On 28/10/2022 09:07, Damien Le Moal wrote:
Well, yeah. So if some error happens and EH kicks in, then full queue
depth of requests may be allocated. I have seen this for NCQ error. So
this is why I make in very first patch change allow us to allocate
reserved request from sdev request queue even when budget is fully
allocated.
Please also note that for AHCI, I make reserved depth =1, while for SAS
controllers it is greater. This means that in theory we could alloc > 1x
reserved command for SATA disk, but I don't think it matters.
Yes, 1 is enough. However, is 1 reserved out of 32 total, meaning that the
user can only use 31 tags ? or is it 32+1 reserved ? which we can do since
when using the reserved request, we will not use a hw tag (all reserved
requests will be non-ncq).
The 32 + 1 scheme will work.
Yes, 32 + 1 is what we want. I now think that there is a mistake in my
code in this series for ahci.
So I think we need for ahci:
can_queue = 33
nr_reserved_cmds = 1
while I only have can_queue = 32
I need to check that again for ahci driver and AHCI SHT...
But for CDL command completion handling, we
will need a NCQ command to do a read log, to avoid forcing a queue drain.
For that to reliably work, we'll need a 31+1+1 setup...
So is your idea to permanently reserve 1 more command from 32 commands ?
Or re-use 1 from 32 (and still also have 1 separate internal command)?
Thanks,
John
