Since the conference was founded, in 1974, by the leading national laboratories, MSST (the International Conference on Massive Storage Systems and Technology) has been a venue for massive-scale storage system designers and implementers, storage architects, researchers, and vendors to share best practices and discuss building and securing the world’s largest storage systems for high-performance computing, web-scale systems, and enterprises.

MSST 2024  will be returning on its 50th anniversary to its new home at Santa Clara University, where it will be hosted by the School of Engineering, and held from June 3rd through June 7th, 2024

Registration is available here (the early-bird registration rates end after May 14th, 2024).

Directions to the venue and hotel information is available here.

The Research CFP (now closed for paper submissions) is archived here, and the poster CFP here.

MSST 2024 is possible thanks to sponsorship and support from SCU’s School of Engineering, and Hammerspace.

June 3rd

Tutorials

8:30 – 9:30

Breakfast & Badge Pickup

A Continental breakfast will be provided from 8:30 to 9:30am.

Badge pick-up will continue from 8:30 to 4:30pm.

9:15 – 9:30

Welcome to Analytics for the Storage Practitioner

Gary Grider (LANL)

9:30 – noon

Columnar Analytics

 

Overview (what, how, ecosystem, implications on storage) Fernanda Foertter (Voltron Data)
Object Computational Storage analytics offload Qing Zheng (LANL)
Erasured Object Computational Storage analytics offload Donpaul Stephens (AirMettle)
Hardware Accelerated Computational Storage analytics offload Krishna Maheshwari (Neuroblade)

noon – 1:00

Lunch

1:00 – 3:00

Row Analytics

 

Overview (what, how, ecosystem, implications on storage) Rob Johnson (Broadcom)
Hardware Accelerated Row analytics offload Edward Bortnikov (Pliops)
Hardware Accelerated Row analytics offload Phil Chan (Eideticom)

3:30 – 4:30

GraphDB / Analytics

 

Overview (what/how/market/ecosystem/storage implications) Amine Mhedhbi (Polytechnique Montréal)

June 4th

Invited Track

8:00 – 9:00

Breakfast & Badge Pickup

A Continental breakfast will be provided from 8:00 to 9:00am.

Badge pick-up will continue from 8:30 to 5:00pm.

8:30 – 8:45

Welcome & Opening Remarks

8:45 – 10:15

Computational Storage 1

 

Open Object Computational Storage Pushdown Jongryool.Kim (Skhynix)
Open PNFS Pushdown Dominic Manno (LANL)
Hardware Accelerated Computational Storage analytics offload Krishna Maheshwari (Neuroblade)

10:30 – 11:30

Computational Storage 2/Media Trends 1

 

Erasured Object Computational Storage analytics Donpaul Stephens (AirMettle)
TBD Steffen Hellmold (Cerabyte)

11:30 – 12:30

Keynote: Michael Cornwell (Pure) – “Storage Landscapes”

12:30 – 1:30

Lunch

Badge pick-up will continue from 8:30 to 5:00pm.

1:30 – 3:00

Media Trends 2

 

Tape (Spectra) Nathan Thompson (Spectra)
Disk (WDC/Seagate) Paul Peck (Western Digital)
Flash (Samsung) Young Paik (Samsung)

3:15 – 4:45

Data Lakes

 

Apache Data Lake Ecosystem Fernanda Foertter (Voltron Data)
Iceberg (Apple/LinkedIn/Stripe) Alex Merced (Dremio)
Tackling I/O Challenges in Modern Data Lakes Hope Wang (Alluxio)

4:45 – 5:00

Invited Track Day 1 Wrap-Up

Adam Manzanares (Samsung)

June 5th

Invited Track

8:00 – 9:00

Breakfast & Badge Pickup

A Continental breakfast will be provided from 8:00 to 9:00am.

Badge pick-up will continue from 8:00 to 5:00pm.

8:30 – 8:45

Welcome & Introduction for Day 2

8:45 – 9:45

A.I. Storage Case Studies 1

 

AI storage case studies Hari Kennan (Pure)
AI storage case studies David Flynn (Hammerspace)

10:00 – 11:30

.

A.I. Storage Case Studies 2

 

All Flash Storage Systems Devasena Inupakutika (Samsung)
AI storage case studies Caden Bradbury
AI storage case studies Andy Pernsteiner (VAST)

11:30 – 12:30

Keynote: Garth Gibson – “Storage for A.I.”

12:30 – 1:30

Lunch

Badge pick-up will continue from 8:30 to 5:00pm.

1:30 – 3:00

Heterogenous Workloads

 

Disaggregated Storage based on NFS/RDMA for AI workload Davide Villa (Xinnor)
PNFS/NFS4.2 Diverse Workloads Trond Myklebust (Hammerspace)
Scalable Composable NVME Storage Matthew Williams (Cerio)

3:15 – 4:45

Distributed Storage Management

 

Open Community Distributed Storage Managment Dominic Manno (LANL)
Beyond BeeOND: A Proposal for Composable Storage Joe McCormick (ThinkparQ)

4:45 – 5:00

Invited Track Day 2 Wrap-Up

Rohan Puri (Samsung)

June 6th

Research Track

8:00 – 9:00am

Breakfast & Badge Pickup

A Continental breakfast will be provided from 8:00 to 9:00am.

Badge pick-up will continue from 8:00 to 5:00pm.

8:45 – 9:30am

Keynote: Hoshik Kim (SK Hynix)

VP & Fellow of Memory Systems Research

9:45 – 10:45am

Session 1: Archival Data

Revisiting HDD Rules of Thumb: 1/3 Is Not (Quite) the Average Seek Distance

BURST: A Chunk-Based Data Deduplication System with Burst-Encoded Fingerprint Matching

A Generic and Efficient Framework for Estimating Lossy Compressibility of Scientific Data

11:00 – noon

Session 2: Long Live the Data

Repair I/O Optimization for Clay Codes via Gray-Code Based Sub-Chunk Reorganization in Distributed Storage Systems

Cauchy-Merge: An Efficient Cauchy Matrix based Stripe Merging Method for Reed-Solomon Codes

Minimizing Performance Degradation of RAID Recovery Through Pre-Failure Prediction

noon – 1:30pm

Lunch

Badge pick-up will continue from 8:30 to 5:00pm.

1:30 – 2: 30pm

Session 3: Log Structured Session

Prophet: Optimizing LSM-Based Key-Value Store on ZNS SSDs with File Lifetime Prediction and Compaction Compensation

SAS-Cache: A Semantic-Aware Secondary Cache for LSM-based Key-Value Stores

A GPU-accelerated Compaction Strategy for LSM-based Key-Value Store System

2:45 – 3: 45pm

Session 4: Getting Real

Dissecting I/O Burstiness in Machine Learning Cloud Platform: A Case Study on Alibaba’s MLaaS

Answering the Call to ARMs with PACER: Power-Efficiency in Storage Servers

Mitigating Write-ahead Log Contention on Shared Storage Devices

4:00 – 5:00pm

Session 5: Cloudy With A Chance of Serverless

FastStore: Optimization of Distributed Block Storage Services for Cloud Computing

FuncStore: Resource Efficient Ephemeral Storage for Serverless Data Sharing

Balancing Costs and Durability for Serverless Data

5:00 – 7:00pm

 

Poster Session

June 7th

Research Track

8:00 – 9:00 both days

Breakfast & Badge Pickup

A Continental breakfast will be provided from 8:00 to 9:00am.

Badge pick-up will continue from 8:00 to 5:00pm.

9:00 – 10:00am

Session 6: Heterogeneity

Learning to Coordinate Read-Write Cache Policies in SSD

TieredMMS: A Portable Tiered Memory Management System

Minding the Semantic Gap for Effective Storage-Based Ransomware Defense

10:15-11:15am

Session 7: Flashy Session

Adaptive Selection of Parity Chunk Update Methods in RAID-enabled SSDs

AUGEFS: A Scalable Userspace Log-Structured File System for Modern SSDs

Fully Harnessing the Performance Potential of DRAM-less Mobile Flash Storage

11:30-12:30pm

Session 8: All Alone with the Memory

LodgeTree: A Last-Level Distributed and Surrogate Buffer Tree for Non-Volatile Memories

Dolphin: A Resource-efficient Hybrid Index on Disaggregated Memory

H2KV: A Hotspot Awareness based Hybrid Fault-tolerant In-memory Key-Value Store

12:30 – 1:30pm

Lunch

Badge pick-up will continue from 8:30 to 5:00pm.

1:30-2:30pm

Session 9: Even More Flashy

PhasedRR: Read Reclaim Scheduling without Page-level Access Counting

Ensuring Compaction and Zone Cleaning Efficiency through Same-Zone Compaction in ZNS Key-Value Store

PhatKV: Towards an Efficient Metadata Engine for KV-based File Systems on Modern SSD

2:45-3:45pm

 

Panel: Emerging Memory Technologies