Re: which kind of driver to design for AoE protocol?
- From: "KOOLER" <anton@xxxxxxxxxxxxxxxxxx>
- Date: 19 Aug 2006 01:26:31 -0700
You have to process as many requests at raised interrupt level as you
can. If you'd queue SRBs to PASSIVE_LEVEL worker in some way just b/c
it's easier to implement such a model - it would be a engineering
failure... You would not get adequate performance if you'd exploit
context switches, memory copy operations etc etc etc. In case of AoE
everything is comparably easy, but in case of say iSCSI delays would be
really deadly as for TCP you need to issue "other side" with request
completion status ASAP.
Anton
sven.kreamer@xxxxxxxxx писал(а):
scsi/storport miniports for hardware do tend to run at raised irql and
why not, all their code is IRQL insensitive. However, it is also
technically possible to process all of the SRB's at PASSIVE_LEVEL. I
had provided a link in this thread to an example that demonstrates
this. Thus, you could use the standard network stack. I don't know
about the iSCSI miniport architecture, but would hope it too allows
PASSIVE_LEVEL since this is very important for many types of virtual
hardware.
.
- Follow-Ups:
- Re: which kind of driver to design for AoE protocol?
- From: sven . kreamer
- Re: which kind of driver to design for AoE protocol?
- References:
- Re: which kind of driver to design for AoE protocol?
- From: Don Burn
- Re: which kind of driver to design for AoE protocol?
- From: soviet_bloke
- Re: which kind of driver to design for AoE protocol?
- From: sven . kreamer
- Re: which kind of driver to design for AoE protocol?
- Prev by Date: Re: which kind of driver to design for AoE protocol?
- Next by Date: Re: KeSetEvent crashing
- Previous by thread: Re: which kind of driver to design for AoE protocol?
- Next by thread: Re: which kind of driver to design for AoE protocol?
- Index(es):
Relevant Pages
|