9/6/2023 0 Comments Crystal disk mark explained![]() For completeness sake, you would need to disable the cache or use it at least only for metadata for the ZFS dataset in question: zfs set primarycache=metadata.ĭo not forget that ZFS is copy on write, which will lead to fragmentation over time. The ARC is a read cache, therefore, unless you want to do read performance benchmarks, you should not have to worry about it. Then start with the next layer, ZFS, then from within a VM to see what each layer is costing you. ![]() Have a look the ZFS benchmark paper to see what FIO commands to use: First a single disk, write with 4k and 4m and potentially sequential and random. ![]() If all you have on the disks is some test data, I would recommend to start benchmark from the bottom layers. I glanced over the thread, so if I misunderstand or missed something, let me know. Most frequently used (MFU) ghost: 0.0 % 0 L2 eligible MRU evictions: 85.3 % 278.5 KiBĪRC total accesses (hits + misses): 10.4kĪctual hit ratio (MFU + MRU hits): 94.8 % 9.9k L2 eligible MFU evictions: 14.7 % 48.0 KiB Metadata cache size (current): 3.5 % 206.1 MiBĭnode cache size (hard limit): 10.0 % 588.3 MiBĭnode cache size (current): < 0.1 % 183.1 KiB Metadata cache size (hard limit): 75.0 % 5.7 GiB Most Recently Used (MRU) cache size: 98.1 % 625.9 MiB Most Frequently Used (MFU) cache size: 1.9 % 12.2 MiB ZFS Subsystem Report Tue Aug 09 15:45:04 2022
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |