Recent content by ericloewe

We must be looking at different things, because all I see is the generic QVL entry for the SAS3008, which in no way provides meaningful information on SR-IOV besides listing "SR-IOV" with no further context. Also, no, I do not believe I asked how to activate SR-IOV. The link talks about SR-IOV...

No, you told ZFS to use a device, it tried to do so - could use a bit more intelligence, but whatever. Pretty easy fix, just create a partition that starts at 1M.

They're a tool you have maybe a handful of, like you might have a USB to SATA bridge or two. Occasionally useful for maintenance tasks, and very rarely useful if you happen to have a mountain of M.2 SSDs sitting on the shelf.

Yeah, these things are all over the place. It's literally just a PCB, two connectors, and some mounting hardware.

The first of those links does very little to explain how SR-IOV would work, the second link does not even contain the sequence of characters "SR-IOV"... However, off-topic, I find it interesting that the VMware docs mention a P16.00.13.00 firmware, which I'd never heard of. P16.00.10 is the...

Not these days, not ever. Put together 10 people, give them all of Broadcom's internal documentation and firmware code, make sure you have at least two SCSI and one PCI expert on the team, give them free rein to implement whatever crazy interface they want and give them six months. You might...

It doesn't make sense in that it is not a thing.

Which is exactly what this thread is about, an LSI SAS2208... I have first-hand experience with the H740P in standard RAID mode. It is atrocious. The HBA mode is probably better, but why pay more for functionality that won't be used and to end up with something that is an unknown quantity...

Yes. Completely irrelevant. It does not and cannot. If every single resource you found agrees, why do you still doubt that? That's a good sign, but not necessarily indicative of how things will work on TrueNAS. Support for real HBA functionality was introduced relatively late in the...

The U.2 connector was probably cheaper and/or more available for that production run. I bet the PCIe pins are all not connected to anything.

Because why not? They're cheap and cheerful and easily handle 3 Gb/s and 6 Gb/s per their spec. 12 Gb/s would get dodgy, though. Of course, single lane only, but you would never connect both lanes to the same host port, so there's no point in having a dual-lane SAS cable. As you've discovered...

Also, running compression with 4k writes is utterly pointless as all blocks with ashift=12 (you did set ashift=12 when creating the pool, right?) will be at least 4k anyway. But really, reconsider whether 4k sync writes are really necessary or representative of your future workload.

The .12 firmware update, IIRC, fixed some edge cases with SATA devices that would fail pretty obviously with .10. Probably not a big deal if Dell's firmware works without apparent issue.

I'm not sure I've seen it done with the SAS3108, but the process has been documented for some SAS2 controllers. It's definitely not officially supported and Broadcom's tools will fight you every step of the way, but it's also true that the hardware is essentially compatible (which is also how...

Since it wasn't obvious, my post #13 above was sarcastic.