This technology generally relates to traffic dependent direct memory access (DMA) optimization.
Today, software and hardware interact in a rigid way. Network interface controllers (NICs) provide only a single DMA (direct memory access) behavior mechanism, such as deciding how to lay down buffers and interact with the driver. With a single DMA behavior mechanism, upon receiving packets by the NICs, the packets are transmitted to a queue. This transmission of the packets into the queue by the NICs is independent of the contents included in the packet and the flow associated with the packet. However, different types of packets based on their content would have increased efficiency if alternate DMA behavior mechanisms were utilized, such as mechanisms with improved use of CPU cache, CPU, or DRAM.
A method, implemented by a network traffic management system comprising one or more network traffic management apparatuses, server devices or client devices, includes inspecting a plurality of incoming packets to obtain packet header data for each of the incoming packets. The packet header data is filtered using one or more filtering criteria. At least one of a plurality of optimized DMA behavior mechanisms for each of the incoming packets are selected based on associating the filtered header data for each of the incoming packets with stored profile data. The incoming packets are disaggregated based on the corresponding selected one of the optimized DMA behavior mechanisms.
A network traffic management apparatus including memory including programmed instructions stored thereon and one or more processors configured to be capable of executing the stored programmed instructions to inspect a plurality of incoming packets to obtain packet header data for each of the incoming packets. The packet header data is filtered using one or more filtering criteria. At least one of a plurality of optimized DMA behavior mechanisms for each of the incoming packets are selected based on associating the filtered header data for each of the incoming packets with stored profile data. The incoming packets are disaggregated based on the corresponding selected one of the optimized DMA behavior mechanisms.
A non-transitory computer readable medium having stored thereon instructions for including executable code that, when executed by one or more processors, causes the processors to inspect a plurality of incoming packets to obtain packet header data for each of the incoming packets. The packet header data is filtered using one or more filtering criteria. At least one of a plurality of optimized DMA behavior mechanisms for each of the incoming packets are selected based on associating the filtered header data for each of the incoming packets with stored profile data. The incoming packets are disaggregated based on the corresponding selected one of the optimized DMA behavior mechanisms.
A network traffic management system includes one or more traffic management modules, server modules, or client modules, memory comprising programmed instructions stored thereon, and one or more processors configured to be capable of executing the stored programmed instructions to a plurality of incoming packets to obtain packet header data for each of the incoming packets. The packet header data is filtered using one or more filtering criteria. At least one of a plurality of optimized DMA behavior mechanisms for each of the incoming packets are selected based on associating the filtered header data for each of the incoming packets with stored profile data. The incoming packets are disaggregated based on the corresponding selected one of the optimized DMA behavior mechanisms.
This technology has a number of advantages including providing methods, non-transitory computer readable media, network traffic management apparatuses, and network traffic management systems that provide increased efficiency with network load balancing by intelligently processing different types of traffic with a correlated one of a plurality of DMA behavior mechanism. This correlation improves CPU, CPU cache, DRAM or Bus Bandwidth utilization resulting in an improved experience for client devices. As a result, this technology provides optimized utilization of NIC storage to eliminate duplicated data to reduce size of entry tables which reduces costs for utilizing expensive storage devices.
Referring to
incorporates an exemplary network traffic management system 10 is illustrated. The network traffic management system 10 in this example includes a network traffic management apparatus 12 that is coupled to server devices 14(1)-14(n), and client devices 16(1)-16(n) via communication network(s) 18(1) and 18(2), although the network traffic management apparatus 12, server devices 14(1)-14(n), and client devices 16(1)-16(n) may be coupled together via other topologies. The network traffic management system 10 may include other network devices such as one or more routers or switches, for example, which are known in the art and thus will not be described herein. This technology provides a number of advantages including methods, non-transitory computer readable media, network traffic management systems, and network traffic management apparatuses that provide an increased efficiency of network load balancing by intelligently processing different types of traffic with a correlated one of a plurality of DMA behavior mechanism.
In this particular example, the network traffic management apparatus 12, server devices 14(1)-14(n), and client devices 16(1)-16(n) are disclosed in
As one example, the network traffic management apparatus 12, as well as any of its components, models, or applications, can be a module implemented as software executing on one of the server devices 14(1)-14(n), and many other permutations and types of implementations can also be used in other examples. Moreover, any or all of the network traffic management apparatus 12, server devices 14(1)-14(n), and client devices 16(1)-16(n), can be implemented, and may be referred to herein, as a module.
Referring to
The processor(s) 20 of the network traffic management apparatus 12 may execute programmed instructions stored in the memory 22 of the network traffic management apparatus 12 for any number of the functions identified above. The processor(s) 20 of the network traffic management apparatus 12 may include one or more central processing units (CPUs) or general purpose processors with one or more processing cores, for example, although other types of processor(s) can also be used.
The memory 22 of the network traffic management apparatus 12 stores these programmed instructions for one or more aspects of the present technology as described and illustrated herein, although some or all of the programmed instructions could be stored elsewhere. A variety of different types of memory storage devices, such as random access memory (RAM), read only memory (ROM), hard disk, solid state drives, flash memory, or other computer readable medium which is read from and written to by a magnetic, optical, or other reading and writing system that is coupled to the processor(s) 20, can be used for the memory 22.
Accordingly, the memory 22 of the network traffic management apparatus 12 can store one or more applications that can include computer executable instructions that, when executed by the network traffic management apparatus 12, cause the network traffic management apparatus 12 to perform actions, such as to transmit, receive, or otherwise process messages, for example, and to perform other actions described and illustrated below with reference to
Even further, the application(s) may be operative in a cloud-based computing environment. The application(s) can be executed within or as virtual machine(s) or virtual server(s) that may be managed in a cloud-based computing environment. Also, the application(s), and even the network traffic management apparatus 12 itself, may be located in virtual server(s) running in a cloud-based computing environment rather than being tied to one or more specific physical network computing devices. Also, the application(s) may be running in one or more virtual machines (VMs) executing on the network traffic management apparatus 12. Additionally, in one or more examples of this technology, virtual machine(s) running on the network traffic management apparatus 12 may be managed or supervised by a hypervisor.
In this particular example, the memory 22 of the network traffic management apparatus 12 may include a filtering criteria data storage 28, data store 32, profile data storage 30, although the memory 22 can include other policies, modules, databases, or applications, for example.
The filtering criteria stored in the filtering criteria data storage 28 may include by way of example, virtual local area network (VLAN) data criteria, listening data criteria, pool members data criteria, and self-internet protocol (IP) criteria, although other types and numbers of criteria may be used.
The profile data storage 30 may include profile data, such as Layer-4 Proxy Profile (L4 proxy profile), Partial Layer-7 proxy profile (Partial L7 proxy profile), Full Layer-7 proxy profile (Full L7 proxy profile) and associated rules for selecting one or more DMA behavior mechanisms.
The L4 proxy profile includes one or more policies used to make a determination about the particular processing of each packet. With the L4 proxy profile, processing is on a packet by packet basis and acknowledgements are not required which reduces overhead.
The Partial L7 proxy profile in the profile data storage 30 includes one or more policies for processing packets associated with a flow, such as HTTP packets by way of example. With the Partial L7 proxy profile, packets are processed on a per-flow-basis instead of packet by packet basis and then allocated to a particular one of the server devices 14(1)-14(n) based on one of plurality identified types of flow.
The Full L7 proxy profile in the profile data storage 30 also includes one or more policies for processing packets associated with a flow, such as HTTP packets by way of example. With the Full L7 proxy profile, all the packets associated with a flow are collected and then processed. By way of example, this processing may comprise examining the full stream of traffic for virus or attack signatures. By way of another example, this processing may include examining an HTTP request's URL for special processing such as compression, although other types of processing may be performed.
The stored associated rules are used to select one or more optimized DMA behavior mechanisms. By way of example only, one of the rules for selecting one of the DMA behavior mechanisms may comprise determining when a packet is processed using a L4 proxy profile. Upon determining the packet is processed using the L4 proxy profile, another one of the rules may be used to determine whether the Header DMA mechanism or the Contiguous Ring DMA mechanism is selected for processing the packet. In other examples, the rules may comprise determining whether a flow is being processed by either the Partial L7 proxy profile or the Full L7 proxy profile. Upon determining the packet is processed using either the Partial L7 proxy profile or the Full L7 proxy profile, then one of a plurality of DMA mechanisms may be selected for processing the packets in the flow.
The data store 32 may store data from multiple data sources which may be utilized for DMA selection and may include a plurality of data entry tables. By way of a further example, the data store 32 is illustrated in
Referring to
By way of example only, the communication network(s) 18(1) and 18(2) can include local area network(s) (LAN(s)) or wide area network(s) (WAN(s)), and can use TCP/IP over Ethernet and industry-standard protocols, although other types or numbers of protocols or communication networks can be used. The communication network(s) 18(1) and 18(2) in this example can employ any suitable interface mechanisms and network communication technologies including, for example, teletraffic in any suitable form (e.g., voice, modem, and the like), Public Switched Telephone Network (PSTNs), Ethernet-based Packet Data Networks (PDNs), combinations thereof, and the like.
Referring to
While the network traffic management apparatus 12 is illustrated in this example as including a single device, the network traffic management apparatus 12 in other examples can include a plurality of devices or blades each having one or more processors (each processor with one or more processing cores) that implement one or more steps of this technology. In these examples, one or more of the devices can have a dedicated communication interface or memory. Alternatively, one or more of the devices can utilize the memory, communication interface, or other hardware or software components of one or more other devices included in the network traffic management apparatus 12.
Additionally, one or more of the devices that together comprise the network traffic management apparatus 12 in other examples can be stand-alone devices or integrated with one or more other devices or apparatuses, such as one or more of the server devices 14(1)-14(n), for example. Moreover, one or more of the devices of the network traffic management apparatus 12 in these examples can be in a same or a different communication network including one or more public, private, or cloud networks, for example.
Each of the server devices 14(1)-14(n) of the network traffic management system 10 in this example includes one or more processors, a memory, and a network interface controller, which are coupled together by a bus or other communication link, although other numbers and/or types of network devices could be used. The server devices 14(1)-14(n) in this example can include application servers, database servers, access control servers, or encryption servers, for example, that exchange communications along communication paths expected based on application logic in order to facilitate interactions with an application by users of the client devices 16(1)-16(n).
Accordingly, in some examples, one or more of the server devices 14(1)-14(n) process login and other requests received from the client devices 16(1)-16(n) via the communication network(s) 18(1) and 18(2) according to the HTTP-based application RFC protocol, for example. A web application may be operating on one or more of the server devices 14(1)-14(n) and transmitting data (e.g., files or web pages) to the client devices 16(1)-16(n) (e.g., via the network traffic management apparatus 12) in response to requests from the client devices 16(1)-16(n). The server devices 14(1)-14(n) may be hardware or software or may represent a system with multiple servers in a pool, which may include internal or external networks.
Although the server devices 14(1)-14(n) are illustrated as single devices, one or more actions of each of the server devices 14(1)-14(n) may be distributed across one or more distinct network computing devices that together comprise one or more of the server devices 14(1)-14(n). Moreover, the server devices 14(1)-14(n) are not limited to a particular configuration. Thus, the server devices 14(1)-14(n) may contain network computing devices that operate using a master/slave approach, whereby one of the network computing devices of the server devices 14(1)-14(n) operate to manage or otherwise coordinate operations of the other network computing devices. The server devices 14(1)-14(n) may operate as a plurality of network computing devices within a cluster architecture, a peer-to peer architecture, virtual machines, or within a cloud architecture, for example.
Thus, the technology disclosed herein is not to be construed as being limited to a single environment and other configurations and architectures are also envisaged. For example, one or more of the server devices 14(1)-14(n) can operate within the network traffic management apparatus 12 itself rather than as a stand-alone server device communicating with the network traffic management apparatus 12 via communication network(s) 18(2). In this example, the one or more of the server devices 14(1)-14(n) operate within the memory 22 of the network traffic management apparatus 12.
The client devices 16(1)-16(n) of the network traffic management system 10 in this example include any type of computing device that can exchange network data, such as mobile, desktop, laptop, or tablet computing devices, virtual machines (including cloud-based computers), or the like. Each of the client devices 16(1)-16(n) in this example includes a processor, a memory, and a communication interface, which are coupled together by a bus or other communication link (not illustrated), although other numbers or types of components could also be used.
The client devices 16(1)-16(n) may run interface applications, such as standard web browsers or standalone client applications, which may provide an interface to make requests for, and receive content stored on, one or more of the server devices 14(1)-14(n) via the communication network(s) 18(1) and 18(2). The client devices 16(1)-16(n) may further include a display device, such as a display screen or touchscreen, or an input device, such as a keyboard for example (not illustrated). Additionally, one or more of the client devices 16(1)-16(n) can be configured to execute software code (e.g., JavaScript code within a web browser) in order to log client-side data and provide the logged data to the network traffic management apparatus 12, as described and illustrated in more detail later.
Although the exemplary network traffic management system 10 with the network traffic management apparatus 12, server devices 14(1)-14(n), client devices 16(1)-16(n), and communication network(s) 18(1) and 18(2) are described and illustrated herein, other types or numbers of systems, devices, components, or elements in other topologies can be used. It is to be understood that the systems of the examples described herein are for exemplary purposes, as many variations of the specific hardware and software used to implement the examples are possible, as will be appreciated by those skilled in the relevant art(s).
One or more of the components depicted in the network security system 10, such as the network traffic management apparatus 12, server devices 14(1)-14(n), or client devices 16(1)-16(n), for example, may be configured to operate as virtual instances on the same physical machine. In other words, one or more of the network traffic management apparatus 12, server devices 14(1)-14(n), or client devices 16(1)-16(n) may operate on the same physical device rather than as separate devices communicating through communication network(s) 18(1) or 18(2). Additionally, there may be more or fewer network traffic management apparatuses, client devices, or server devices than illustrated in
In addition, two or more computing systems or devices can be substituted for any one of the systems or devices in any example. Accordingly, principles and advantages of distributed processing, such as redundancy and replication also can be implemented, as desired, to increase the robustness and performance of the devices and systems of the examples. The examples may also be implemented on computer system(s) that extend across any suitable network using any suitable interface mechanisms and traffic technologies, including by way of example only, wireless traffic networks, cellular traffic networks, Packet Data Networks (PDNs), the Internet, intranets, and combinations thereof.
The examples may also be embodied as one or more non-transitory computer readable media having instructions stored thereon, such as in the memory 22, for one or more aspects of the present technology, as described and illustrated by way of the examples herein. The instructions in some examples include executable code that, when executed by one or more processors, such as the processor(s) 20, cause the processors to carry out steps necessary to implement the methods of the examples of this technology that are described and illustrated herein.
An exemplary method of traffic dependent DMA behavior will now be described with reference to
In step 510, the network traffic management apparatus 12 performs an inspection of the packet header data in each of the plurality of packets to determine source address data and destination address data from the packet header data, although other types of data in each of the plurality of packets could be inspected and determined.
In step 520, the network traffic management apparatus 12 filters the determined source address data and destination address data from the packet header data for each packet using one or more filtering criteria stored in the filtering criteria data storage 28 to obtain filtered data, although other data may be filtered from the packet header data. The stored filtering criteria may include by way of example, virtual local area network (VLAN) data criteria, listening data criteria, pool members data criteria, self-internet protocol (IP) criteria and/or tenant account data described further in detail below. Examples of this filtering using the virtual local area network (VLAN) data criteria are described below with reference to
In this example, when the received packet is originating from a client request, and the packet is received over, for example, a VLAN 1, the packet header data is inspected to obtain a destination address data, such as a destination IP address of 10.0.0.1:80 which is a virtual server internet protocol (IP) address. The network traffic management apparatus 12 may map this virtual server IP address to stored profile data associated with for example an L4 proxy profile. This process of mapping the virtual server IP address to the profile data is considered filtering with VLAN data criteria.
In another example, when the received packet is originating from a server response and the packet is received over, for example a VLAN 2, the packet header is inspected to obtain a source address data, such as a source IP address and the port number. Since this is a response coming in from the server for which earlier load balancing decisions had been made based on the earlier client request packet header data which was associated with for example, the L4 proxy profile, this packet that is associated with the server response will also be associated with the L4 proxy profile associated with the client request by the network traffic management apparatus. Since the L4 proxy profile in this example is associated with, for example the contiguous ring DMA behavior mechanism, then the contiguous ring DMA behavior mechanism is selected to service this packet associated with the server response. This process of mapping the server response to the profile data based on listening for the client request profile is considered filtering with listening data criteria. Although two examples of filtering are provided above with reference to
By way of another example, when the network traffic management system 10 is providing TCP stack load balancing with URL matching with TLS decryption, then the network traffic management apparatus 12 may filter from the packet header data source IP which may be matched to identify packets in received traffic for load balancing.
In another example, when the network traffic management system 10 is providing network address translation (NAT'ing) behavior, then the network traffic management apparatus 12 may filter from the packet header data in received packets the local host's IP address (self-IP) in the destination IP to be used in NAT'ing behaviour. This example represents traffic where only the headers need be examined to provide the translation service.
In yet another example, a security engine in or associated with the network traffic management apparatus 12 may have determined that a specific IP time to live field value has been associated with hacker activity in traffic. Accordingly, in this example, the network traffic management apparatus 12 may filter packets in traffic matching this criteria and would send those matching packets to a full L7 proxy for deep inspection.
In step 530, the network traffic management apparatus 12 may select one or more optimized DMA behavior mechanisms from a plurality of optimized DMA behavior mechanisms for each of the packets based on the filtered packet header data. For example, the filtering which mapped the packet header data to the L4 proxy profile can now be used to select either a header behavior mechanism or contiguous ring mechanism for the packet based on the association with the L4 proxy profile. In other examples, the filtering associates the packets with other proxy profiles which are correlated to other DMA behavior mechanisms. In other examples, the filtering may select DMA behavior based on a comparison of packet length against MTU. A NAT'ing application that also employs IP fragmentation may choose to direct packets for fragmentation through a contiguous ring instead of header mechanism. In other examples, the ingress physical port may also be used in the filtering process. In a URL examination example, packets arriving from a client warrant examination and thus require a contiguous ring. Packet from servers will only require header mechanism. If the ingress physical port can be used to distinguish client from server, then the ingress physical port will be used in the filtering mechanism to select DMA behavior.
By way of example, other exemplary types of DMA behavior mechanisms which may be selected may include the scatter/gather mechanism, the contiguous ring mechanism, the dis-contiguous ring mechanism and the header behavior mechanism, although other types and/or numbers of mechanisms may be used.
With the scatter/gather mechanism, a single procedure call sequentially reads data from multiple buffers and writes it to a single data stream, or reads data from a data stream and writes it to multiple buffers. The buffers are given in a vector of buffers, and the packets in this scatter/gather mechanism are long lived. The scatter/gather mechanism refers to the process of gathering data from, or scattering data into, the given set of buffers. A scatter/gather I/O can operate synchronously or asynchronously and may be used for efficiency and convenience.
With the contiguous ring mechanism, upon receiving the packets from the client, a buffer holds the packets for a pre-determined period of time before the packets are transmitted to the server. With this contiguous ring mechanism, the packets arrive inline and are processed in a standard manner upon arrival. The size of the contiguous ring dictates the amount of data that can be stored and a fixed maximum speed of data transfer provides a maximum time in which the incoming packet must be processed.
The dis-contiguous ring mechanism is an optimized form of the contiguous ring mechanism. The dis-contiguous ring mechanism resembles the contiguous ring mechanism, however with the dis-contiguous ring mechanism when the data arrives a determination is made to identify which of the arrived data requires a longer processing time than a threshold. Upon the determining that data requires a longer processing time, that data is skipped which may result in holes or gaps in the buffer for this skipped data.
With the header behavior mechanism, upon receiving the packets the packet header data, payload data including predictably located values may be inspected and based on the inspected data the packets are then forwarded.
In step 540, the network traffic management apparatus 12 disaggregates each of the plurality of incoming packets based on the corresponding selected one of the optimized DMA behavior mechanisms to the one or more queues, wherein the queues are a data structure for processing packets as illustrated by way of example back in
Accordingly, as illustrated by way of the examples herein, an increased efficiency with network load balancing is provided by this technology intelligently processing different types of traffic with an associated DMA behavior mechanism which improves CPU, CPU cache, DRAM or Bus Bandwidth utilization resulting in improved experience for users of client devices. As a result, this technology provides advantages of optimized utilization of NIC storage to eliminate duplicated data to reduce size of entry tables which reduces costs for utilizing expensive storage devices.
Having thus described the basic concept of the invention, it will be rather apparent to those skilled in the art that the foregoing detailed disclosure is intended to be presented by way of example only, and is not limiting. Various alterations, improvements, and modifications will occur and are intended to those skilled in the art, though not expressly stated herein. These alterations, improvements, and modifications are intended to be suggested hereby, and are within the spirit and scope of the invention. Additionally, the recited order of processing elements or sequences, or the use of numbers, letters, or other designations therefore, is not intended to limit the claimed processes to any order except as may be specified in the claims. Accordingly, the invention is limited only by the following claims and equivalents thereto.
This application claims the benefit of U.S. Provisional Patent Application Ser. No. 62/642,725 filed Mar. 14, 2018, which is hereby incorporated by reference in its entirety.
Number | Name | Date | Kind |
---|---|---|---|
4914650 | Sriram | Apr 1990 | A |
5388237 | Sodos | Feb 1995 | A |
5477541 | White et al. | Dec 1995 | A |
5588128 | Hicok et al. | Dec 1996 | A |
5699361 | Ding et al. | Dec 1997 | A |
5742765 | Wong et al. | Apr 1998 | A |
5761534 | Lundberg et al. | Jun 1998 | A |
5797033 | Ecclesine | Aug 1998 | A |
5809334 | Galdun et al. | Sep 1998 | A |
5809560 | Schneider | Sep 1998 | A |
5828835 | Isfeld et al. | Oct 1998 | A |
5940838 | Schmuck et al. | Aug 1999 | A |
5941988 | Bhagwat et al. | Aug 1999 | A |
5948080 | Baker | Sep 1999 | A |
6026090 | Benson et al. | Feb 2000 | A |
6026443 | Oskouy et al. | Feb 2000 | A |
6055619 | North | Apr 2000 | A |
6070219 | McAlpine et al. | May 2000 | A |
6070230 | Capps | May 2000 | A |
6115802 | Tock et al. | Sep 2000 | A |
6347337 | Shah et al. | Feb 2002 | B1 |
6347347 | Brown et al. | Feb 2002 | B1 |
6385624 | Shinkai | May 2002 | B1 |
6388989 | Malhortra | May 2002 | B1 |
6529508 | Li et al. | Mar 2003 | B1 |
6574220 | Petty | Jun 2003 | B1 |
6647438 | Connor | Nov 2003 | B1 |
6700871 | Harper et al. | Mar 2004 | B1 |
6748457 | Fallon et al. | Jun 2004 | B2 |
6781990 | Puri et al. | Aug 2004 | B1 |
6785236 | Lo et al. | Aug 2004 | B1 |
6820133 | Grove et al. | Nov 2004 | B1 |
6904040 | Salapura et al. | Apr 2005 | B2 |
6915404 | Desai et al. | Jul 2005 | B1 |
6934776 | Connor et al. | Aug 2005 | B2 |
6999457 | Shinohara | Feb 2006 | B2 |
7046628 | Luhmann et al. | May 2006 | B2 |
7065630 | Ledebohm et al. | Jun 2006 | B1 |
7107348 | Shimada et al. | Sep 2006 | B2 |
7117308 | Mitten et al. | Oct 2006 | B1 |
7120753 | Accapadi et al. | Oct 2006 | B2 |
7124196 | Hooper | Oct 2006 | B2 |
7142540 | Hendel et al. | Nov 2006 | B2 |
7164678 | Connor | Jan 2007 | B2 |
7174393 | Boucher et al. | Feb 2007 | B2 |
7181457 | Reinauer et al. | Feb 2007 | B2 |
7203815 | Haswell | Apr 2007 | B2 |
7236491 | Tsao et al. | Jun 2007 | B2 |
7272150 | Bly et al. | Sep 2007 | B2 |
7281030 | Davis | Oct 2007 | B1 |
7324525 | Fuhs et al. | Jan 2008 | B2 |
7327674 | Eberle et al. | Feb 2008 | B2 |
7349405 | Deforche | Mar 2008 | B2 |
7353326 | Cho et al. | Apr 2008 | B2 |
7355977 | Li | Apr 2008 | B1 |
7359321 | Sindhu et al. | Apr 2008 | B1 |
7376772 | Fallon | May 2008 | B2 |
7403542 | Thompson | Jul 2008 | B1 |
7411957 | Stacy et al. | Aug 2008 | B2 |
7415034 | Muller et al. | Aug 2008 | B2 |
7420931 | Nanda et al. | Sep 2008 | B2 |
7457313 | Patrick | Nov 2008 | B2 |
7475122 | Azpitarte | Jan 2009 | B2 |
7478186 | Onufryk et al. | Jan 2009 | B1 |
7493398 | Bush | Feb 2009 | B2 |
7496689 | Sharp et al. | Feb 2009 | B2 |
7496695 | Go et al. | Feb 2009 | B2 |
7500028 | Yamagishi | Mar 2009 | B2 |
7512078 | Swain | Mar 2009 | B2 |
7512721 | Olson | Mar 2009 | B1 |
7533197 | Leonard et al. | May 2009 | B2 |
7552232 | Helmer, Jr. et al. | Jun 2009 | B2 |
7558910 | Alverson et al. | Jul 2009 | B2 |
7571299 | Loeb | Aug 2009 | B2 |
7590753 | Wolde et al. | Sep 2009 | B2 |
7620046 | Ronciak et al. | Nov 2009 | B2 |
7620071 | Makineni et al. | Nov 2009 | B2 |
7621162 | Bartky | Nov 2009 | B2 |
7647416 | Chiang et al. | Jan 2010 | B2 |
7649882 | Stiliadis | Jan 2010 | B2 |
7657659 | Lambeth et al. | Feb 2010 | B1 |
7660916 | Moskalev et al. | Feb 2010 | B2 |
7668727 | Mitchell et al. | Feb 2010 | B2 |
7668851 | Triplett | Feb 2010 | B2 |
7710989 | Chew | May 2010 | B2 |
7729239 | Aronov et al. | Jun 2010 | B1 |
7734809 | Joshi et al. | Jun 2010 | B2 |
7735099 | Micalizzi, Jr. | Jun 2010 | B1 |
7742412 | Medina | Jun 2010 | B1 |
7784093 | Deng et al. | Aug 2010 | B2 |
7813277 | Okholm et al. | Oct 2010 | B2 |
7826487 | Mukerji et al. | Nov 2010 | B1 |
7835391 | Chateau et al. | Nov 2010 | B2 |
7840841 | Huang et al. | Nov 2010 | B2 |
7877524 | Annem et al. | Jan 2011 | B1 |
7916728 | Mimms | Mar 2011 | B1 |
7929433 | Husak et al. | Apr 2011 | B2 |
7930444 | Shasha et al. | Apr 2011 | B2 |
7936772 | Kashyap | May 2011 | B2 |
7975025 | Szabo et al. | Jul 2011 | B1 |
7991918 | Jha et al. | Aug 2011 | B2 |
7996569 | Aloni et al. | Aug 2011 | B2 |
8001430 | Shasha et al. | Aug 2011 | B2 |
8006016 | Muller et al. | Aug 2011 | B2 |
8077620 | Solomon et al. | Dec 2011 | B2 |
8099528 | Millet et al. | Jan 2012 | B2 |
8103809 | Michels et al. | Jan 2012 | B1 |
8112491 | Michels et al. | Feb 2012 | B1 |
8112594 | Giacomoni et al. | Feb 2012 | B2 |
8233380 | Subramanian et al. | Jul 2012 | B2 |
8274976 | Aloni | Sep 2012 | B2 |
8279865 | Giacomoni et al. | Oct 2012 | B2 |
8306036 | Bollay et al. | Nov 2012 | B1 |
8346993 | Michels et al. | Jan 2013 | B2 |
8417842 | Vu | Apr 2013 | B2 |
8447884 | Baumann | May 2013 | B1 |
8447897 | Xu et al. | May 2013 | B2 |
8448234 | Mondaeev et al. | May 2013 | B2 |
8630173 | Sundar | Jan 2014 | B2 |
8762595 | Muller | Jun 2014 | B1 |
8799403 | Chan et al. | Aug 2014 | B2 |
8848715 | Izenberg et al. | Sep 2014 | B2 |
8880632 | Michels et al. | Nov 2014 | B1 |
8880696 | Michels et al. | Nov 2014 | B1 |
8984178 | Michels et al. | Mar 2015 | B2 |
9032113 | Conroy et al. | May 2015 | B2 |
9036822 | Jain et al. | May 2015 | B1 |
9152483 | Michels et al. | Oct 2015 | B2 |
9270602 | Michels et al. | Feb 2016 | B1 |
9313047 | Michels et al. | Apr 2016 | B2 |
10177795 | Frishman | Jan 2019 | B1 |
20010038629 | Shinohara | Nov 2001 | A1 |
20010042200 | Lamberton et al. | Nov 2001 | A1 |
20010043614 | Viswanadham | Nov 2001 | A1 |
20020133586 | Shanklin | Sep 2002 | A1 |
20020143955 | Shimada et al. | Oct 2002 | A1 |
20020156927 | Boucher et al. | Oct 2002 | A1 |
20030067930 | Salapura | Apr 2003 | A1 |
20030204636 | Greenblat et al. | Oct 2003 | A1 |
20040013117 | Hendel et al. | Jan 2004 | A1 |
20040032830 | Bly et al. | Feb 2004 | A1 |
20040062245 | Sharp et al. | Apr 2004 | A1 |
20040098538 | Horn et al. | May 2004 | A1 |
20040202161 | Stachura et al. | Oct 2004 | A1 |
20040249881 | Jha et al. | Dec 2004 | A1 |
20040249948 | Sethi et al. | Dec 2004 | A1 |
20040267897 | Hill et al. | Dec 2004 | A1 |
20050007991 | Ton et al. | Jan 2005 | A1 |
20050050364 | Feng | Mar 2005 | A1 |
20050063307 | Samuels et al. | Mar 2005 | A1 |
20050083952 | Swain | Apr 2005 | A1 |
20050091390 | Helmer et al. | Apr 2005 | A1 |
20050114559 | Miller | May 2005 | A1 |
20050141427 | Bartky | Jun 2005 | A1 |
20050144394 | Komaria et al. | Jun 2005 | A1 |
20050154825 | Fair | Jul 2005 | A1 |
20050175014 | Patrick | Aug 2005 | A1 |
20050193164 | Royer | Sep 2005 | A1 |
20050213570 | Stacy et al. | Sep 2005 | A1 |
20050226234 | Sano et al. | Oct 2005 | A1 |
20060007928 | Sangillo | Jan 2006 | A1 |
20060015618 | Freimuth et al. | Jan 2006 | A1 |
20060067349 | Ronciak et al. | Mar 2006 | A1 |
20060104303 | Makineni et al. | May 2006 | A1 |
20060174324 | Zur et al. | Aug 2006 | A1 |
20060221832 | Muller et al. | Oct 2006 | A1 |
20060221835 | Sweeney | Oct 2006 | A1 |
20060221990 | Muller | Oct 2006 | A1 |
20060224820 | Cho et al. | Oct 2006 | A1 |
20060235996 | Wolde et al. | Oct 2006 | A1 |
20060271740 | Mark et al. | Nov 2006 | A1 |
20060288128 | Moskalev et al. | Dec 2006 | A1 |
20070005904 | Lemoal et al. | Jan 2007 | A1 |
20070073915 | Go | Mar 2007 | A1 |
20070094452 | Fachan | Apr 2007 | A1 |
20070106849 | Moore et al. | May 2007 | A1 |
20070162619 | Aloni et al. | Jul 2007 | A1 |
20080040538 | Matsuzawa et al. | Feb 2008 | A1 |
20080126509 | Subramanian et al. | May 2008 | A1 |
20080184248 | Barua et al. | Jul 2008 | A1 |
20080201772 | Mondaeev et al. | Aug 2008 | A1 |
20080219159 | Chateau et al. | Sep 2008 | A1 |
20080219279 | Chew | Sep 2008 | A1 |
20090003204 | Okholm et al. | Jan 2009 | A1 |
20090007266 | Wu et al. | Jan 2009 | A1 |
20090016217 | Kashyap | Jan 2009 | A1 |
20090089619 | Huang et al. | Apr 2009 | A1 |
20090106470 | Sharma | Apr 2009 | A1 |
20090138420 | Swift et al. | May 2009 | A1 |
20090144130 | Grouf et al. | Jun 2009 | A1 |
20090154459 | Husak et al. | Jun 2009 | A1 |
20090222598 | Hayden | Sep 2009 | A1 |
20090248911 | Conroy et al. | Oct 2009 | A1 |
20090279559 | Wong et al. | Nov 2009 | A1 |
20100023595 | McMillan | Jan 2010 | A1 |
20100082849 | Millet et al. | Apr 2010 | A1 |
20100085875 | Solomon et al. | Apr 2010 | A1 |
20100094945 | Chan et al. | Apr 2010 | A1 |
20100174824 | Aloni | Jul 2010 | A1 |
20110110380 | Muller et al. | May 2011 | A1 |
20110134915 | Srinivasan | Jun 2011 | A1 |
20110228781 | Izenberg et al. | Sep 2011 | A1 |
20110258337 | Wang | Oct 2011 | A1 |
20110307663 | Kultursay | Dec 2011 | A1 |
20120191800 | Michels et al. | Jul 2012 | A1 |
20120195192 | Matthews | Aug 2012 | A1 |
20130166793 | Shahar | Jun 2013 | A1 |
20130250777 | Ziegler | Sep 2013 | A1 |
20140032695 | Michels et al. | Jan 2014 | A1 |
20140185442 | Newman et al. | Jul 2014 | A1 |
20140301207 | Durand et al. | Oct 2014 | A1 |
20170235702 | Horie | Aug 2017 | A1 |
20180322913 | Friedman | Nov 2018 | A1 |
20190163441 | Hagspiel | May 2019 | A1 |
20190392297 | Lau | Dec 2019 | A1 |
20210152659 | Cai | May 2021 | A1 |
Number | Date | Country |
---|---|---|
0803819 | Oct 1997 | EP |
1813084 | Aug 2007 | EP |
WO 2004079930 | Sep 2004 | WO |
WO 2006055494 | May 2006 | WO |
WO 2009158680 | Dec 2009 | WO |
Entry |
---|
“Cavium Networks Product Selector Guide,” Single & Multi-Core MIPS Processors, Security Processors and Accelerator Boards, Cavium Networks, pp. 1-44, Spring 2008. |
“Comtech AHA Announces 3.0 Gbps GZIP Compression/Decompression Accelerator, AHA362-PCIX offers high-speed GZIP compression and decompression,” News Release, Comtech AHA Corporation, Moscow, ID, pp. 1-2, Apr. 20, 2005. |
“Comtech AHA Announces GZIP Compression and Decompression IC Offers the highest speed and compression ratio performance in hardware on the market,” News Release, Comtech AHA Corporation, Moscow, ID, pp. 1-2, Jun. 26, 2007. |
“Gigabit Ethernet/PCI Network Interface Card; Host/NIC Software Interface Definition,” Revision 12.4.13, P/N 020001, Alteon WebSystems, Inc., pp. 1-80, Jul. 1999. |
“Memory Mapping and DMA,” Linux Device Drivers, Third Edition, Chapter 15, pp. 412-463, Jan. 21, 2005. |
“NITROX™ XL Security Acceleration Modules, PCI 3V or 3V/5V-Universal Boards for SSL and IPSec,” Cavium Networks, 1 pp, 2002. |
“PCI, PCI-X,” Cavium Networks, Product Sheet, 1 pp, last retrieved Oct. 24, 2008. |
“Plan 9 Kernel History: Overview,” Lucent Technologies, pp. 1-16, last accessed Oct. 22, 2007. |
Agrawala, Ashok K., “Operating Systems,” Operating System Concepts, pp. 1-24, 2004. |
“Layer 4/7 Switching and Other Custom IP Traffic Processing Using the NEPPI API,” Bell Laboratories, pp. 1-11, 1999. |
“Direct Memory Access (DMA) and Interrupt Handling,” EventHelix.com, pp. 1-4, last accessed Jan. 29, 2010. |
“TCP-Transmission Control Protocol (TCP Fast Retransmit and Recovery),” EventHelix.com, pp. 1-5, Mar. 28, 2002. |
Goglin et al., “Performance Analysis of Remote File System Access Over a High-Speed Local Networks,” 18th International Parallel and Distributed Processing Symposium, pp. 1-8, Apr. 26-30, 2004. |
Harvey et al., “DMA Fundamentals on Various PC Platforms,” National Instruments, Application Note 011, pp. 1-18, Apr. 1991. |
Kim, Hyong-youb, “TCP Offload Through Connection Handoff,” Thesis submitted to Rice University, pp. 1-132, Aug. 2006. |
Kurmann et al., “A Comparison of Two Gigabit SAN/LAN Technologies: Scalable Coherent Interface Versus Myrinet,” Proceedings of SCI Europe '98 Conference, EMMMSEC'98, pp. 1-12, Sep. 28-30, 1998. |
Mangino, John, “Using DMA With High Performance Peripherals to Maximize System Performance,” Texas Instruments, pp. 1-23, Jan. 2007. |
Mogul, Jeffrey C., “The Case for Persistent-Connection HTTP,” ACM SIGCOMM Computer Communication Review, vol. 25, No. 4, pp. 299-313, Oct. 1995. |
Moore et al., “Inferring Internet Denial-of-Service Activity,” University of California, pp. 1-14, 2000. |
Rabinovich et al., “DHTTP: An Efficient and Cache-Friendly Transfer Protocol for the Web,” IEEE/ACM Transactions on Networking, vol. 12, No. 6, pp. 1007-1020, Dec. 2004. |
Salchow, Jr., KJ, “Clustered Multiprocessing: Changing the Rules of the Performance Game,” F5 Networks, Inc., White Paper, pp. 1-11, 2008. |
Stevens, W., “TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms,” Network Working Group, Request for Comments 2001, Standards Track, pp. 1-6, Jan. 1997. |
Wadge, Wallace, “Achieving Gigabit Performance on Programmable Ethernet Network Interface Cards,” pp. 1-9, May 29, 2001. |
Welch, Von, “A User's Guide to TCP Windows,” pp. 1-5, Jun. 19, 1996. |
“Direct Memory Access,” from Wikipedia, pp. 1-6, Jan. 26, 2010. |
“Nagle's Algorithm,” from Wikipedia, pp. 1-2, Oct. 9, 2009. |
Number | Date | Country | |
---|---|---|---|
62642725 | Mar 2018 | US |