Editor
348
edits
Difference between revisions of "Performance tuning"
Jump to navigation
Jump to search
m
Add information about larger record sizes.
m (Add information about larger record sizes.) |
|||
| Line 63: | Line 63: | ||
Changing the recordsize on a dataset will only take effect for new files. If you change the recordsize because your application should perform better with a different one, you will need to recreate its files. A cp followed by a mv on each file is sufficient. Alternatively, send/recv should recreate the files with the correct recordsize when a full receive is done. | Changing the recordsize on a dataset will only take effect for new files. If you change the recordsize because your application should perform better with a different one, you will need to recreate its files. A cp followed by a mv on each file is sufficient. Alternatively, send/recv should recreate the files with the correct recordsize when a full receive is done. | ||
==== Larger record sizes ==== | |||
Record sizes of up to 16M are supported with the large_blocks pool feature, which is enabled by default on new pools on systems that support it. However, record sizes larger than 1M is disabled by default unless the zfs_max_recordsize kernel module parameter is set to allow sizes higher than 1M. Larger record sizes than 1M are not well tested as 1M, although they should work. `zfs send` operations must specify -L to ensure that larger than 128KB blocks are sent and the receiving pools must support the large_blocks feature. | |||
=== zvol volblocksize === | === zvol volblocksize === | ||