- Minor
There seems to be a really odd performance issue with LSI-2308 based controllers
When all the drives on the controller are spun down (I only have eight) and you attempt to access them for parity checking, benchmarking a single drive
We get the following speed results from
Parity tests:
2021-04-27, 03:06:09 1 day, 4 hr, 36 min, 29 sec 77.7 MB/s OK 0
2021-03-15, 14:44:59 15 hr, 14 min, 58 sec 145.8 MB/s OK 0
2021-02-15, 15:16:28 15 hr, 46 min, 27 sec 140.9 MB/s OK 0
2021-01-11, 15:39:25 16 hr, 9 min, 24 sec 137.6 MB/s OK 0
2020-12-14, 15:40:07 16 hr, 10 min, 5 sec 137.5 MB/s OK 0
2020-11-09, 14:42:48 15 hr, 12 min, 47 sec 146.1 MB/s OK 0
2020-10-12, 14:54:37 14 hr, 57 min, 53 sec 148.5 MB/s OK 0
As you can see my typical speed for parity tests should be about 140MB/s on average
Drive benchmarks:
The benchmarks are also weird in that I got the second results by simplying spinning down and spinning up all the drives prior to just blindly benchmarking all my drives.
Testing this condition with the parity check also produces the same result - starting the parity check while the drives are spun down results in a prity check that runs at 777MB/s max, whereas spinning up all the drives first allows them hit the max speed of about 200MB/s
Also it seems only my Toshiba N300 drives are affected, and none of my Seagate Archive drives or drives on the onboard SATA controller seems to be affected (or I haven't noticed)
Any suggestions or ideas?