PPT-I/O Systems (2): Disks 1

CSE 2431 Introduction to Operating Systems Instructor Adam C Champion PhD Reading Chap 11 135 1456 OSC Outline Disk Organization Disk Performance Disk Scheduling Algorithms. The View From Telescopes, Computers. and the Lab. Adam Frank. University of Rochester. A Cast Of Lots and Lots. AstroBEAR development. : J. Carroll, B. . Lui. , M. . Huarte. -Espinosa, S. Li, E. Hanson, E. Kaminski, K. . RAID (Redundant Arrays of Independent Disks). Disk . organization technique that manages a large number of disks, providing a view of a single disk of. High capacity and high speed up using multiple disk in parallel. Case Study: Facebook f4. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Engineering principle. Make the common case fast, and rare cases correct. Power law. Haystack. A design for warm photos. a. nd stellar multiplicity. Insights from recent surveys. Gaspard . Duchêne. (UC Berkeley, Obs. Grenoble). © NASA/JPL/Caltech. Planets in multiple systems?. © . LucasFilm. Ltd.. They must exist!. Phil Armitage. Colorado. Processes in Protoplanetary Disks. Disk structure. Disk evolution. Turbulence. Episodic accretion. Single particle evolution. Ice lines and persistent radial structure. Transient structures in disks. multicore issues. By Paul Grubbs. Portions of this talk were taken from Deniz Altinbuken’s talk on Disco in 2009: http://www.cs.cornell.edu/courses/cs6410/2009fa/lectures/09-multiprocessors.ppt. What papers will we be discussing?. and RAID. Outline. Disks. Disk scheduling algorithms. Redundancy in storage . systems, RAID. 2. Disk Geometry. Disks have multiple platters. Each platter has . an arm and a head for accessing data. The arms for the different platters move together. Pawel. . Artymowicz. U of Toronto. MRI turbulence. Some non-MRI turbulence. Roles and the dangers of turbulence. UCSC Santa Cruz 2010. I borrowed some . figures & slides from. X. Wu (2004). R. Nelson (2008). Web Content Distribution-. --3. Case Study: Facebook f4. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Engineering principle. Make the common case fast, and rare cases correct. Insights from recent surveys. Gaspard . Duchêne. (UC Berkeley, Obs. Grenoble). © NASA/JPL/Caltech. Planets in multiple systems?. © . LucasFilm. Ltd.. They must exist!. Planets in multiple systems!. Reads and writes are equally fast.. Arrays of these disks are used to provide highly reliable storage.. Increasingly popular as they are fast and do not contain moving parts.. Magnetic Disks.. . What is a magnetic disk and how it works. Two main types: Magnetic and Optical. Random access to memory. The hardware must be controlled by driver software called the “controller” in order to be used. Hard Disks, RAID, and Error Handling. Don Porter. Portions courtesy Emmett . Witchel. 1. Quick Recap. CPU Scheduling. Balance competing concerns with heuristics. What were some goals?. No perfect solution. Today: Block device scheduling. By Paul Grubbs. Portions of this talk were taken from Deniz Altinbuken’s talk on Disco in 2009: http://www.cs.cornell.edu/courses/cs6410/2009fa/lectures/09-multiprocessors.ppt. What papers will we be discussing?.