New converged solutions from HP Networking



    Apparently there is not a single IT company that would not appeal to the topic of convergence (integration), as to the life buoy of the IT industry, without which, if it had gone to the bottom, it would at least significantly slow down the pace of development.

    In recent years, the issue of convergence has been particularly acute and relevant in the field of telecommunications. It was the telecom area that became a real testing ground for testing many new hardware solutions, technologies, and protocols that would allow a little (or dramatic) reduction of costs and time for their implementation, reduction of operating costs, and optimal resources available.

    But is the new topic of convergence, which had time, to fill the mouth of the technical people? Let us turn to a quote from the journal “Life and communication technology”: “What are the provisions we come to when we outline ways to reorganize (including new buildings) wired communications? First of all, its design, reconstruction should be completely combined for the telegraph and telephone, and first of all, this combination of design and device should be on the lines. The network of telegraph and telephone wires should be a unified system of wire communication ... Now this full integration is not only possible, but also absolutely necessary, starting with the local network, which should, as a rule, be designed for the possibility of both telephone and telegraph services ” . If you do not pay attention to the mention of an archaic form of communication such as a telegraph and a dubious transmission medium in the form of a wire connection, then you might think that we are talking about the present or relatively recent time. But no, this article has been over 90 years old and these words belong to the then deputy. drug addict of the post and telegraph of Russia AM Lubovitch.

    Thus, the issue of unification and integration of several solutions or technologies into one excites the minds for a very long time.
    HP has been actively developing and releasing converged business solutions for a very long time and sees this as a great, if not to say, bright future. Many CIO and IT specialists are still cautiously considering the possibility of switching from traditional types of communications to new and promising ones. But let's recall at least how the era of IP telephony began. Perhaps a dozen years have passed since the first tests of voice over IP transmission before IP telephony began to be massively introduced into food networks, proving its right to exist.

    So why all this long introduction?

    HP Launches New Converged Modular Switches for Data Center and Campus Networks! And I hasten to share this good news with you, and, at the same time, tell a little about it.

    We are talking about two new models of the HP FlexFabric 5930 series. This series has existed for some time on the market and was introduced until recently by a single device - the HP FlexFabric 5930 32QSFP + Switch - a compact single-unit switch with 32 40 Gbe ports and an unlockable switching matrix. This device is interesting in that it was the first switch in the HP line (and one of the first on the market) with hardware support for VXLAN and NVGRE.



    These switches are positioned primarily as the top of rack in large implementations or the distribution level or core for small data center sites. However, for campus networks, these devices can also be used as a kernel, since there is a full set of protocols for L3 traffic processing, PBR, Multicast, QoS, VRRP, stacking up to 9 devices with a combination of control plane, VRF-lite, virtualization of MCE switch resources A wide selection of SFP transceivers, etc.

    But today it’s not about him, but his two new brothers: the HP FlexFabric 5930 2QSFP + 2-slot Switch and the HP FlexFabric 5930-4Slot Switch.




    Brief performance characteristics of both devices:

    HP 5930 -2Slot + 2QSFP + Switch

    HP 5930-4Slot Switch

    Number of module slots

    2

    4

    CPU

    1GHz, dual core

    1GHz, dual core

    RAM

    4G

    4G

    Flash

    Nand: 1G Nor: 8M

    Nand: 1G Nor: 8M

    Packet memory buffer (bytes)

    12M

    12M

    MAC Address Table

    32K min / 288K Max

    32K min / 288K Max

    ARP table

    16K min / 120K max

    16K min / 120K max

    Number of IPv4 Routes

    16K min / 120K max

    16K min / 120K max

    Maximum number of VLAN interfaces

    2K

    2K

    Performance

    720Gbps

    1.28Tbps

    Throughput

    1071Mpps

    1428Mpps

    Delay (64byte / us)

    40GE: <1.2us

    40GE: <1.2us




    You can see that the number of entries in the MAC, ARP, IP tables can vary. It depends on the mode of operation of the switch. Depending on the needs and tasks, we can allocate a larger resource for storing L2 information to the detriment of L3, or, reducing the resource L2, allocate more for L3. Entry mode 0 is active by default.

    Entry mode

    MAC address table

    ARP or ND table

    Routing table

    0

    288 KB

    16 KB (ARP table) or 8 KB (ND table)

    16 KB (IPv4) or 8 KB (IPv6-64)

    1

    224 KB

    56 KB (ARP table) or 28 KB (ND table)

    16 KB (IPv4) or 8 KB (IPv6-64)

    2

    160 KB

    88 KB (ARP table) or 44 KB (ND table)

    16 KB (IPv4) or 8 KB (IPv6-64)

    3

    96 KB

    120 KB (ARP table) or 60 KB (ND table)

    16 KB (IPv4) or 8 KB (IPv6-64)

    4

    32 KB

    16 KB (ARP table) or 8 KB (ND table)

    128 KB (IPv4) or 64 KB (IPv6-64)




    Next, let's see what blocks the device data consists of.



    The first device on the front side has 2 slots for interface modules (I will talk about them later). Those. initially the slots are empty, and modules are an option that the user determines himself, depending on the technical requirements. Each integrated module is connected via bus to the ASIC processor at a speed of 320 Gbit / s. This bandwidth provides non-blocking switching for 8 40 Gbit / s ports or 24 10 Gbit / s + 2 40 Gbit / s per slot.

    On the back of the switch, we see that the power and cooling modules are duplicated. It is possible to choose the direction of cooling depending on the location of the hot-cold corridor, as well as the type of power supply - AC or DC with a power of 650 watts.

    Also nearby are 2 ports of 40 Gb / s each (for organizing a stack or as uplink ports). These two ports have their own 80 Gb / s ASIC connection bus, which also gives wire-speed.

    To the left are the OOB management port, console port, and USB port.


    The second device is very similar to the first. Presented already in the 2 RU form factor, there are 4 slots for optional interface modules, the number of power supplies is increased to 4, cooling modules are optimized for increased internal space, 2 fixed 40 Gbe ports are no longer available. Stacking and uplinks should be organized through standard modules on the front side.



    The two-unit version has a more efficient processor, otherwise the architecture is identical.



    The second device is very similar to the first. Presented already in the 2 RU form factor, there are 4 slots for optional interface modules, the number of power supplies is increased to 4, cooling modules are optimized for increased internal space, 2 fixed 40 Gbe ports are no longer available. Stacking and uplinks should be organized through standard modules on the front side.

    At its core, we can consider these switches as a modular switch with a passive backplane. The big advantage of such switches is the ability to individually select interfaces with a given set of characteristics. What interface modules are currently available:

    • HP 5930 24p SFP + and 2p QSFP + Mod - 24 universal SFP + ports and 2 QSFP + ports for connecting either 1/10 GbE or 40 GbE, respectively;



    • HP 5930 24p SFP + and 2p QSFP + Mod w Msec - a module similar in port capacity, but with hardware support for MACSec;



    • JH184A HP 5930 24 CP and 2p QSFP + Mod - 24 ports that can be used as 1/10 Gb Ethernet, or as 4/8 Gb Fiber Channel, and additional licenses are not required to enable native FC. Each port is configured individually, i.e. can be either Ethernet or FC. On similar competitor switches, you have to immediately select a group of ports that will work in one of the modes, which is not very flexible. As well as for the 5900CP switch, universal SFP + transceivers are available that are suitable for connecting LAN devices as well as SAN devices (H6Z42 HP 16Gb FC / 10GbE 100m SFP + Transceiver);



    • HP 5930 24p 10GBase-T and 2p QSFP + Mod - 24 copper 10GBase-T ports, as well as 2 QSFP +;



    • HP 5930 8-port QSFP + Module - and finally a card with 8 ports QSPF +



    It is worth noting that 3 types of DAC splitter are available for 40G ports - a cable designed to separate one 40G port into 4 10G. From the CLI, such interfaces will look like independent physical 10G ports, with the corresponding configuration capabilities. But it should be borne in mind that not every 40G port can work in this mode. Such ports for all interface modules and switches of the 5930 series are marked in the picture. This is a hardware limitation associated with the architecture of the switch. This should be borne in mind when designing.



    The physical characteristics of the switches of course mean a lot, but in the end, it all comes down to what the switch can do in terms of software tools. But he knows how much, since the device was originally developed for the Comware v7 operating system, which differs from the previous version in its modular architecture, isolation of memory allocated to processes, so the collapse of one process does not affect others, the ability to use ISSU, SDN support, and OpenFlow 1.3.1 converged protocols FCoE, DCB and much, much more. It does not make sense to list all supported protocols here, but you can get acquainted with the device capabilities in the datasheet or release note .

    Nevertheless, I will give some examples of the use of these switches. The main differentiator is the fact that the devices are convergent and can connect both standard Ethernet 1 / 10Gb and Native FC and FCoE to themselves. FC requires the HP 5930 24 CP and 2p QSFP + Mod, and Ethernet and FCoE require any interface modules. Thus, we can significantly save both on capital costs by buying only one or a couple of convergent switches for fault tolerance, and on operating ones, saving on service support, power consumption, rack space, cooling. It is also worth considering that administrators will deal with only one physical network instead of LAN and SAN separately.

    Since the switches expand due to modularity and are stacked, we can always be sure that we can increase the capacity of the ports if necessary without replacing all the hardware and stopping the service.





    By the way, the possibility of using converged ports does not bear any hidden cost in the form of additional licenses (unlike competitors), as well as all other functionality of this switch. It's simple - when buying a device, the client receives the entire list of features embedded by the developers in the network operating system. HP is trying to follow this principle in most of its other network solutions.

    Returning to the interesting features of this device, it is worth mentioning the now actively mastered VXLAN technology. About a year ago, the 5930 32QSFP + Switch (one that is not modular) was the first device in the HP line with VXLAN hardware support (this requires a specialized chipset). Further development of this line has expanded the number of compact access devices supporting this technology, i.e. 2 new modular switches support VXLAN VTEP and can terminate up to 4K tunnels. Today it is difficult to imagine the work of a modern data center without using various techniques for virtualization of computing resources. The trend towards maximum virtualization and the rapid growth of hosts within the average data center has led to that traditional L2-level traffic structuring models (such as VLANs) have become unsuitable due to the low scalability. This, in turn, was the impetus for the emergence of technologies such as VXLAN or NVGRE. They, of course, have their pluses and minuses, but, nevertheless, the development trends of the industry and the market show that the need for such technologies is significant. You can read more about VXLANhere .



    Thus, we organically fit into the structures of overlay networks, allowing the interaction of physical and virtual media.

    The next noteworthy EVB / VEPA technology. Briefly can be found here. And in a nutshell, the protocol is based on the open IEEE 802.1Qbg standard, which allows network administrators to better see and understand what is happening inside physical servers in the process of exchanging data between virtual machines. Since network traffic between two virtual hosts within one physical server is nothing more than moving data from one area of ​​RAM to another, the ability to apply some policies and carry out advanced monitoring is quite difficult. Of course, there are quite a lot of new products on the market that implement this or that functionality (for example, virtual firewalls or traffic analyzers), however, many manufacturers, in particular HP, believe that servers should be involved in computing, and traffic processing should be left network devices. So, EVB / VEPA allows us to “pull” traffic between virtual hosts into an external network, apply any policies and rules (be it QoS, access lists, DPI, or something else), and then return this traffic back to the server and direct it to the original destination host. Thus, we can unload the resources of the servers associated with the application of policies to network data, making it completely transparent to all participants in this process.



    Another technology worth mentioning that is contained in the devices in question is TRILL. A brief overview of this protocol, as well as other modern L2 routing protocols, as well as development trends in this area can be found in our HP FlexFabric Reference Architecture: Data Center Trends. In addition to TRILL, the switches also support the older Shortest Path Bridging IEEE 802.1aq protocol. Both protocols support up to 8 ECMP routes (Equal Cost Multipath), which in principle is more than enough for data centers of all sizes. Thus, we get rid of idle links, if we use the good old xSTP, uniformly load the available resources and ensure stable and stable operation of the network as a whole in case of failure of one or several paths of traffic direction. The convergence rate is again significantly higher than traditional L2 level technologies, which allows us to minimize or even eliminate packet loss in the event of a rebuild of the route tree.



    With this solution, we hope to take another step to expand and strengthen our product portfolio for data center networks and campus networks, to allow customers to more flexibly make their choice when building truly converged networks.

    Also popular now: