High Performance Storage System

HPSS Logo
Incremental Scalability
Based on storage needs and deployment schedules, HPSS scales incrementally by adding computer, network and storage resources. A single HPSS namespace can scale from petabytes of data to exabytes of data, from millions of files to billions of files, and from a few file-creates per second to thousands of file-creates per second.
About HPSS   :    HPSS Version 8.1.0

The following is an overview of three new features that can be found in HPSS 8.1.0.

New to HPSS 8.1.0

Ordered Migration by Directory

HPSS now supports the ability to co-locate data on tape by directory. The objective is to improve tape recall efficiency. This new feature is especially pertinent when considering the use of the Full Aggregate Recall (FAR) feature released in HPSS 7.5.3.

If users organize files by directory and usually recall files from a given directory in bulk, by using Ordered Migration by Directory and Full Aggregate Recall users may see a 7x to 10x improvement in recall performance. Thus, HPSS 8.1 may be able to meet site tape-recall requirements using many fewer tape drives when compared to HPSS 7.5.3.

The migration policy will continue to honor the migration policy settings for when a file is eligible for migration, how often migration will run and the number of migration streams to use.

Prevent tape-recall events from HPSS FUSE

The HPSS FUSE mount point may now be configured to deny users from triggering HPSS tape recall events. If the nostagetape HPSS FUSE mount point option is specified, no data is staged from tape-only files. If the stagetape HPSS FUSE mount point option is specified or not included, users will trigger HPSS tape recall events for files that are not on the HPSS disk cache.

Most UNIX commands that come from FUSE are blocked, so HPSS receives one tape-recall at a time. When HPSS receives one tape-recall at a time, HPSS does not have an opportunity to organize and optimize the tape recall events. On the other hand, if a site monitors log messages, triggers can be put in place to process the error messages that are logged when the nostagetpae HPSS FUSE mount point option is specified, and a user tries to recall a file on tape. When files are recalled in bulk, HPSS will organize and optimize the tape-recall events.

HPSS accounting information by UID and GID

HPSS will now track accounting information by UID and GID rather than by Account ID alone.

< Home

Come meet with us!
HPSS @ MSST 2020
The 35th International Conference on Massive Storage Systems and Technology will be in Santa Clara, California in May of 2020 - Learn More. Please contact us if you would like to meet with the IBM business and technical leaders of HPSS at Santa Clara University.

HPSS @ ISC20
The 2020 international conference for high performance computing, networking, and storage will be in Frankfurt, Germany from June 21st through 25th, 2020 - Learn More. Come visit the HPSS folks at the IBM booth and contact us if you would like to meet with the IBM business and technical leaders of HPSS in Frankfurt.

2020 HUF
The 2020 HPSS User Forum (HUF) is being hosted by Karlsruhe Institute of Technology (KIT) in Karlsruhe, Germany from September 7th through September 11th, 2020. This is a great place to meet HPSS users, collaboration developers and testers (from IBM and DOE Labs), support folks, and leadership. More details coming soon.

HPSS @ SC20
The 2020 international conference for high performance computing, networking, storage and analysis will be in Atlanta, Georgia from November 16th through 19th, 2020 - Learn More. Come visit the HPSS folks at the IBM booth and contact us if you would like to meet with the IBM business and technical leaders of HPSS in Atlanta.

What's New?
HPSS 8.2 Release - HPSS 8.2 was released on December 6th, 2019 and introduces a few new features.

Lots Of Data - In November 2019 IBM/HPSS delivered a system to Shared Services Canada (SSC) for Environment Canada and demonstrated a sustained tape ingest rate of 11,574 MB/sec (1 PB/day peak tape ingest) while simultaneously demonstrating a sustained tape recall rate of 8,832 MB/sec (791 TB/day peak tape recall). HPSS pushed four 13-frame IBM TS4500 tape libraries (scheduled to house over 500 PB of tape media) to 2,168 mounts/hour.

HPSS 8.1 Release - HPSS 8.1 was released on October 1st, 2019 and introduces a few new features.

July 2019 - Argonne Team Breaks Record for Globus Data Movement from the Summit supercomputer at Oak Ridge National Laboratory to HPSS tape.

Capacity Leader - ECMWF (European Center for Medium-Range Weather Forecasts) has a single HPSS namespace with 451 PB spanning 344 million files.

File-Count Leader - LLNL (Lawrence Livermore National Laboratory) has a single HPSS namespace with 55 PB spanning 1.415 billion files.

Explosive data growth - HPSS Collaboration leadership from Lawrence Berkeley National Laboratory's National Energy Research Scientific Computing Center (NERSC) helped author the "NERSC Storage 2020" report, and NERSC trusts HPSS to meet their immediate and long term data storage challenges.

Older News - Want to read more?
Home    |    About HPSS    |    Services    |    Contact us
Copyright 2018, HPSS Collaboration. All Rights Reserved.