Thanks
but I mean, in detail, what was fixed and how, I know I read it somewhere while exploring 3008 option few months ago
Aha its same article but it has "Discussion" tab.
What I found, "our" 16.00.12.00 has in release notes only one bug fix, but in 16.00.12.00 on Broadcom site here
16.00.12.00 for 9305 there is also a second bug fix, reading as follows:
Code:
ID: DCSG00398894
Headline: SATA only: WRITE SAME NCQ encapsulation assumes NonData NCQ is supported if Zero EXT is Supported
Description Of Change: Disable NCQ encapsulation if Zero EXT is supported but Non Data NCQ is not supported
Issue Description: In case if Zero EXT is supported but Non Data NCQ is not supported by drive, WRITE SAME
NCQ encapsulation would send Non Data NCQ command to the drive.
Drive would fail the command as Non Data NCQ is not supported by drive.
This will cause command failure to host.
Steps To Reproduce: IO errors are observed when mkfs.ext4 operation is done on drives that support Zero EXT but
do not support Non Data NCQ.
This could be an answer to people having problems with 3008 like here
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=224496 where people report them not only with Seagate but with WD Red also
So far after all the search only reliable fixes were either updated FW for drives, not always available, or disabling NCQ completely via mprutil or camcontrol tags, with performance hit
But the release notes above imply Broadcom possibly got to the bottom of it, and made a fix without complete disabling NCQ and which may be universal for all the drives.
Or maybe I just hope they did it.
I can't even test to be sure because I don't have access to 9305.
This version of 16.00.12.00 with 2nd bug fix isn't available for 9300-8i
How to get that 2nd fix ported for all 3008 series?