Editor
17
edits
Difference between revisions of "ZFS on high latency devices"
Jump to navigation
Jump to search
no edit summary
Jlcampbell (talk | contribs) (Created page with "This guide assumes familiarity with common ZFS commands and configuration steps. At a mimimum, you should understand how ZFS categorizes I/O and how to use zpool iostat -r, -...") |
Jlcampbell (talk | contribs) |
||
| Line 11: | Line 11: | ||
reads and writes. This is a method for optimizing that; very high performance and large | reads and writes. This is a method for optimizing that; very high performance and large | ||
IOP size is possible. | IOP size is possible. | ||
--- | |||
There are a few requirements, though: | There are a few requirements, though: | ||
| Line 117: | Line 119: | ||
aggr-final = 3 * K * blocksize | aggr-final = 3 * K * blocksize | ||
write gap = ashift * 4 = 16K | write gap = ashift * 4 = 16K | ||
| Line 124: | Line 125: | ||
sync taskq = 75 | sync taskq = 75 | ||
--- | |||
The approach taken works like this: | The approach taken works like this: | ||
| Line 156: | Line 159: | ||
the other max numbers are within 4 threads of SRmax | the other max numbers are within 4 threads of SRmax | ||
--- | |||
If AW dominates, decrease zfs_sync_taskq_batch_pct. | If AW dominates, decrease zfs_sync_taskq_batch_pct. | ||