WO2021257565A1

WO2021257565A1 - Systems, methods, and media for providing multi-homing

Info

Publication number: WO2021257565A1
Application number: PCT/US2021/037434
Authority: WO
Inventors: Vishal Misra; Daniel S. RUBENSTEIN
Original assignee: The Trustees Of Columbia University In The City Of New York
Priority date: 2020-06-15
Filing date: 2021-06-15
Publication date: 2021-12-23

Abstract

Mechanisms for providing multi -homing, comprising: a memory device; and at least one hardware processor coupled to the memory device and configured to: intercept a connection between a device and a server using a proxy; establish a first connection between the device and the proxy; create multiple second connections between the proxy and the server, wherein at least two of the multiple second connections use different connection types; receive a request for blocks of data from the device using the first connection; allocate the blocks of data across the multiple second connections; request the blocks of data from the server using the multiple second connections as allocated; receive the blocks of data from the server using the multiple second connections; and forward the blocks of data to the device using the first connection.

Description

SYSTEMS, METHODS, AND MEDIA FOR PROVIDING MULTI-HOMING

Cross-Reference To Related Applications

[0001] This International application claims the benefit of United States Patent

Application No. 16/902,157, filed June 15, 2020, which is hereby incorporated by reference herein in its entirety.

[0002] This International application is related to United States Patent Application No.

16/190,122, filed November 13, 2018, which claims the benefit of United States Provisional Patent Application No. 62/585,895, filed November 14, 2017, and which is a continuation-in- part of International Patent Application No. PCT/US2017/053556, filed September 26, 2017, which claims the benefit of United States Provisional Patent Application No. 62/399,518, filed September 26, 2016, and United States Provisional Patent Application No. 62/470,094, filed March 10, 2017, each of which is hereby incorporated by reference herein in its entirety.

Statement Regarding Federally Sponsored Research or Development

[0003] This invention was made with government support under 1822317 awarded by the

National Science Foundation. The government has certain rights in the invention.

Background

[0004] WiFi is a dominant means of connectivity, and yet despite its wide use by consumers, it remains a performance bottleneck for a vast majority of users. There are a variety of reasons that performance suffers, including varying channel quality from mobility of devices, interference among devices, and physical layer characteristics such as multipath, fading, and the rate anomaly problem. In fact, although existing commodity routers permit prioritization of sessions, they are still generally unable to maintain any guaranteed Quality of Service (QoS), even for those prioritized sessions. Even if QoS can be guaranteed at the physical or link layer, it does not translate into throughput or goodput (i.e., the rate of successful transmission after ignoring re-transmissions and any other error correction) at the transport layer due to link layer retransmissions. The impact of this unreliability is even more pronounced as WiFi is increasingly the only shared broadcast link on an end-to-end path, whereas almost everything else is switched. [0005] Unfortunately, existing mechanisms do not sufficiently compensate for these undesirable characteristics, resulting in unpredictable performance.

Summary

[0006] Systems, methods, and media for providing multi-homing are provided. In some embodiments, systems for providing multi-homing are provided, the systems comprising: a memory device; and at least one hardware processor coupled to the memory device and configured to: intercept a connection between a device and a server using a proxy; establish a first connection between the device and the proxy; create multiple second connections between the proxy and the server, wherein at least two of the multiple second connections use different connection types; receive a request for blocks of data from the device using the first connection; allocate the blocks of data across the multiple second connections; request the blocks of data from the server using the multiple second connections as allocated; receive the blocks of data from the server using the multiple second connections; and forward the blocks of data to the device using the first connection.

Brief Description of the Drawings

[0007] FIG. l is a diagram of an example of a system including a transparent proxy in accordance with some embodiments.

[0008] FIG. 2 is a diagram of an example of a process for a scheduling function of a transparent proxy in accordance with some embodiments.

[0009] FIG. 3 is a diagram of an example of hardware on which a transparent proxy can be implemented in accordance with some embodiments.

[0010] FIG. 4 is a diagram of an example of a process for multi-homing in a transparent proxy in accordance with some embodiments.

Detailed Description

[0011] In accordance with some embodiments, mechanisms that transparently provide

Quality of Service (QoS) to applications in a WiFi environment are provided.

[0012] In accordance with some embodiments, a transparent proxy that works at the transport layer and guarantees QoS to certain applications whenever possible and abstracts away rate fluctuations in the physical layer is provided. The transparent proxy can be implemented as part of a WiFi access point, or as a separate device that sits between the access point and a wired connection, in some embodiments. The transparent proxy can provide QoS to applications connected to any WiFi access point.

[0013] An example 100 of a system including the transparent proxy is shown in FIG. 1.

As illustrated, system 100 includes an Internet interface 102, transparent proxy hardware 103 (which can be a general-purpose computer, a special-purpose computer, a router, or any other suitable hardware, and which may run any suitable operating system (e.g., Linux) or no operating system at all), a transparent proxy 104 (which runs on hardware 103), a WiFi access point 106 (e.g., a WiFi router), and applications 108. Applications 108 can be running on any suitable devices for accessing WiFi, such as mobile phones, laptop computers, printers, tablet computers, Internet-of-things devices, cameras, etc.

[0014] As shown in FIG. 1, transparent proxy 104 includes a rate reservation function

110, a traffic splitting function 112, a session splitting function 114, a congestion and goodput measuring function 116, a scheduling function 118, and buffers 120 and 122. Scheduling function 118 uses a rate regulation function 124 and an airtime based forwarding function 126.

As shown, the session splitting function can use TCP instances (TCP-intemet instance 128 and TCP -WiFi instance 130) that are provided by an operating system (e.g., Linux) in which the transparent proxy is implemented, in some embodiments.

[0015] For the purposes of clarity, FIG. 1 only shows the portion of the architecture of the transparent proxy for communication flows toward WiFi access point 106. Although not shown in FIG. 1, the functions of transparent proxy 104 can be replicated for communication flows away from WiFi access point 106, and those replicated functions can behave similarly to what is described herein for the functions shown in FIG. 1.

[0016] In some embodiments, instead of implementing the functions of transparent proxy

104 in a device separate from WiFi access point 106, these functions can be performed in WiFi access point 106 using any suitable hardware (e.g., a hardware processor) therein, and dedicated hardware for transparent proxy 104 shown in FIG. 1 can be omitted.

[0017] As the name transparent proxy suggests, transparent proxy 104 can act as a proxy between applications 108 and other devices with which they are communicating (e.g., such as servers) via a WiFi network. In doing so, communication sessions between the applications and the other devices can be split to form sessions between the applications and the proxy and to form sessions between the proxy and the other devices. This session splitting can be performed by session splitting function 114.

[0018] In some embodiments, when an application initiates a TCP or UDP session, a connection request is sent by the application via the WiFi network to hardware 103 and is redirected by routing functionality (e.g., which can be provided by the hardware's operating system (e.g., Linux)) in the hardware from going to an original destination of the connection request to going to the transparent proxy. A session is then established between the application and the proxy. At the same time, another session is also established between the proxy and the original destination.

[0019] In some embodiments, in order to redirect TCP packets, an iptables command can be sent by transparent proxy 104 to the routing function of hardware 103 to add REDIRECT rules in the routing function's PREROUTING table. The REDIRECT rules can be used to change the destination of packets from going to the original destination to going to the proxy, and from going to the application to going to the proxy, in some embodiments.

[0020] In some embodiments, in order to establish a TCP connection between the proxy and the original destination, the original destination address can be retrieved by transparent proxy 104 from the socket option using getsockopt(...,SO_ORIGINAL_DST,...). For this TCP connection, if the original destination address is in the WiFi network, CUBIC congestion control can be used for the connection in some embodiments. Alternatively, in some embodiments the connection can be managed by the transparent proxy as described below.

[0021] In some embodiments, for UDP packets, instead of using REDIRECT rules in the routing function of hardware 103, the TPROXY rule in iptables can be used to redirect packets. Also, in some embodiments, for UDP packets, instead of using getsockopt, and the original destination address can be retrieved from the header by calling recvmsg().

[0022] In some embodiments, communication sessions can be separated into multiple category service classes, such as: business class; and economy class. Although two classes are illustrated herein, it should be apparent that more classes can be used in some embodiments. In some embodiments, there can be multiple business classes, and the proxy can provide bandwidth guarantees for network sessions in each business class, while the network sessions in the economy class compete for the rest of bandwidth in an unmanaged way. [0023] In some embodiments, the class of a session can be determined using rules based on any suitable information, such as: the application's IP address; the original destination's IP address; the original destination's port number; the protocol number; the application's MAC address; the application's device type (e.g. TV, cell phone, laptop, tablet computer, streaming media player, IP camera, Internet-of-things device, etc.); and the application's hostname. The classification rules can be pre-defmed or specified by a user using a configuration user interface (e.g., which can be presented as a Web page that is hosted by the transparent proxy). For example, in some embodiments, upon receiving the suitable information, the transparent proxy can access a lookup table it maintains, or that is maintained on a remote server, to determine the classification of a session.

[0024] Note that an application may have multiple sessions and it may be hard to identify such sessions as being associated with the application only using transport layer information and network layer information. In some embodiments, any suitable tools (e.g. L7-filter, or HTTP proxy) can be used to identify an application associated with one or more sessions. In some embodiments, if an application supports HTTP proxy, the application can be configured to direct traffic to an HTTP proxy server running the operating system of hardware 103, which will then forward the traffic to the transparent proxy in a manner that identifies all of the traffic as coming from the same application.

[0025] In some embodiments, a class can be selected for a session based on a type of data being communicated in a session. For example, a session can be communicating data for streaming video, streaming audio, voice-over-IP, a file download, web browsing, email, etc. One or more streaming video sessions can be put in one class (or multiple classes), one or more streaming audio sessions can be put in another class (or multiple other classes), and one or more filed download sessions can be put in yet another class (or multiple other classes). In some embodiments, each class can have a reserved rate that is the amount of bandwidth allocated to that class. In some embodiments, a reserved rate for a class can be dynamic. That is, the rate can be altered based on how that rate is impacting one or more other classes. For example, if a reserved rate for a streaming video class is sufficient to support 1080p, but that class is negatively impacting one or more other classes, the reserved rate for the streaming video class can be dropped to a lower level, such as one that only supports 720p, 480p, or 240p. [0026] A class for a session can be determined in any suitable manner, in some embodiments. For example, in some embodiments, a machine learning classifier can be used to determine a class for a session. More particularly, for example, a machine learning classifier, such as a decision tree, a support vector machine, a deep learning based classifier, or any other suitable classifier, can be used to identify a session as containing a particular type of data (e.g., streaming video, streaming audio, voice-over-IP, a file download, web browsing, email, etc.) and based on that determine that the session is to be assigned to a particular class, in some embodiments. Any suitable parameters can be used in some embodiments. For example, in some embodiments, the following parameters for a session can be used by a machine learning classifier to determine a type of data for the session and what class the session is to be placed in: interval(s) between packets for the session; where packets for the session are coming from; where packets for the session are going to; frequenc(ies) of packets for the session; size of packets for the session; and/or any other suitable parameters. A classifier can be trained in any suitable manner and the classifier can be an offline classifier or an online classifier. For example, a user interface can be provided so that a user on a WiFi network can see a list of all sessions on the network and how they are classified, and then the user can provide feedback on whether the sessions are properly classified and/or how the sessions should be classified. In some embodiments, such feedback can be aggregated from multiple separate users and used to update the classifiers of some or all users.

[0027] Returning to FIG. 1, each business class session can have its own buffer 120 and its own buffer 122, while all economy class sessions can share the same buffer 120 and the same buffer 122.

[0028] In some embodiments, for each session between an original destination and the transparent proxy, a buffer 120 (which can be managed, for example, by a Linux kernel of the operating system of hardware 103) stores the data already sent by the original destination, but not yet processed by scheduling function 118.

[0029] In some embodiments, for each session between the proxy and an application, a buffer 122 (which can be managed, for example, by a Linux kernel of the operating system of hardware 103) stores the data already sent by the proxy but not ACK-ed (e.g., acknowledged by a TCP " ACK" message) yet by the application. When the Wi-Fi network is not a bottleneck, the physical transmission rate is greater than the sending rate. In this circumstance, buffers 122 will not hold data very long, and the size of the data in the buffers will be relatively small. On the other hand, when the Wi-Fi network becomes a bottleneck, the size of the data in buffers 122 will become relatively large. Congestion and goodput measuring function 116 of the proxy monitors the sum of the sizes (hereinafter, the "size-sum") of these buffers for all sessions between the proxy and the applications as compared to a threshold to indicate the conditions of Wi-Fi network.

[0030] In some embodiments, to decide if the WiFi network is under congestion, the size-sum of the buffers can be monitored using ioctl(SIOCOUTQ) on the bottleneck interface (which is either the WiFi link between WiFi access point 106 and an application 108 or the wired connection between hardware 103 and WiFi access point 106) and compare it against a threshold. Any suitable threshold can be used in some embodiments. In some embodiments, the threshold can be set to prevent under-utilization while also allowing the transparent proxy to respond after detecting congestion and before an amount of economy data can build up in the buffer that causes a head of the line blocking problem. For example, in some embodiments, the threshold can be set to max(10KB; 0:05s *T), where T is the measured aggregate throughput of all sessions on the WiFi network. This setting of threshold implies that, if the congestion state is triggered, the WiFi needs 0.05s to send all the data in the WiFi part buffers, which further implies that, during a 10ms holding time (described below), the WiFi network always has data to send.

[0031] In some embodiments, for throughput measuring, the goodput of data can be measured instead of its raw throughput. This can be accomplished by measuring on the transport layer so that only the ACK-ed data is counted in some embodiments.

[0032] In some embodiments, if the Wi-Fi network is not a bottleneck, scheduling function 118 in the proxy can forward packets from buffers 120 to buffers 122 in an unmanaged manner. Specifically, in these embodiments, whenever the proxy receives data in one of buffers 120, it forwards the data to the corresponding one of buffers 122.

[0033] In some embodiments, if the Wi-Fi network becomes a bottleneck, scheduling function 118 in the proxy can prioritize the sessions in business class using rate regulation function 124 and airtime-based forwarding function 126.

[0034] In some embodiments, using the airtime-based forwarding function 126, the proxy can prevent the economy class from getting starved even when the business class cannot be satisfied. In doing so, a portion of airtime can be reserved for the economy class so that the business class does not consume the whole network. After the business class consumes an allocated portion of the airtime, or all the sessions in business class reach desired bandwidth, the proxy can then serve the economy class.

[0035] Two counters, airtime_b and airtime_e, can be used to record the airtime consumed by business class and economy class, respectively. Alternatively, in some embodiments, airtime_b and airtime_e, can be used to record the bandwidth consumed by business class and economy class, respectively. In some embodiments, the airtime consumed can be based on actual transmission time which takes into the amount of data transferred and the goodput of one or more sessions. More particularly, in some embodiments, for every packet, its airtime can be estimated by (its packet length)/(data rate) in some embodiments. Here, the data rate can be set to be the measured link rate for that particular session in some embodiments.

[0036] In some embodiments, there are multiple business class sessions, each with a different desired bandwidth. In some embodiments, for each business class session, a token bucket (e.g., a counter) can be used to control the communication rate of the business class session in some embodiments. The token buckets can be initialized with some positive value, such as a percentage for the reserved rate for the corresponding business class session in some embodiments. Every byte of data sent in a business class session can decrease a token in the corresponding token bucket in some embodiments. The tokens for a given business class session can be generated at the reserved rate of that business class session in some embodiments. When there is some token in a token bucket for a business class session, it means the sending rate for that business class session is below the reserved rate, and thus the proxy will forward data for that business class session. When there is no token in a token bucket for a business class session, the desired rate for that business class session is reached, and the proxy will hold the traffic forwarding process for the business class session.

[0037] As mentioned above, in some embodiments, a reserved rate for a class can be dynamic. That is, the rate can be altered based on how that rate is impacting one or more other classes. For example, if a reserved rate for a streaming video class is sufficient to support 1080p, but that class is negatively impacting one or more other classes, the reserved rate for the streaming video class can be dropped to a lower level, such as one that only supports 720p, 480p, or 240p. Likewise, if a reserved rate for a streaming video class is below a maximum rate and all bandwidth on the WiFi network is not being used, the reserved rate can be increased if it is determined that it will not negatively impact other classes. Similarly, in some embodiments, streaming audio classes can have reserved rates that are dynamically controlled.

[0038] In some embodiments, the dynamic control of a class' reserved rate can be based on any suitable parameters, such as: WiFi device physical rate, utility function, airtime constraints, etc. In some embodiments, multiple classes' reserved rates can be determined by solving an optimization problem. More particularly, for example, the optimization problem may be solved to find the best sum of utilities for the multiple classes based on their corresponding utility functions (which may be a step type, a ladder type, a linear type, etc.).

[0039] In some embodiments, when multiple token buckets contain one or more tokens, the transparent proxy can select the business class sessions with maximum tokens to work.

[0040] As mentioned above, in some embodiments, the token generating rate for a business class session's token bucket can be set according to the session's reserved rate bandwidth. When doing so, the tokens will accumulate in the token bucket if the desired bandwidth is less than the reserved rate. To prevent a flow consuming too much bandwidth after a long idle period, the transparent proxy can set an upper limit on the number of tokens in a token bucket in some embodiments. In some embodiments, the limit can be set to be 0.5s * P, where P is the reserved rate. In some embodiments, when a business class session is selected based on airtime share but it has no packet in buffers 120, the system will hold the forwarding action for a tiny while to wait for the packets already in WiFi part buffers 122 to be sent out. In some embodiments, this delay can be any suitable duration, such as 10ms.

[0041] FIG. 2 illustrates an example 200 of a process for scheduling function 118 of a transparent proxy in accordance with some embodiments. As shown, after process 200 begins at 201, the process can determine if the network is saturated at 202. If not, the process can operate on an unmanaged schedule (e.g., pass data as it is received at the proxy without any restrictions or modifications) at 204 and loop back to starting point 201.

[0042] Otherwise, at 206, the proxy can select the minimum of p_e * airtime_b and p_¾ * airtime_e, where p_b and p_e are the desired airtime portion for business class (e.g., 0.9 or 90%) and the desired airtime portion for economy class (e.g., 0.1 or 10%), respectively. If p_e * airtime_b is smaller than p_b * airtime_e, the proxy can determine if any token buckets have tokens, and, if so, select the token bucket with the most tokens at 210. [0043] If there are no tokens in any buckets, then at 216, the process can sleep for a small time frame (e.g., 0.01s as shown in FIG. 2) to wait for the data in the buffer to be processed and then loop back to 201. (Economy data may not be sent at this point, in some embodiments, because doing so may cause the buffer to fill up with economy data and business data to not get a chance to transmit.)

[0044] Otherwise, if a token bucket with tokens is selected, process 200 can determine at

214 whether a data packet for business class is waiting to be sent. If not, process will branch to 216 and proceed as described above. However, if process 200 determines at 214 that a packet is waiting, process 200 can schedule the packet to be sent, add the time for the packet (which can be determined as described above (e.g., as the packet length divided by the goodput rate)) to airtime_b, and decrease the token count for the bucket by the packet length at 218 and then loop back to 201.

[0045] If it is determined at 206 that p_¾ * airtime_e is smaller than p_e * airtime_b, the proxy can determine whether an economy class packet is waiting to be sent at 208. If not, process 200 can branch to 210 and proceed as described above. However, if process 200 determines at 208 that an economy class packet is waiting to be sent, then process 200 can schedule the packet to be sent and add the consumed airtime (which can be determined as described above (e.g., as the packet length divided by the goodput rate)) to the airtime_e counter at 212 and then loop back to 201.

[0046] While the transparent proxy has been described above as being used to control traffic between applications on a WiFi network and other devices on networks separate from the WiFi network (e.g., the Internet), in some embodiments, the transparent proxy can be used to control traffic between an application on a WiFi network and another device on the same WiFi network. In such case, the WiFi access point can be configured to act in bridge mode so that all internal WiFi network traffic is routed through the transparent proxy. For example, traffic from another device on the WiFi network traveling to an application on the WiFi network would travel from WiFi access point 106 to buffers 120 of the transparent proxy, be processed as described above by the transparent proxy, and then travel from buffers 122 to WiFi access point 106 and then to the application.

[0047] In some embodiment, the mechanisms described herein can be used in a multi access point environment. In such environments, a common transparent proxy 104 can be used for all access points, or a different transparent proxy 104 can be used for each access point.

When using a common transparent proxy, because traffic rates on each access point may be different, the transparent proxy can provide separate goodput rate monitors, token buckets, airtime counters, buffers, etc. as described above for each access point. When an application migrates from one access point to another, information necessary to perform the functions described herein (e.g., such as session goodput, airtime counters, buffer sizes, etc.) can be maintained for the flows on both access points until the migration is complete.

[0048] In some embodiments, to control uplink flows in TCP, the flow control mechanism in TCP can be used by delaying the ACK packet. In other words, by delaying ACK packets, inbound data packets can be prevented from being sent to the transparent proxy.

[0049] In some embodiments, the transparent proxy can maintain a persistent TCP pool that has one or more TCP sessions to popular sites (like GOOGLE, FACEBOOK, etc.) that are in an "established" state. When an application initiates a TCP connection to a corresponding site, the transparent proxy can split the requested TCP session (and thereby form a session between the application and the proxy) and use an existing, established TCP session from the pool to use for the connection between the proxy and the site. In this way, the transparent proxy can eliminate the delay associated with the initial handshake process with the site. This technique can also be used for video streaming devices where over-the-top streaming doesn't have as smooth an experience as cable channel switching. Using this technique, the access point can maintain a pool of active connections to popular streaming services and improve the end-user experience.

[0050] In some embodiments, the transparent proxy can additionally or alternatively be used to provide multi-homing services. For example, in some embodiments, the transparent proxy can connect one or more applications (running on one or more devices that are connected to a WiFi router) to the Internet via multiple providers and/or technologies simultaneously and transparently to the application(s).

[0051] In some embodiments, multi-homing can be implemented using the multi-path

TCP (MPTCP) protocol.

[0052] In some embodiments, the proxy can set up any suitable number of connections to a remote site using any suitable type of connections (e.g., wired connections, wireless connections (e.g., an LTE connection, a WiFi connections, any other suitable wireless connection)). The proxy tool can then automatically pick the best path(s) or load balance over the connections based on any suitable metric (e.g., speed, cost, and/or a combination of the same).

[0053] In some embodiments, when using multi-homing, a device running an application can open up a regular connection to a server on the Internet. The transparent proxy can then act as the endpoint for this connection (as if it was the server) and create and control multiple connections to the server.

[0054] In some embodiments, for TCP connections, when the server is MPTCP capable, the proxy can provide an MPTCP proxy that creates and controls the connections between the proxy and the server.

[0055] In some embodiments, for TCP connections, when the server is not MPTCP capable, the proxy can request (in a stateless manner) different blocks of data from the server on the different connections. In this way, the proxy can open up multiple independent connections on behalf of the client device to the server and aggregate them into one unified TCP connection between the device and proxy, in some embodiments. Also, in this way, neither the client device nor server has to be MPTCP capable because the PROXY emulates the capability on their behalf, in some embodiments.

[0056] Turning to FIG. 4, an example 400 of a process for implementing multi-homing in a transparent proxy for TCP connections in accordance with some embodiments is illustrated. Process 400 can be implemented on any suitable hardware, such as hardware 103 illustrated in FIG. 1.

[0057] As shown in FIG. 4, after process 400 begins at 402, the process can wait for a connection from a device (or an application running on a device) to a server. The connection can be any suitable type of connection such as a TCP connection.

[0058] Next, at 406, process 400 can intercept the connection request and route it to the proxy. In this way, the connection is established between the device (or the application running on the device) and the proxy.

[0059] Then, at 408, process 400 can determine if the server is MPTCP capable. This determination can be made in any suitable manner. For example, in some embodiments, when establishing a connection to the server, process 400 can determine if the server responds with an option “MP CAPABLE” to determine if the server is MPTCP capable. [0060] If the server is determined to be MPTCP capable at 408, then, at 410, process 400 can use an MPTCP proxy (such as the one available at www.openmptcprouter.com) to create and control connections between proxy and server and send data between the device and the server in some embodiments. As described above, any suitable number and type of connections can be established.

[0061] If the server is determined to not be MPTCP capable at 408, then process 400 can perform 412, 414, 416, 418, and 420 in some embodiments.

[0062] As shown, at 412, process 400 can create multiple TCP connections between the proxy and the server. As described above, any suitable number and type of connections can be established in some embodiments.

[0063] Next, at 414, process 400 can receive a request for blocks of data from the device on the single TCP connection between the device and the proxy. This request can be received in any suitable manner in some embodiments.

[0064] Then, at 416, process 400 can request blocks of data from the server using the multiple TCP connections between the proxy and the server. This request can be sent in any suitable manner in some embodiments. Any suitable allocation of blocks of data for each connection can be made in any suitable manner based on any suitable metric (e.g., speed, cost, and/or a combination of the same) in some embodiments.

[0065] Next, at 418, process 400 can receive blocks of data from the server using the multiple TCP connections between the proxy and the server.

[0066] Then, at 420, process 400 can forward the received blocks of data to the device using the single connection between the device and the proxy and then loop back to 414.

[0067] In some embodiments, for a UDP connection, or any other type of connection, the process described in connection with FIG. 4 can be modified to use a corresponding connection type (e.g., UDP) instead of a TCP connection type, to use a different multi-path proxy instead of an MPTCP proxy at 410, and to determine at 408 if the server is capable of using that different multi-path proxy instead of being MPTCP capable.

[0068] FIG. 3 illustrates an example 300 of hardware that can be used to implement hardware 103 and/or a portion of WiFi access point 106 in accordance with some embodiments. As shown, hardware 300 can include a hardware processor 302, memory 304, communication interfaces 306, input/output interface(s) 308, and/or any other suitable components. Hardware processor 302 can be implemented using any suitable microprocessor, microcontroller, digital signal processor, field programmable gate array, dedicated logic, and/or any other hardware capable of performing the functions of the transparent proxy described herein. Memory 304 can be implemented using any suitable random-access memory (RAM), read only memory (ROM), magnetic media, optical media, etc. Communication interfaces 306 can include any suitable one way or two-way interface(s) for communicating over wires, optical fiber, airwaves, and/or any other suitable media. Input/output interface(s) 308 can include any suitable interface for receiving user input and/or providing output including keyboards, touch screens, pointer controls (mouse, mice, track ball, stylus, track pad, etc.), displays, audio outputs, etc.

[0069] In some embodiments, any suitable computer readable media can be used for storing instructions for performing the functions and/or processes described herein. This media can be part of or separate from memory 304 in some embodiments. For example, in some embodiments, computer readable media can be transitory or non-transitory. For example, non- transitory computer readable media can include media such as non-transitory magnetic media (such as hard disks, floppy disks, etc.), non-transitory optical media (such as compact discs, digital video discs, Blu-ray discs, etc.), non-transitory semiconductor media (such as random access memory (RAM), flash memory, electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), etc.), any suitable non- transitory media that is not fleeting or devoid of any semblance of permanence during transmission, and/or any suitable tangible media. As another example, transitory computer readable media can include signals on networks, in wires, conductors, optical fibers, circuits, any suitable media that is fleeting and devoid of any semblance of permanence during transmission, and/or any suitable intangible media.

[0070] In some embodiments of the disclosed subject matter, the above described blocks of the process of FIG. 2 can be executed or performed in any order or sequence not limited to the order and sequence shown and described in the figure. Also, some of the above blocks of the process of FIG. 2 can be executed or performed substantially simultaneously where appropriate or in parallel to reduce latency and processing times. Furthermore, it should be noted that FIG. 2 is provided as an example only. At least some of the blocks shown in this figure may be performed in a different order than represented, performed concurrently, or omitted. [0071] The provision of the examples described herein (as well as clauses phrased as

"such as," "e.g.," "including," and the like) should not be interpreted as limiting the claimed subject matter to the specific examples; rather, the examples are intended to illustrate only some of many possible aspects. It should also be noted that, as used herein, the term mechanism can encompass hardware, software, firmware, or any suitable combination thereof.

[0072] Although the invention has been described and illustrated in the foregoing illustrative embodiments, it is understood that the present disclosure has been made only by way of example, and that numerous changes in the details of embodiment of the invention can be made without departing from the spirit and scope of the invention, which is limited only by the claims that follow. Features of the disclosed embodiments can be combined and rearranged in various ways.

Claims

What is claimed is:

1. A system for providing multi-homing, comprising: a memory device; and at least one hardware processor coupled to the memory device and configured to: intercept a first connection between a device and a server; establish a second connection with the device; create multiple third connections with the server, wherein at least two of the multiple third connections use different connection types; receive a request for blocks of data from the device using the second connection; allocate the blocks of data across the multiple third connections; request the blocks of data from the server using the multiple third connections as allocated; receive the blocks of data from the server using the multiple third connections; and forward the blocks of data to the device using the second connection.

2. The system of claim 1, wherein the at least one hardware processor is further configured to determine if the server is multi-path TCP (MPTCP) capable.

3. The system of claim 2, wherein the at least one hardware processor is further configured to determine if the server is multi-path TCP (MPTCP) capable by determining if the server responds with an option “MP CAPABLE” when establishing a connection to the server.

4. The system of claim 2, wherein the at least one hardware processor is configured to perform the intercepting, the establishing of the second connection, the creating of the multiple third connections, the receiving of the request for the blocks of data, the allocating of the blocks of data, the requesting of the blocks of data from the server, the receiving of the blocks of data from the server, and the forwarding of the blocks of data in response to determining that the server is not multi-path TCP (MPTCP) capable.

5. The system of claim 1, wherein the at least one hardware processor is further configured to use a multi-path TCP (MPTCP) proxy to create and control connection with a second server.

6. The system of claim 1, wherein the blocks of data are allocated across the multiple third connections based on speed.

7. The system of claim 1, wherein the blocks of data are allocated across the multiple third connections based on cost.

8. A method for providing multi-homing, comprising: intercepting, by a hardware processor, a first connection between a device and a server; establishing a second connection with the device; creating multiple third connections with the server, wherein at least two of the multiple third connections use different connection types; receiving a request for blocks of data from the device using the second connection; allocating the blocks of data across the multiple third connections; requesting the blocks of data from the server using the multiple third connections as allocated; receiving the blocks of data from the server using the multiple third connections; and forwarding the blocks of data to the device using the second connection.

9. The method of claim 8, further comprising determining if the server is multi-path TCP (MPTCP) capable.

10. The method of claim 9, wherein the determining if the server is multi-path TCP (MPTCP) capable is performed by determining if the server responds with an option “MP CAPABLE” when establishing a connection to the server.

11. The method of claim 9, wherein the intercepting, the establishing of the second connection, the creating of the multiple third connections, the receiving of the request for the blocks of data, the allocating of the blocks of data, the requesting of the blocks of data from the server, the receiving of the blocks of data from the server, and the forwarding of the blocks of data is performed in response to determining that the server is not multi-path TCP (MPTCP) capable.

12. The method of claim 8, further comprising using a multi-path TCP (MPTCP) proxy to create and control connection with a second server.

13. The method of claim 8, wherein the blocks of data are allocated across the multiple third connections based on speed.

14. The method of claim 8, wherein the blocks of data are allocated across the multiple third connections based on cost.

15. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for providing multi homing, the method comprising: intercepting a first connection between a device and a server; establishing a second connection with the device; creating multiple third connections with the server, wherein at least two of the multiple third connections use different connection types; receiving a request for blocks of data from the device using the second connection; allocating the blocks of data across the multiple third connections; requesting the blocks of data from the server using the multiple third connections as allocated; receiving the blocks of data from the server using the multiple third connections; and forwarding the blocks of data to the device using the second connection.

16. The non-transitory computer-readable medium of claim 15, wherein the method further comprises determining if the server is multi-path TCP (MPTCP) capable.

17. The non-transitory computer-readable medium of claim 16, wherein the determining if the server is multi-path TCP (MPTCP) capable is performed by determining if the server responds with an option “MP CAPABLE” when establishing a connection to the server.

18. The non-transitory computer-readable medium of claim 16, wherein the intercepting, the establishing of the second connection, the creating of the multiple third connections, the receiving of the request for the blocks of data, the allocating of the blocks of data, the requesting of the blocks of data from the server, the receiving of the blocks of data from the server, and the forwarding of the blocks of data is performed in response to determining that the server is not multi-path TCP (MPTCP) capable.

19. The non-transitory computer-readable medium of claim 15, wherein the method further comprises using a multi-path TCP (MPTCP) proxy to create and control connection with a second server.

20. The non-transitory computer-readable medium of claim 15, wherein the blocks of data are allocated across the multiple third connections based on speed.

21. The non-transitory computer-readable medium of claim 15, wherein the blocks of data are allocated across the multiple third connections based on cost.