meta data for this page
  •  

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
linux:fs:zfs:tuning [2026/04/10 09:24] – niziaklinux:fs:zfs:tuning [2026/04/14 21:43] (current) – niziak
Line 35: Line 35:
     * BS=16m jobs=1 IOPS RW 9/4     * BS=16m jobs=1 IOPS RW 9/4
     * BS=16m jobs=6 IOPS RW 17/7     * BS=16m jobs=6 IOPS RW 17/7
 +  * zfs dataset with recordsize 1M:
 +    * BS=4k jobs=6 IOPS RW 21,7/9k - aggregated
 +    * BS=128k jobs=6 IOPS RW 1125/484
 +    * BS=1m jobs=6 IOPS RW 232/101
 +    * BS=16m jobs=6 IOPS RW
   * zfs dataset with recordsize 16M:   * zfs dataset with recordsize 16M:
     * BS=4k jobs=1 IOPS RW 38/16     * BS=4k jobs=1 IOPS RW 38/16
Line 41: Line 46:
     * BS=16k jobs=6 IOPS RW 122k/52k     * BS=16k jobs=6 IOPS RW 122k/52k
     * BS=128k jobs=1 IOPS RW 20/9     * BS=128k jobs=1 IOPS RW 20/9
-    * BS=128k jobs=6 IOPS RW 17.7K/7607+    * BS=128k jobs=6 IOPS RW 17.7K/7607 - small iops are aggregated into 16M
     * BS=1m jobs=1 IOPS RW 30/13     * BS=1m jobs=1 IOPS RW 30/13
     * BS=1m jobs=6 IOPS RW 2586/1117     * BS=1m jobs=6 IOPS RW 2586/1117
Line 47: Line 52:
     * BS=16m jobs=6 IOPS RW 20/8     * BS=16m jobs=6 IOPS RW 20/8
  
 +For example: on pool composed as 6x HDD raidz2: 
 +  * zfs dataset with recordsize 16M: 
 +    * BS=128k jobs=6 IOPS RW 16.4k/7026 
 +    * BS=1m jobs=6 IOPS RW 2472/1068 
 +    * BS=16m jobs=6 IOPS RW 27/11
  
 ===== zil limit ===== ===== zil limit =====