BIOScaler ™

The Life Sciences Workflow Challenge

The amount of data produced by a high-performance sequencer has increased by more than 1000x. Many other scientific instruments, such as certain microscopes, have increased output by even more than that. The need to support reliable and fast instrument data ingest as well as analysis, archive, collaboration, publication, and data protection can drive architects to create multiple, separate infrastructure silos. Silos are cumbersome to grow, can slow research due to the delay of data transfers, and are expensive to maintain. Modern Life Sciences workflows need a data infrastructure solution that can handle the entire workflow on a single platform and grow capacity and performance across all functions.

Introducing the Single Solution For End-To-End Life Sciences Workflows

To overcome never-ending data growth, the BIOScaler™ High-Performance Converged Life Sciences Storage Platform delivers a best-in-class solution that allows you to manage end-to-end sequencing, microscopy or modeling, and simulation workﬂows – from high-performance, multi-instrument ingest, to analysis and cost-effective, active archive – within a single platform. BIOScaler delivers an all-in-one turnkey solution that overcomes scale, performance, and cost hurdles and is simple to install, conﬁgure, and manage.

BioScaler Benefits

With conﬁgurations starting under 100TB, BIOScaler scales up in either capacity or performance, either locally or remotely, and presents a single view of data across flash, RAID, and object storage, giving you multiple growth options. For simple and straightforward access, BIOScaler delivers a range of connectivity options, including 1/10/40 Gb/E, Fibre Channel, InﬁniBand, and protocol support such as NFS, SMB, S3, OpenStack/Swift, and HDFS. With performance beyond traditional NAS or SAN, BIOScaler offers per-client speeds from megabytes per second up to 10 gigabytes per second to accommodate a large number of high data-rate instruments (HDRs) as your environment grows.

Starts from a few GB/s of performance in a single base unit and scales to hundreds of GB/s using a building-block approach
Starts small and scales to hundreds of concurrent instrument streams
Scales to more than hundreds of PB, with a capacity that ranges from 80TB to 9PB/rack
Delivers up to 5 or even 10GB/s single-stream performance and scales linearly using Parallel Workload Clients
Simplify management by consolidating workﬂows onto a single platform
Minimize TCO with scale-up and scale-out options locally using the industry’s highest density storage
Collaborate seamlessly with geo-distributed sites using BIOScaler Cloud Nodes
Achieve peace of mind with simpliﬁed and automated tape backup, disaster recovery, synchronous and asynchronous replication, and erasure coding
Mix SSDs, SATA, and SAS in the same single platform, even in the same enclosure

USE CASES

BIOScaler Configurations & Specifications

BIOScaler efficiently grows to hundreds of petabytes of capacity and hundreds of gigabytes per second, delivering high performance, industry-leading density, and scalability for core workﬂows. It also provides simple and cost-effective automatic data tiering to an Active Archive, private/hybrid cloud, and tape—all under a single global namespace that is completely transparent to end users and applications and leverages existing, standard security measures.

For ultimate control over data proximity and availability, BIOScaler provides automated policies that tier data based on your requirements and provides a single ﬁle-system view of all data—regardless of location. BIOScaler delivers high-performance archiving options that seamlessly add cloud nodes for collaborative workﬂows and high availability. For lower-cost archiving, BIOScaler also provides the option to add Active Archive and tape nodes for warm and cold data.

Entry Level

(1) GS7K with 60x4TB drives
(1) WOS7000 with 60x8TB drives
(2) GRIDScaler Bridge Servers
(1) Mellanox Switch
(2) Protocol Nodes

High Performance

(1) GS14KX-EDR with 26x960GB SSDs and 400x4TB drives
(5) WOS8460 with 84x8TB drives
(2) ASG ADA servers
(1) Mellanox Switch
(2) Protocol Nodes

Large-Archive and Data-Protection Repository

(1) GS7K with 60x4TB drives
(4) WOS8460 with 84x8TB drives
(2) ASG ADA servers
(1) Mellanox Switch
(2) Protocol Nodes

GS7KX®

GS14KX®

WOS7000®

WOS8460®

SS8462

Specifications

Performance Node

Protocols	NFS v3, SMB; Linux and Windows Parallel Workload Clients
Performance	Delivers up to 100s of GB/s performance and 100,000s of IOPS using a building block approach; single building block delivers up to 42GB/s Accelerated Performance with Advanced Controller Caching, Software Defined SSDs and all-SSD Options
Streams	Scales to 100s of concurrent media streams using a building block approach; single building block delivers over 40 4K uncompressed streams
Scalability	From 80TB to 100s of PB using a building block approach
Data Protection	RAID 1/5/6; up to 256 Snapshots per Volume – policy driven; Snapshot Rollback; DirectProtect and DirectProtect+; Online and Automatic Storage Rebalancing; High Speed Defragmentation
Connectivity Options	1/10/40/100GigE Ethernet, 16/32GB/s Fibre Channel, EDR/FDR InfiniBand, Intel® Omni-Path
Drives Supported	SSD, Performance SAS and Nearline SAS

Active Archive and Cloud

Cloud Access Gateway Options	S3, SWIFT, NFS/SMB, Parallel Workload Clients
Min/Max Object Size	512B / 5TB
Data Protection and Distribution Options	Replication (Sync, Async) – up to 4 copies, Erasure Coding w/ Replication, Global ObjectAssure®
Full Lifecycle Archive Capability	Support of Simplified Digital Tape Storage with Linear Tape File System
Namespace Growth	Simple Non-Disruptive Scaling, Auto-Balance, Online Upgrades

LTFS Tape

Performance Service Level Agreements (SLAs)	Online, Nearline, Archive
Maximum Capacity	Virtually Unlimited
Full Lifecycle Archive Capability	LTFS Tape Support for Offsite Copy and Deep Archive
Data Protection	Hash Code per File, Tamper Checking, Multi-copy