WARNING: This is the _old_ Lustre wiki, and it is in the process of being retired. The information found here is all likely to be out of date. Please search the new wiki for more up to date information.

Lustre Design Documents: Difference between revisions

From Obsolete Lustre Wiki
Jump to navigationJump to search
No edit summary
Line 1: Line 1:
About once a year, the Lustre Engineering team gathers to discuss new features under development and testing efforts.  In November 2009, the senior Lustre engineers met in conjunction with the SC'09 event in Portland, Oregon, to discuss designs for upcoming features and implementation status of current development projects.
the designs reflect a certain point in time to the extent that a design finds itself in a feature in a release there will be other pages and assets on the wiki. Some of the information may not be current ... more historical.
Latest presentations are current.
The rest needs to be in an archive place. Some content may be out of date.  


* [[Media:SC09-kDMU-Code.pdf|Kernel DMU Project Review]] - Alex Zhuravlev
About once a year, the Lustre Engineering team gathers to discuss new features under development and testing efforts. 
* [[Media:SC09-SOM-Code.pdf|Size On MDS Project Review]] - Vitaly Fertman
 
* [[Media:SC09-FID-on-OST.pdf|FIDs on OST Design Presentation]] - Mike Pershin
The Lustre team has prepared several design documents as part of the HPCS program. The DARPA High Productivity Computing Systems (HPCS) project is a program created to ensure that US Government agencies continue to have access to the advanced high-performance computing technologies needed to fulfill their missions. The program objectives include achieving extremely high IO performance and file system scale and reliability. Cray Inc. has partnered with Sun to use Lustre to achieve these goals.
* [[Media:SC09-HSM-Code.pdf|HSM Project Review]] - Nathan Rutman
 
* [[Media:SC09-SMP-Scaling.pdf|Server SMP Scaling Project Review]] - Liang Zhen
In November 2009, the senior Lustre engineers met in conjunction with the SC'09 event in Portland, Oregon, to discuss designs for upcoming features and implementation status of current development projects.
* [[Media:SC09-Quota-Code.pdf|Quota Project Review]] - Johann Lombardi
 
* [[Media:SC09-Imperative-Recovery.pdf|Imperative Recovery Design Presentation]] - Nicolas  
The following presentations and design documents describe new Lustre features currently under development. They were made available as part of the the DARPA High Productivity Computing Systems (HPCS)project or presented at Supercomputing 2009 (SC'09).
* [[Media:SC09-ZFS-End-to-End-Integrity.pdf|ZFS, Lustre, End-to-end Data Integrity BOF]] - Andreas Dilger
 
* [[Media:SC09-LOV-OSC.pdf|LOV/OSC/llog Redesign Presentation]] - Alex Zhuravlev
* [[Media:SC09-kDMU-Code.pdf|Kernel DMU Project Review (November 2009)]] - Alex Zhuravlev
* [[Media:SC09-CMD-Code.pdf|Clustered Metadata Project Review]] - Tom Wang
* [[Media:SC09-SOM-Code.pdf|Size On MDS Project Review (November 2009)]] - Vitaly Fertman
* [[Media:SC09-Simplified-Interop.pdf|Simplified Interop (CSS) Design Presentation]] - Eric Mei
* [[Media:SC09-FID-on-OST.pdf|FIDs on OST Design Presentation (November 2009)]] - Mike Pershin
* [[Media:SC09-HSM-Code.pdf|HSM Project Review(November 2009)]] - Nathan Rutman
* [[Media:SC09-SMP-Scaling.pdf|Server SMP Scaling Project Review (November 2009)]] - Liang Zhen
* [[Media:SC09-Quota-Code.pdf|Quota Project Review (November 2009)]] - Johann Lombardi
* [[Media:SC09-Imperative-Recovery.pdf|Imperative Recovery Design Presentation(November 2009)]] - Nicolas  
* [[Media:SC09-ZFS-End-to-End-Integrity.pdf|ZFS, Lustre, End-to-end Data Integrity BOF (November 2009)]] - Andreas Dilger
* [[Media:SC09-LOV-OSC.pdf|LOV/OSC/llog Redesign Presentation (November 2009)]] - Alex Zhuravlev
* [[Media:SC09-CMD-Code.pdf|Clustered Metadata Project Review (November 2009)]] - Tom Wang
* [[Media:SC09-Simplified-Interop.pdf|Simplified Interop (CSS) Design Presentation (November 2009)]] - Eric Mei




The DARPA High Productivity Computing Systems (HPCS) project is a program created to ensure that US Government agencies continue to have access to the advanced high-performance computing technologies needed to fulfill their missions. The program objectives include achieving extremely high IO performance and file system scale and reliability. Cray Inc. has partnered with Sun to use Lustre to achieve these goals.  
The DARPA High Productivity Computing Systems (HPCS) project is a program created to ensure that US Government agencies continue to have access to the advanced high-performance computing technologies needed to fulfill their missions. The program objectives include achieving extremely high IO performance and file system scale and reliability. Cray Inc. has partnered with Sun to use Lustre to achieve these goals.  


The Lustre team has prepared several design documents as part of the HPCS program. These designs are:
The Lustre team has prepared several design documents as part of the HPCS program. These designs are:


    * Lustre HPCS Design Overview
*[[Media:JKD_Wiki_V1_2009_08_07_Lustre_HPCS_Overview.pdf|Lustre HPCS Design Overview (June 2009)]]
    * Filesystem Integrity Check Design
*[[Media:FSCK_Design-2009-06-15-09.pdf|Filesystem Integrity Check Design(June 2009)]]
    * End to End Data Integrity Design
*[[Media:End-to-End-Integrity-2009-06-15.pdf|End to End Data Integrity Design(June 2009)]]
    * LNet Channel Bonding Design
*[[Media:Channel Bonding_06_15_09.pdf|LNet Channel Bonding Design(June 2009)]]
    * Rebuild Performance Design
*[[Media:Rebuild_performance-2009-06-15.pdf|Rebuild Performance Design(June 2009)]]
    * Clustered Metadata Design
*[[Media:HPCS_CMD_06_15_09.pdf|Clustered Metadata Design(June 2009)]]

Revision as of 10:08, 1 December 2009

the designs reflect a certain point in time to the extent that a design finds itself in a feature in a release there will be other pages and assets on the wiki. Some of the information may not be current ... more historical. Latest presentations are current. The rest needs to be in an archive place. Some content may be out of date.

About once a year, the Lustre Engineering team gathers to discuss new features under development and testing efforts.

The Lustre team has prepared several design documents as part of the HPCS program. The DARPA High Productivity Computing Systems (HPCS) project is a program created to ensure that US Government agencies continue to have access to the advanced high-performance computing technologies needed to fulfill their missions. The program objectives include achieving extremely high IO performance and file system scale and reliability. Cray Inc. has partnered with Sun to use Lustre to achieve these goals.

In November 2009, the senior Lustre engineers met in conjunction with the SC'09 event in Portland, Oregon, to discuss designs for upcoming features and implementation status of current development projects.

The following presentations and design documents describe new Lustre features currently under development. They were made available as part of the the DARPA High Productivity Computing Systems (HPCS)project or presented at Supercomputing 2009 (SC'09).


The DARPA High Productivity Computing Systems (HPCS) project is a program created to ensure that US Government agencies continue to have access to the advanced high-performance computing technologies needed to fulfill their missions. The program objectives include achieving extremely high IO performance and file system scale and reliability. Cray Inc. has partnered with Sun to use Lustre to achieve these goals.


The Lustre team has prepared several design documents as part of the HPCS program. These designs are: