ME3800 packet forward performance

[qitianbiao]

Hi There,

Do anybody know how is the packet forward performance of ME3800 please? Is it hardware directly foward or software? We are concerned a lot on how fast ME3800 can forward packets, since we want to use it as a timing/synchronous auxiliary test equipment and we don't want much packet delay added through ME3800.

Thanks in advance,

Chico

[Parvesh Paliwal]

I think this type of info is easily available with the datasheets.    

[qitianbiao]

Hi Parvesh,

Thank you! There is one sentence in  the datasheet said 'Forwarding rate: Cisco ME 3800X-24FS AC or DC: 65  Mpps'. Does that mean the packet forward delay is 1/65M=15.4ns?

Regards,

Chico

[Joseph W. Doherty]

Disclaimer

The  Author of this posting offers the information contained within this  posting without consideration and with the reader's understanding that  there's no implied or expressed suitability or fitness for any purpose.  Information provided is for informational purposes only and should not  be construed as rendering professional advice of any kind. Usage of this  posting's information is solely at reader's own risk.

Liability Disclaimer

In  no event shall Author be liable for any damages whatsoever (including,  without limitation, damages for loss of use, data or profit) arising out  of the use or inability to use the posting's information even if Author  has been advised of the possibility of such damage.

Posting

It means the aggregate forwarding performance is 65 Mpps (normally for minimal size Ethernet packets) across the whole switch at wire-rate (less serialization delay, store-and-forward).  BTW, 65 Mpps supports about 44 Gbps (or 22 Gbps duplex).

[qitianbiao]

Let's say a packet with 100 bytes length, without any bandwidth confliction at all. Can we get that how long the ME3800 needs to forward the packet from one port to the other completely?

Store-and-forward is not the fastest way and usually it cause micor-second delay as I know, it ME3800 not cut-through mode or is it configurable? Cut-through mode is fastest, isn't it?

[Joseph W. Doherty]

Disclaimer

The   Author of this posting offers the information contained within this   posting without consideration and with the reader's understanding that   there's no implied or expressed suitability or fitness for any purpose.   Information provided is for informational purposes only and should not   be construed as rendering professional advice of any kind. Usage of  this  posting's information is solely at reader's own risk.

Liability Disclaimer

In   no event shall Author be liable for any damages whatsoever (including,   without limitation, damages for loss of use, data or profit) arising  out  of the use or inability to use the posting's information even if  Author  has been advised of the possibility of such damage.

Posting

Off the top of my head, don't know whether a ME3800 supports cut though.  The need for cut through sort of fell out of favor with 100 Mbps.  I think the Nexus revived it for ultra low latency in the data center.

The major part of store-and-forward delay can be calculated by taking the packet (frame) size, converting to bits, and dividing by line speed.  So 100 bytes would be (roughly) 80 us @ 10 Mbps, 8 us @ 100 Mbps, .8 us @ gig (if my math is correct).

[qitianbiao]

Thanks!