You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
LSI MegaRAID controller with 4 disks in JBOD mode (and nothing else). One disk fails, and the whole controller gets stuck and stalls and crashes and has to have the firmware full reset by the driver. Seriously, why are hardware RAID cards such complete garbage?
This has happened to me on *two* machines with different LSI cards recently. How do they intend to sell redundancy if their whole card crashes when a disk goes down? Yes I know about IT mode firmware, these are not personal boxes, crossflashing experiments aren't an option.
firmware. Just always go for JBOD. MPT is a better LSI driver anyway than mrsas
See reply. I know IT mode works. It's not an option here.
Fun fact: cacheless software parity RAID performance is still way better than (LSI) cacheless hardware parity RAID performance.https://twitter.com/marcan42/status/1051535931411324928?s=19 …
So why using an lsi raid controller in jbod? 
Direct attach on ahci works fine isn't it?
Because that's what server vendors sell you.
What do you think about freenas? ZFS based, seems to be a great choice, not?
My only experience with ZFS has been quite poor (horrid snapshot mirroring performance between two FreeNAS instances). I've heard some horror stories of data loss too. And it's not native to Linux. I use CephFS myself. It's a cluster solution but it works on single hosts too.
Had the same think happen to me, a disk drop down of the array and the controller went nut and mptsas did a reset of thye HBA, flapping a hundred SAS path failing the ZFS pool because of the induced latency marking disks as error'ed
LSI HP-branded HBA (no raid crap or anything)
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
