> -----Original Message-----
> From: netdev-bounce@xxxxxxxxxxx [mailto:netdev-bounce@xxxxxxxxxxx] On
> Behalf Of Dmitry Yusupov
> Sent: Monday, March 28, 2005 4:55 PM
> To: open-iscsi@xxxxxxxxxxxxxxxx
> Cc: David S. Miller; mpm@xxxxxxxxxxx; andrea@xxxxxxx;
> michaelc@xxxxxxxxxxx; James.Bottomley@xxxxxxxxxxxxxxxxxxxxx; ksummit-2005-
> discuss@xxxxxxxxx; netdev@xxxxxxxxxxx
> Subject: Re: Topic: Remote DMA network technologies
>
> On Mon, 2005-03-28 at 16:44 -0800, Asgeir Eiriksson wrote:
> > Care to be more specific about the performance you achieved?
> >
> > You might want to contrast your numbers to veritest verified numbers of
> > 800+ MBps and 600+KOPS achieved by Chelsio HBA with stateful offload
> > using either 1500B or 9KB MTU (for full detail see Veritest report at
> > http://www.chelsio.com/technology/Chelsio10GbE_iSCSI_report.pdf)
> >
> > 'Asgeir
FYI,
http://biz.yahoo.com/prnews/050329/cgtu006.html?.v=4
The actual whitepaper with performance results is on our site. In short, it
shows that it's fine to run sw iSCSI over 10GbE NIC with Linux-supported
stateless offloads (receive side could use more of these though :-)), on a
generic Opteron box.
Leonid
>
> I changed the subject, btw.
>
> In your paper. Its 28 M$ Initiator against one iSCSI Target on top of
> Chelsio HBA. Now prove me that Chelsio HBA as an Initiator can do
> somewhat close to 100K IOPS with regular Linux SCSI-MidLayer...
>
> Regards.
> Dmitry
>
>
|