Netronome Systems Incorporated

Rolf Neugebauer

Gavin J Stark

Espen Skoglund

Francois Henri Theron

Nicolaas J Viljoen

Niel Viljoen

A Network Interface Device (NID) of a web hosting server implements multiple virtual NIDs. For each virtual NID there is a block in a memory of a transactional memory on the NID. This block stores configuration information that configures the corresponding virtual NID. The NID also has a single managing processor that monitors configuration of the plurality of virtual NIDs. If there is a write into the memory space where the configuration information for the virtual NIDs is stored, then the transactional memory detects this write and in response sends an alert to the managing processor. The size and location of the memory space in the memory for which write alerts are to be generated is programmable. The content and destination of the alert is also programmable.

Network interface device that alerts a monitoring processor if configuration of a virtual NID is changed

A Network Interface Device (NID) of a web hosting server implements multiple virtual NIDs. A virtual NID is configured by configuration information in an appropriate one of a set of smaller blocks in a high-speed memory on the NID. There is a smaller block for each virtual NID. A virtual machine on the host can configure its virtual NID by writing configuration information into a larger block in PCIe address space. Circuitry on the NID detects that the PCIe write is into address space occupied by the larger blocks. If the write is into this space, then address translation circuitry converts the PCIe address into a smaller address that maps to the appropriate one of the smaller blocks associated with the virtual NID to be configured. If the PCIe write is detected not to be an access of a larger block, then the NID does not perform the address translation.

Network interface device that maps host bus writes of configuration information for virtual NIDs into a small transactional memory

A source code symbol can be declared to have a scope level indicative of a level in a hierarchy of scope levels, where the scope level indicates a circuit level or a sub-circuit level in the hierarchy. A novel instruction to the linker can define the symbol to be of a desired scope level. Location information indicates where different amounts of the object code are to be loaded into a system. A novel linker program uses the location information, along with the scope level information of the symbol, to uniquify instances of the symbol if necessary to resolve name collisions of symbols having the same scope. After the symbol uniquification step, the linker performs resource allocation. A resource instance is allocated to each symbol. The linker then replaces each instance of the symbol in the object code with the address of the allocated resource instance, thereby generating executable code.

Resource allocation with hierarchical scope

A transactional memory receives a command, where the command includes an address and a novel DAT (Do Address Translation) bit. If the DAT bit is set and if the transactional memory is enabled to do address translations and if the command is for an access (read or write) of a memory of the transactional memory, then the transactional memory performs an address translation operation on the address of the command. Parameters of the address translation are programmable and are set up before the command is received. In one configuration, certain bits of the incoming address are deleted, and other bits are shifted in bit position, and a base address is ORed in, and a padding bit is added, thereby generating the translated address. The resulting translated address is then used to access the memory of the transactional memory to carry out the command.

Transactional memory that performs a programmable address translation if a DAT bit in a transactional memory write command is set

A flow key is determined from an incoming packet. Two hash values A and B are then generated from the flow key. Hash value A is an index into a hash table to identify a hash bucket. Multiple simultaneous CAM lookup operations are performed on fields of the bucket to determine which ones of the fields store hash value B. For each populated field there is a corresponding entry in a key table and in other tables. The key table entry corresponding to each field that stores hash value B is checked to determine if that key table entry stores the original flow key. When the key table entry that stores the original flow key is identified, then the corresponding entries in the other tables are determined to be a 'lookup output information value'. This value indicates how the packet is to be handled/forwarded by the network appliance.

Flow key lookup involving multiple simultaneous cam operations to identify hash values in a hash bucket

A novel allocate instruction and a novel API call are received onto a compiler. The allocate instruction includes a symbol that identifies a non-memory resource instance. The API call is a call to perform an operation on a non-memory resource instance, where the particular instance is indicated by the symbol in the API call. The compiler replaces the API call with a set of API instructions. A linker then allocates a value to be associated with the symbol, where the allocated value is one of a plurality of values, and where each value corresponds to a respective one of the non-memory resource instances. After allocation, the linker generates an amount of executable code, where the API instructions in the code: 1) are for using the allocated value to generate an address of a register in the appropriate non-memory resource instance, and 2) are for accessing the register.

Allocate instruction and API call that contain a sybmol for a non-memory resource

A novel declare instruction can be used in source code to declare a sub-pool of resource instances to be taken from the resource instances of a larger declared pool. Using such declare instructions, a hierarchy of pools and sub-pools can be declared. A novel allocate instruction can then be used in the source code to instruct a novel linker to make resource instance allocations from a desired pool or a desired sub-pool of the hierarchy. After compilation, the declare and allocate instructions appear in the object code. The linker uses the declare and allocate instructions in the object code to set up the hierarchy of pools and to make the indicated allocations of resource instances to symbols. After resource allocation, the linker replaces instances of a symbol in the object code with the address of the allocated resource instance, thereby generating executable code.

Hierarchical resource pools in a linker

A network appliance includes a network processor and several processing units. Packets a flow pair are received onto the network appliance. Without performing deep packet inspection on any packet of the flow pair, the network processor analyzes the flows, estimates therefrom the application protocol used, and determines a predicted future time when the next packet will likely be received. The network processor determines to send the next packet to a selected one of the processing units based in part on the predicted future time. In some cases, the network processor causes a cache of the selected processing unit to be preloaded shortly before the predicted future time. When the next packet is actually received, the packet is directed to the selected processing unit. In this way, packets are directed to processing units within the network appliance based on predicted future packet arrival times without the use of deep packet inspection.

Growing community of inventors

Cambridge, United Kingdom

Rolf Neugebauer