Showing posts with label End-to-End. Show all posts
Showing posts with label End-to-End. Show all posts

Thursday, November 17, 2011

"CLOUD" Infrastructure as a Service (IaaS) and FCoE VN2VN

When the new FCoE (Fibre Channel over Ethernet) VN2VN (aka Direct End Node to End Node) was defined in the T11.3 FC-BB-6 Ad Hoc Working Group it was assumed that it would find a niche in the Low to medium IT organizations that wanted to have compatibility with Fibre Channel (FC). Though that is still valid, it looks as though it may also be important to some of the new "Cloud" services that provide Infrastructure as a Service (IaaS). 

FCoE VN2VN is a additional FCoE protocol which permits FCoE End Nodes such as Servers acting as "Initiators" and FCoE End Nodes such as Storage Controllers acting as" Targets" to either directly attach to each other or attach with only lossless Ethernet switches between them (perhaps as few as one switch between the End Nodes).  This form of FCoE does not require any FC/FCoE networking equipment.

FCoE VN2VN permits the IaaS organization to enable their installation to provide storage interconnectivity with FC and/or FCoE.  FCoE VN2VN capability can be used to give a customer an FCoE VN2VN connection between the servers and the storage that are supplied by the IaaS provider. This VN2VN interconnect can provide the fastest end-to-end connection with the fewest number of "hops" as possible.  That is, the data path can traverse between the server and the storage unit by passing through perhaps as few as one Lossless Ethernet switch. No FCF (Fibre Channel Forwarder) is required, which means that no additional FC switching processes and overhead are involved in the data path.  In addition, the lossless Ethernet switch can be provided by a great number of vendors, thus permitting the lowest possible cost data path.  This means that the IaaS provider can give a customer the fastest interconnect at the lowest possible cost.

To enable this type of capability there is certain implications upon the configuration of the "Cloud" installation. For example: if the customer would like to purchase infrastructure where the required servers and storage can fit into a single rack (or even a 2-3 rack side-to-side configuration) they are candidates for FCoE VN2VN interconnection.  In such a configuration a lossless Ethernet switch can be placed at the top of the Rack (or Rack set) and Ethernet connections run from the servers to the Switch and then to the storage units. For total installation flexibility the Top-of Rack (ToR) switches may also be physically interconnected to an End-of-Row (EoR) Director class FCoE switch that may have full FCF capabilities.  However, the EoR Director would have no direct involvement with the data path for this IaaS rack-set.  It is also possible to have a ToR switch at the top of each rack and have them interconnected with each other. In this case, the data path may go through two ToR switches but would still not need to go through the EoR FCoE Director.

So depending on the needs of the customer, and the physical configuration required by the provider, it is possible to obtain the minimum switch/"hop" count and lowest latency interconnect. This means that the provider of IaaS services can "carve-out" a rack or set of racks that can be dedicated to a specific IaaS customer, and give them isolated service yet when that customers grows and has a much larger requirement, or they leave the IaaS provider's installation, the installation can easily re-task the servers and storage, or expand to other racks of server and storage, without needing to physically re-cable the network configuration. 
 
In this example, the IaaS systems and storage are given their own VLANs that can be used by the FCoE VN2VN to permit "direct" connection between the IaaS customer's servers and storage without involvement of other systems within the IaaS providing installation. It should be noted that when the customer either leaves the installation or expands, the provider can re-task the equipment and remove the VLAN specification, and in the case of expansion utilize a regular FCoE interconnect (via the EoR director FCoE switches). 

Likewise, a company often has the need to provide IaaS like services to various internal departments which for various company technical or "political" reasons need to be provided with dedicated server and storage rack(s) which can function as isolated environments for various company departments and projects. This then becomes an internal IaaS "Cloud" environment in which FCoE VN2VN can often be an appropriate solution to this configuration requirement.

But independent of the internal or external "Cloud" IaaS environments FCoE VN2VN is still appropriate for the smaller computing environments such as "Big Box" stores, "Disaster Recovery Trailers" and small to medium IT installations.

In smaller organizations such as local "Big Box" stores, they can have their whole data center located in a single rack which has the appropriate servers and storage all inclusive.  In this type of configuration the various Server vendors can be asked to bid on the "total rack" that includes FCoE VN2VN, and often obtain a "total solution" at a minimum cost.  I was once associated with an organization that wanted to sell such configurations to the big box stores but was deterred because of the cost of the Fibre Channel Connections and switches. That concern is no longer relevant when FCoE and VN2VN connections, within the rack, are utilized.  

I also understand that various "disaster recovery trailers" can utilize such configurations in their trailers when they are used to provide temporary IT service to big box stores (and others) after various disasters. 

And, of course, when it comes small to medium IT installations (ones that fit within a single or few Racks) FCoE VN2VN configurations seems to offer a high performing low cost storage interconnect solution that is compatible with future growth into a full FCoE or FC installation.  These types of installations may also be seen as a valuable asset that can easily be integrated during a merge or buy-out with larger organizations that probably have an FC and/or FCoE.

Friday, June 25, 2010

FCoE Direct End-to-End (aka FCoE VN2VN)

Blog on June 25, 2010

At the latest meeting of the T11.3 standards organization (FC-BB-6 Ad Hoc Working Group) the concept of FCoE Direct End-to-End protocol was accepted for input into the Workgroup's next standard. It is also known as FCoE VN_Port to VN_Port (FCoE VN2VN). This new function permits FCoE adapters, which are interconnected within the same Level 2 Lossless Ethernet network, to discover and connect to compatible FCoE adapters -- which have the appropriate Virtual N_Ports -- and then transmit Fibre Channel commands and data via the standard FCoE protocol.

This is all done on a Lossless Ethernet Network without any assistance from a Fibre Channel Switch or an FCoE Switch (called an FC Forwarder -- FCF). All that is needed is the appropriate VN2VN FCoE Adapters and a Lossless Ethernet layer 2 Network.

There also exists, today, some Open Source FCoE software that only requires a normal Ethernet NIC, to operate standard FCoE protocols (a special Converged Network Adapter -- CNA -- is not required). It is expected that this Open Source software will be updated to also support the new VN2VN function.

The VN2VN (direct End-to-End) function will support 2 types of direct connections:
1. Connections through Lossless Ethernet switches
2. One to One Connection via a single cable (point to point)

The FCoE protocol is made up of 2 types of Ethernet frames (which have their own unique Ethertypes):
1. The FCoE initialization Protocol (FIP) frame packets
2. The Fibre Channel over Ethernet (FCoE) frame packets

The FIP packets are only used as part of discovery and connection setup whereas the FCoE packets carry the actual FC commands and data. The new VN2VN functions have only added additional FIP packets, and have left the rest of the protocol unchanged. The new VN2VN FIP packets were needed since in this mode there is no FCF to provide connection services.

The transfer of FC data and commands via the FCoE protocol -- which was developed in the T11.3 standards organization (FC-BB-5 Ad Hoc Working Group) -- continues to operate as currently specified and will continue unchanged in this new VN2VN environment.

The upper levels of the protocol remain FC, and that means that there continues to be complete compatibility with existing FC & FCoE Device Drivers etc. The vendors are, of course, adding additional management capabilities to exploit the additional capabilities of FCoE, but the command and data protocol do not require any modifications. Likewise, as adapters are updated to support VN2VN mode, the upper layers will retain their current FC compatibility even as additional management capabilities are added to permit ease (and flexibility) of use.

This new VN2VN capability will permit FC protocol to go "Down Market" to entry and Mid Range environments. Yet, as the installation grows it will be able to install FCF switches and thereby obtain the additional functions of a FC network without having to change the server or storage connections.

The new VN2VN capability will be competitive to iSCSI within a Data Center Environment. And I fully expect the Lossless Ethernet Standards, which were focused at a 10Gb/s Ethernet, to be offered by various vendors on 1Gb/s networks and switches. This will mean that FCoE VN2VN will operate very well with the Open Source FCoE code and 1Gb/s NICs without the overhead of TCP/IP. This should make the FCoE VN2VN capability very performance competitive with iSCSI.

Stay tuned to this Blog to see how the capability unfolds.