User Tools

Site Tools


projects:borg:start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
projects:borg:start [m/d/Y H:i]
luis
projects:borg:start [m/d/Y H:i] (current)
raju
Line 1: Line 1:
 ====== Block reORGanization for Self-optimizing Storage Systems ====== ====== Block reORGanization for Self-optimizing Storage Systems ======
 +
  
 ===== Authors ===== ===== Authors =====
 +  * [[http://​www.cs.fiu.edu/​~mbhad001/​|Medha Bhadkamkar]]
   * [[http://​www.cs.fiu.edu/​~jguer022/​|Jorge Guerra]]   * [[http://​www.cs.fiu.edu/​~jguer022/​|Jorge Guerra]]
   * [[http://​www.cs.fiu.edu/​~lusec001/​|Luis Useche]]   * [[http://​www.cs.fiu.edu/​~lusec001/​|Luis Useche]]
-  * [[http://​www.cs.fiu.edu/​~mbhad001/​|Medha Bhadkamkar]] +  * Sam Burnett 
-  * [[http://​www.cs.fiu.edu/​~rkoll001/​|Ricardo Koller]]+  * Jason Liptak
   * [[http://​www.cs.fiu.edu/​~raju/​|Raju Rangaswami]]   * [[http://​www.cs.fiu.edu/​~raju/​|Raju Rangaswami]]
 +  * [[http://​users.cs.fiu.edu/​~vagelis/​|Vagelis Hristidis]]
  
-===== Introduction ​=====+===== Abstract ​===== 
 +This paper presents the design, implementation,​ and evaluation of 
 +BORG, a self-optimizing storage system that performs  
 +//automatic block reorganization//​ based on the observed I/O 
 +workload. 
 + 
 +BORG is motivated by three characteristics of I/O workloads:​ 
 +non-uniform access frequency distribution,​ temporal locality, and 
 +partial determinism in non-sequential accesses. 
 +To achieve its objective, BORG manages a small, dedicated partition 
 +on the disk drive, with the goal of servicing a majority of the I/O 
 +requests from within this partition with significantly reduced seek 
 +and rotational delays. 
 + 
 +BORG is transparent to the rest of the storage stack, including 
 +applications,​ file system(s), and I/O schedulers, thereby requiring no 
 +or minimal modification to storage stack implementations. 
 +We evaluated a Linux implementation of BORG using several 
 +real-world workloads, including individual user desktop environments,​ 
 +a web-server, a virtual machine monitor, and an SVN server. 
 +These experiments comprehensively demonstrate BORG's effectiveness 
 +in improving I/O performance and its incurred resource overhead.
  
 ===== Publications ===== ===== Publications =====
Line 14: Line 38:
   * **BORG: Block-reORGanization for Self-optimizing Storage Systems** {{borg-fast09.pdf|pdf}} {{borg-fast09.ps|ps}}\\ Medha Bhadkamkar, Jorge Guerra, Luis Useche, Sam Burnett†, Jason Liptak, Raju Rangaswami, and Vagelis Hristidis\\ Proceedings of File and Storage Technologies (FAST), February, 2009.   * **BORG: Block-reORGanization for Self-optimizing Storage Systems** {{borg-fast09.pdf|pdf}} {{borg-fast09.ps|ps}}\\ Medha Bhadkamkar, Jorge Guerra, Luis Useche, Sam Burnett†, Jason Liptak, Raju Rangaswami, and Vagelis Hristidis\\ Proceedings of File and Storage Technologies (FAST), February, 2009.
  
 +===== Code =====
 +
 +The code of BORG is not ready to be released. We hope to have a version ready some time soon. However, BORG has similarities to one of our previous projects -- [[..:​exces:​start|EXCES]]. Several details are the same in both projects and thus the EXCES code can be used as reference.
 +
 +
 +===== Traces =====
 +
 +The traces we use to evaluate BORG are available at: [[resources:​start#​traces]]
projects/borg/start.1237589680.txt.gz · Last modified: m/d/Y H:i by luis