After updating to 11.1 my system can't boot with errors like
(ada0:ata2:0:0:0): WRITE_DMA48. ACB: 35 00 50 29 10 40 6c 00 0c 00
(ada0:ata2:0:0:0): CAM status: Command timeout
(ada0:ata2:0:0:0): Retrying command
for all 6 sata hdd(mirror from 2 raidz)
Hardware: Supermicro X8DTN+-F / 6xWD1502FYPS-02W3B0 /2xE5649
HDDs connected to sata ports on baseboard.
If I add
to device.hints I'm able to boot but performance of IO becomes really disappointing.
If I roll back system to 11.0 all works fine again.
What was done so far:
1) Placed disks with same sata cables to another PC - boots fine
2)Tried separate raid controller on this baseboard - doesn't boots properly
4)Used separate power supply for disk - the same errors.
5)Used another power supply for whole system - no effect, same issue
Also, if I add to /etc/rc.d/zfs something like
"find / -name something" after "zfs mount -a" it boots too(without modification of device.hints), but after some time igb0(there is torrent traffic on it)will hung and only reboot helps, maybe this is related or this is some separate bug.
I don't remember exact dmeseg message for hung of igb0, but will post update when will face it again.
Also noticed such thing:
ada0 at ata2 bus 0 scbus0 target 0 lun 0
ada1 at ata2 bus 0 scbus0 target 1 lun 0
ada2 at ata3 bus 0 scbus1 target 0 lun 0
ada3 at ata3 bus 0 scbus1 target 1 lun 0
ada4 at ata4 bus 0 scbus2 target 0 lun 0
ada5 at ata5 bus 0 scbus3 target 0 lun 0
Please ignore last comment 2017-08-21 22:57:59 UTC
Just noticed that posted slightly wrong info.
Stripe from 2 raidz used, not mirror
Tried to revert all changes for ata driver between 11.0 and 11.1. Unfortunately this didn't help.
probably issue somewhere in cam.
I have a couple of thoughts for further debugging, will try them and update this bug.
Seems like issue was with HDDs, after replacing 2 hdds and removing from pool another 2, what was going to die I dont't see such errors.
But this is strange why it was able to work fine on 11.0