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 The information found here is all likely to be out of date.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.
Configuring Lustre File Striping: Difference between revisions
No edit summary |
No edit summary |
||
| Line 10: | Line 10: | ||
OM Chapter 25 - Striping and IO Options | OM Chapter 25 - Striping and IO Options | ||
----- | |||
Using stripes | |||
One of the main reasons for Lustre file system's performance is the striping of data blocks over multiple OSTs. The stripe count can be set on a file system, directory or file level. | |||
To see the current stripe size, use the command lfs getstripe [file, dir, fs]. On the current system this will produce the following output: | |||
As can be seen, the default stripe count is 2 (that is, striping over two OSTs), default stripe size is 4 MB (can be set in K, M or G), and all writes start from the first OST. | |||
Note – When setting the stripe, the offset is set before the stripe count. | |||
Setting a new stripe pattern on the file system can look like this: | |||
This example sets the stripe of /mnt/lustre to 4 MB blocks starting at OST0 and spanning over one OST. If a new file is created with these settings, the following results are seen: | |||
As can be seen, the entire file was written to the first OST, and there is a very uneven distribution of data blocks. | |||
Revision as of 16:21, 7 October 2009
Have asked Torben to suggest subtopics for wiki
Intro...Configure striping to optimize performance ...
http://wiki.lustre.org/index.php/Striping_Guidelines
Cl400_OH - Slides 133-114
Page 13 in Torben's paper
OM Chapter 25 - Striping and IO Options
Using stripes One of the main reasons for Lustre file system's performance is the striping of data blocks over multiple OSTs. The stripe count can be set on a file system, directory or file level. To see the current stripe size, use the command lfs getstripe [file, dir, fs]. On the current system this will produce the following output: As can be seen, the default stripe count is 2 (that is, striping over two OSTs), default stripe size is 4 MB (can be set in K, M or G), and all writes start from the first OST. Note – When setting the stripe, the offset is set before the stripe count. Setting a new stripe pattern on the file system can look like this: This example sets the stripe of /mnt/lustre to 4 MB blocks starting at OST0 and spanning over one OST. If a new file is created with these settings, the following results are seen: As can be seen, the entire file was written to the first OST, and there is a very uneven distribution of data blocks.
