This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revisionBoth sides next revision |
| abstract:caviness:filesystems:lustre [2020-05-29 13:35] – frey | abstract:caviness:filesystems:lustre [2020-05-29 13:37] – frey |
|---|
| Buying a better (and more expensive) disk is one way to improve i/o performance, but once the fastest, most expensive disk has been purchased this path leaves no room for further improvement. The demands of an HPC cluster with several hundred (maybe even thousands) of compute nodes quickly outpaces the speed at which a single disk can shuttle bytes back and forth. Parallelism saves the day: store the filesystem blocks on more than one disk and the i/o performance of each will sum (to a degree). For example, consider a computer that can move data to its hard disks in //1 cycle// with a hard disk that requires //4 cycles// to write a block. Storing four blocks to just one hard disk would require 20 cycles: 1 cycle to move the block to the disk and 4 cycles to write it, with each block waiting on the completion of the previous: | Buying a better (and more expensive) disk is one way to improve i/o performance, but once the fastest, most expensive disk has been purchased this path leaves no room for further improvement. The demands of an HPC cluster with several hundred (maybe even thousands) of compute nodes quickly outpaces the speed at which a single disk can shuttle bytes back and forth. Parallelism saves the day: store the filesystem blocks on more than one disk and the i/o performance of each will sum (to a degree). For example, consider a computer that can move data to its hard disks in //1 cycle// with a hard disk that requires //4 cycles// to write a block. Storing four blocks to just one hard disk would require 20 cycles: 1 cycle to move the block to the disk and 4 cycles to write it, with each block waiting on the completion of the previous: |
| |
| {{ serial-vs-parallel.png?300 |Writing 4 blocks to (a) one disks and (b) four disks in parallel.}} | {{ :abstract:caviness:filesystems:serial-vs-parallel.png?300 |Writing 4 blocks to (a) one disks and (b) four disks in parallel.}} |
| |
| With four disks being used in parallel (example (b) above), the block writing overlaps and takes just 8 cycles to complete. | With four disks being used in parallel (example (b) above), the block writing overlaps and takes just 8 cycles to complete. |
| |
| The Caviness cluster contains multiple //Object Storage Targets// (OSTs) in each rack that each contain many hard disks. For example, ''ost0'' contains 10 SATA hard disks (8 TB each, 1 hot spare) managed as a ZFS storage pool with an SSD acting as a read cache for improved performance: | The Caviness cluster contains multiple //Object Storage Targets// (OSTs) in each rack that each contain many hard disks. For example, ''ost0'' contains 10 SATA hard disks (8 TB each, 1 hot spare) managed as a ZFS storage pool with an SSD acting as a read cache for improved performance: |
| |
| {{ :abstract:caviness:filesystems:caviness-lustre-oss_ost.png?400 |Example image of Caviness Lustre OSS/OST. }} | {{ :abstract:caviness:filesystems:caviness-lustre-oss_ost.png?400 |Example image of Caviness Lustre OSS/OST. }} |
| |