As a followup to this article, I used a zfs volume and an ufs volume with an application doing the same work on both partitions (replicated sql engines).
Click on the still frame to download the video (4 MB, ISO MPEG 4 format):
Click on the still frame to download the video (4 MB, ISO MPEG 4 format):
Red pixels mean write operations, green pixels mean read operations.
One pixel represents approx 10700 blocks or 5,3 MB. The disks have
140GB each.
Both hosts are running MySQL InnoDB databases and the application updates BOTH in the exact same manner (same INSERTs, SELECTs and UPDATEs).
The ZFS host does a "DELETE ..... WHERE ..." at 22:30 (10:30pm), the UFS host does that at 01:30am. Approx 3 million columns are deleted by these operations per database.
Both hosts are running MySQL InnoDB databases and the application updates BOTH in the exact same manner (same INSERTs, SELECTs and UPDATEs).
The ZFS host does a "DELETE ..... WHERE ..." at 22:30 (10:30pm), the UFS host does that at 01:30am. Approx 3 million columns are deleted by these operations per database.
Very interesting to watch, thanks! :)