementation
Available as: PDF, BibTex, Project, Code
Coverage: Morning Paper
OSDI '14

Journal/Workshop/Invited Publications


Too Many Knobs to Tune? Towards Faster Database Tuning by Pre-selecting Important Knobs
Konstantinos Kannelis, Ramnatthan Alagappan, Shivaram Venkataraman
15th Workshop on Hot Topics in Storage and File Systems
Available as: PDF, BibTex,
HotStorage '20
Protocol-Aware Recovery for Consensus-based Storage
Ramnatthan Alagappan, Aishwarya Ganesan, Eric Lee, Aws Albarghouthi, Vijay Chidambaram, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Usenix ATC 2019
Best of the Rest
Usenix ATC '19
Protocol-Aware Recovery for Consensus-Based Distributed Storage
Ramnatthan Alagappan, Aishwarya Ganesan, Eric Lee, Aws Albarghouthi, Vijay Chidambaram, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Transactions on Storage - Vol. 14, Issue 3, October 2018
Fast tracked
Available as: PDF, BibTex,
TOS '18
Redundancy Does Not Imply Fault Tolerance
Aishwarya Ganesan, Ramnatthan Alagappan, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Transactions on Storage - Vol. 13, Issue 3, September 2017
Fast tracked
Available as: PDF, BibTex,
TOS '17
Application Crash Consistency and Performance with CCFS
Thanumalayan Sankaranarayana Pillai, Ramnatthan Alagappan, Lanyue Lu, Vijay Chidambaram, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Usenix ATC 2017
Best of the Rest
Available as: PDF, BibTex,
Usenix ATC '17
Application Crash Consistency and Performance with CCFS
Thanumalayan Sankaranarayana Pillai, Ramnatthan Alagappan, Lanyue Lu, Vijay Chidambaram, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Transactions on Storage - Vol. 13, Issue 3, September 2017
Fast tracked
Available as: PDF, BibTex,
TOS '17
Redundancy Does Not Imply Fault Tolerance
Aishwarya Ganesan, Ramnatthan Alagappan, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
USENIX ;login: Volume 42, Number 2, 2017
Available as: PDF, BibTex,
USENIX ;login: Summer '17
Hybrid NVM Enabled Datacenter Design and Optimization
Yanqi Zhou, Ramnatthan Alagappan, Amir Samam Memaripour, Anirudh Badam, David Wentzlaff
MSR-TR-2017-8 Feb 2017
Available as: PDF, BibTex,
MSR TR
Beyond Storage APIs: Provable Semantics for Storage Stacks
Ramnatthan Alagappan, Vijay Chidambaram, Thanumalayan Sankaranarayana Pillai, Aws Albarghouthi, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
15th Workshop on Hot Topics in Operating Systems
Available as: PDF, BibTex,
HotOS '15
Crash Consistency: Rethinking the Fundamental Abstractions of the File System
Thanumalayan Sankaranarayana Pillai, Vijay Chidambaram, Ramnatthan Alagappan, Samer Al Kiswany, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
ACM Queue July 2015
Available as: PDF, BibTex,
ACM Queue
Crash Consistency:
Thanumalayan Sankaranarayana Pillai, Vijay Chidambaram, Ramnatthan Alagappan, Samer Al Kiswany, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
Communications of the ACM - Vol. 58, No. 10, October 2015
Available as: PDF, BibTex,
CACM

WIPS/Posters


Atomic In-Place Updates for Non-Volatile Main Memories with KaminoTx
Amir Saman Memaripour, Anirudh Badam, Amar Phanishayee, Yanqi Zhou, Ramnatthan Alagappan, Karin Strauss, Steven Swanson

NVMW '18
Simple Crash Consistency With Streams
Thanumalayan Sankaranarayana Pillai, Ramnatthan Alagappan, Andrea Arpaci-Dusseau, Remzi Arpaci-Dusseau

FAST '16

Teaching

I enjoy teaching!

Instructor for CS 739 - Spring 2020 (co-taught by Aishwarya Ganesan).
Evaluation: 6.42/7.00

Guest lectures for CS 739 (Paxos, storage reliability) and CS 736 (AFS).
TA for CS 537 (guest lectures on RAID, FS review)- Spring 2018.
TA for CS 302 - Fall 2013.

Projects

Distributed Durability, Consistency, and Performance

Consistency-aware durability - a new durability model for distributed storage (FAST)

Distributed Storage Reliability

Making Consensus Protocols Situation-Aware (OSDI)
Correlated Crash Vulnerabilities in Distributed Systems (OSDI)
Redundancy Does Not Imply Fault Tolerance (FAST, ;login:, TOS)
Protocol-Aware Recovery for Distributed Storage Systems (FAST, TOS)

Crash Vulnerabilities

Application Crash Vulnerabilities (OSDI, CACM, Queue)
Correlated Crash Vulnerabilities in Distributed Systems (OSDI)
CCFS (FAST, TOS)

Non-Volatile Memory

Atomic In-Place Updates for NVM (Eurosys)
Hybrid NVM Enabled Datacenter Design and Optimization (MSR Tech. Report)

Proving Storage Guarantees

Beyond Storage APIs: Provable Semantics for Storage Stacks (HotOS)

Code

Here are some tools and frameworks we have built to improve the reliability of storage systems. Please feel free to email me if you would like to apply any of these tools to your system.

Distributed Storage Reliability


PACE: To check for correlated crash vulnerabilities in distributed systems
Code on GitHub

CORDS: To test corruption tolerance in distributed systems
Code on GitHub


Local Storage Reliability


ALICE: To check for crash vulnerabilities in local storage systems
Code on GitHub

Service

Reviewer ACM Transactions on Computer Systems '20
Program Committee HotStorage '20
Artifact Evaluation Committee Reviewer SOSP '19
Shadow Program Committee Reviewer Eurosys '19
Reviewer ACM Transactions on Storage '18
External Reviewer FAST '18
Contributor to PC reviews Eurosys '17
External Reviewer OSDI '16
External Reviewer FAST '16


Invited / Conference Talks

Protocol-Aware Recovery for Consensus-Based Storage @ ATC '19
RAID lecture @ Shivaram's CS 537 (slides)
AFS lecture @ Mike's CS 736
Storage Systems at the Edge @ NSF-VMWare ECDI Summit
Paxos lecture @ Remzi's CS 739 (slides)
errfs/CORDS lecture @ Remzi's CS 739
Fault-Tolerance, Fast and Slow: Exploiting Failure Asynchrony in Distributed Systems @ OSDI '18 (slides)
Protocol-Aware Recovery for Consensus-based Storage @ SNIA SDC '18 (slides, video)
Resiliency to Storage Faults in Distributed Systems @ Google Madison (May '18)
Protocol-Aware Recovery for Consensus-Based Storage @ FAST '18 (slides)
Paxos lecture @ Remzi's CS 739 (slides)
Rethinking Consensus with Local Storage in Mind @ SCI-labs 2017
Correlated Crash Vulnerabilities @ OSDI '16 (slides)
Correlated Crash Vulnerabilities @ Microsoft Gray Systems Lab

Invited / Fast-Tracked Articles

Protocol-Aware Recovery for Consensus-based Distributed Storage (Transactions on Storage '18)
Redundancy Does Not Imply Fault Tolerance (Transactions on Storage '17)
Application Crash Consistency and Performance with CCFS (Usenix ATC '17 Best of the Rest)
Application Crash Consistency and Performance with CCFS (Transactions on Storage '17)
Redundancy Does Not Imply Fault Tolerance (Usenix ;login:)
Redundancy Does Not Imply Fault Tolerance (Poster at Netapp)
Crash Consistency (Communications of the ACM)
Crash Consistency: Rethinking the Fundamental Abstractions of File Systems (ACM Queue)

Travel Grants

OSDI ’14, FAST ’17, FAST ’18